Distributed architecture of forest video monitoring

FIELD: physics, computation hardware.

SUBSTANCE: invention relates to video monitoring of vast forest territories for early detection of forests fires with the help of passive optical location. Proposed system comprises multiple video servers with each video server supports one or more video cameras, one or more target servers and multiple computer terminals. Said video servers analyse video data received from video cameras to reveal ignition indications so that the data on potential danger can be compiled and referenced to video data and to send formed data object to target server. Said target server receives the potential object data object to compare said object with previously stored data on potential danger. Then, proceeding from the results of comparison, the following measures are taken: memorisation of received data object, updating of one of previously stored data objects and updating of received data object to transmit one or more potential danger data objects to computer terminal. The latter receives said potential danger data objects to output them to operator.

EFFECT: efficient organisation of data traffic without application of high-speed channels, flexible control over resources.

22 cl, 13 dwg

 

The technical field to which the invention relates

The present invention relates generally to the field of video surveillance and, more specifically, to a distributed architecture of the video monitoring system of the forest, which, in General, provides the ability to monitor large forest areas with the definition of the coordinates of detected objects using passive optical location with the purpose of early detection of forest fires for their further localization and extinguishing.

Prior art

Of the video monitoring system of the forest, intended for the detection and location of forest fires, have been used recently. However, their relevance is increasing all the time, because the problem of forest fires can rightly be considered one of the most serious and unresolved at the moment, a man of challenges. Forest fires occur and bring great damage in many countries of the world, which can serve as forest fires on the territory of the Russian Federation in the summer of 2010, with catastrophic consequences, including due to failure of early detection and determining their position, what and deployed repeatedly mentioned in the media.

Below with reference to Fig. 1, provides an illustration of the basic structure of the classical�Oh" of the video monitoring system of the forest. Known examples of such systems, video surveillance forests are ForestWatch system (Canada), IPNAS (Croatia), FireWatch (Germany). Similar systems developed in the Russian Federation, such as "Maple", "Baltika".

Illustrated in Fig. 1, the video monitoring system 100 of the forest in the General case includes a plurality of remote-controlled video monitoring points 110 and associated one or more workstations 120 operator for proper operation of the video monitoring points 110.

The equipment 120 of the automated workplace of the operator, in General, is implemented based on the widely known computer and communication technologies and, in the typical case, contains made with the possibility of remote data exchange computer with installed specialized software and software utility. Hardware and software for General purpose (e.g., operating system) included with this computer are widely known in the art. Thus, the term "computer" may be understood in a personal computer, a laptop, a set of linked computers, etc. with the characteristics that meet the requirements of the system 100. Is connected to the computer display device that displays at work�e computer associated with a specialized application with a graphical user interface (GUI), by which the operator performs operation for the visual monitoring and control points 110 video monitoring. Interaction with the graphical user interface is implemented using the well-known input devices connected to the computer such as keyboard, mouse, etc.

Each point 110 videomonitoring, in fact, are the hardware 111 of the transmitting side, placed on a high-rise building 112. High-rise building 112, in General, may be any high-rise construction, satisfying imposed on the system 100 requirements (i.e., adapted to accommodate the equipment of the transmitting side and high enough to ensure the possibility to explore quite a large area), and is normally of the tower of communications providers, the tower operator, television tower, tower lighting, etc.

Generic term "equipment of the disclosing party" 111 denoted placed on a high-rise building 112 equipment containing controlled video device 113 and the communication module 114 to communicate/exchange data with a working space(s) 120 of the operator.

Managed video device 113, in the General case, is a digital video camera 115, equipped with a zoom 116 and smontirovan�Yu on the rotator 117, through which can mechanically change the spatial orientation of the camera 115 with high accuracy.

The hardware 111 of the transmitting side also comprises a device 118 camera control associated with a communication module 114, a camera 115, 116 zoom and swivelling device 117 and intended for General control functions on the managed video device 113 in General and its components in particular. So, for reception of control signals from the operator via the communication module 114 device 118 control is adapted to set the required spatial orientation of the camera 115 (e.g., pointing it at the subject, an observation which is required), the rotary driving device 117, and/or perform a zoom in/zoom out image observed with her object, zoom driving 116. In addition, the device 118 control is adapted to determine the current spatial orientation of the camera 115 and issue data on its current spatial orientation via the communication module 114 to the requesting party (in particular, the workstation operator 120, where the data, for example, shown in the GUI). These functionalities are known properties of modern sets of managed cameras offered in the market.

�disorder 118 management in General, is an obvious for the expert-based microprocessors hardware block type controller, microcomputer, etc., in a known manner is programmed and/or programmable to perform prescribed functions. Programming device 118 control may be implemented, for example, by writing ("firmware") of its firmware ("firmware") that is widely known in the art. Accordingly, with the device 118 camera control, in the typical case, is connected to a storage device (e.g., integrated flash memory), which stores the corresponding (micro)software, the execution of which implements associated with the device 118 management functions.

Jobs 120 of the operator can be associated with points 110 video monitoring, both directly and through a network connection (e.g., network 130) using a widely known and used wired and/or wireless, digital and/or analog communication technologies, the communication module 114 points 110 video monitoring and communication interface of a computer workstation 120 operator must comply with communication standards/protocols on the basis of which such a relationship is built.

Thus, the illustrative network 130 to which podsaedinat�s point of video monitoring and automated workstations 120 operator, can be a network address, such as the Internet. If the installation location of the point 110 of video communication channel a third-party provider, which is the common case, it is preferable to use this channel to connect the hardware 111 of the transmitting side to the Internet. If the installation location of the point 110 of the video there is no direct connectivity to the Internet, apply widely known wireless broadband technologies (e.g., wifi, WiMAX, 3G, etc.) for communication between the hardware 111 of the transmitting side and the access point to the Internet. Similarly connects to the network 130 and 120 jobs operator. In particular, for connecting to the network 130 may be used, depending on the implemented technology access, modem (including wireless), network interface card (NIC) fee for wireless access, etc., external or internal to the computer workstation operator 120.

Typically, the system 100 also includes a network-connected server 130 140 delegated centralized management of a set of points 110 video monitoring and their interaction with the jobs 120 of the operator to ensure safe operation of the system 100. The server 140 in the typical case, ameri� a high performance computer or a collection of interconnected computers (e.g., rack blade server) installed on it(them) a specialized server software, having(their) high speed (optical) connection to the Internet. Hardware/software implementation of such a server is obvious to the specialist. In addition to General management functions of the system 100, the server 140 can carry out different specialized functions, for example it can perform the functions of the video server for the collection and intermediate processing data and providing them to the user on request.

With this method the organization of the video monitoring system of the forest, a single user can monitor controlled territory while managing multiple cameras. In addition, due to the characteristic described above functionality provides the ability to automatically locate the location of the fire in visibility with multiple cameras, using a well-known goniometric method, and the storage in memory (e.g., server 140 or in the computer workstation operator 120) pre-defined patrol routes for quick access and monitoring. Here "tour" refers to a predetermined sequence of changes in the orientation of the camera, �rednaznachena to obtain visual information on the required predefined territory.

It should be noted that the performance of modern electronic hardware helps create the device for control and visualization of the composition of the components of the video monitoring system of the forest with a fairly large user functionality, which greatly simplifies the operator's work. In addition, modern hardware, with a special executable their software can take over some of the functions for the automatic detection of potentially dangerous objects in the video or the photo images received from cameras (for monitoring forests such facilities may be smoke, fire, etc.). Such computer vision systems for searching the image of the dangerous objects can use a priori information about the characteristics of smoke or fire, for example specific movement, color, brightness, etc. of Such computer vision systems are used in many industries ranging from robotics to security systems that is quite detailed, for example, in the publication "Computer vision. A modern approach, by D. Forsyth and J. Ponce, publishing house "Williams", 2004, 928 S.

Such an intelligent subsystem that implements these technologists computer vision in General can be implemented in the workplace operator 120, and ser�'ere 140, and even in the managed device 113.

Above presents a generalized structural description of a classical system of video monitoring of the forest, the principle of which is based on the use of managed cameras. Additional aspects related with the definition and processing of the coordinates of detected objects, more extensively, in particular, in patent publications EN 2458407, WO 2012/118403.

It is worth noting that the creation and deployment of such systems video monitoring forest became possible only in recent years. Only now the number of cell towers has become one that covered the main fire place. In addition, steel is significantly more affordable broadband Internet services that allows you to exchange large volumes of information and to transmit via the Internet real-time video, and decreased the cost of equipment for wireless communication over long distances.

However, in the context of the most urgent tasks of monitoring of large areas (i.e., scope of the subject of Federation or country) to build a system of video monitoring of the forest should consider the following significant problems.

Required a large number of PTZ cameras in the system complicates the process of visual control of the territory: for example, the operator may miss the plot which is seen by the camera, whereas the following examination of this area can occur over a long period of time. Therefore must be used in the automation system and automatic detection, this automation of the discovery process requires significant computational resources and the transfer of large amounts of data.

However, a simple increase in computing power in the present context is not a panacea, as it is extremely challenging to ensure adequate communications infrastructure to transmit data from the video monitoring points (e.g., such as video monitoring point 110 in Fig. 1) in computers, operator workstations (120) and/or the server (140) due to the fact that the required communication infrastructure, in fact, an integral image is characterized by significant spatial spacing and strong heterogeneity.

So, at the moment the technical ability to connect the dots video monitoring to data networks, typically, very limited. In particular, for the broadcast video stream from the video camera standard FullHD default implies the existence of a communication channel with a bandwidth of about 4 Mbps, however, in some places on the way from the camera to the operator is provided only channels of communication with the prop�know capacity of the order of 100 kbit/s, that automatically means the inability to direct the video.

In line with the above problems arising in the solution of the problem of monitoring large areas, it becomes apparent weak suitability of classical systems of video monitoring forest described above.

So, due to the "local" focus of the classic video monitoring systems the principles of their construction does not involve sufficient flexibility and suggest the presence of one server that is running the data processing. This, in turn, implies that the communication infrastructure must be such that its characteristics are enough to transport data from video cameras, analysis and delivery of analysis results to the end user. As mentioned above, the experience of building systems for monitoring large areas said that communication infrastructure, significantly separated geographically, always has a bottleneck (i.e., areas with insufficient bandwidth), which reduce the efficiency of data delivery in General. Only this fact makes the application of classical schemes of creation of system of video monitoring is impractical for large areas, both from the technical and from an economic point of view, because in order to address these bottlenecks assumes large-scale organizacionih high speed communication channels, including the deployment of new equipment, etc., and/or expensive rent existing third-party high-speed links.

In addition, when implied intensive automated processing video data, the concentration of this treatment on the same server is also a problem due to the limited computing resources of a single server.

To illustrate the above, in Fig. 2 roughly shows the need of different classic components of the system 100 video monitoring forest of Fig. 1 in communication channels where the width of the arrow conventionally corresponds to the required bandwidth of the input/output communication channel (not to scale). In this case, under "Internet" means some digital data transmission network that actually has no restrictions on speed.

Thus, in the technique there is a need for building a distributed architecture of the video monitoring system of the forest in a large area, which ensures efficient organization of graphics data, eliminating the need for the widespread use of expensive high-speed channels controlled a large area, and also provides a flexible management of computational resources required for data analysis.

Summary of the invention

For�task of the present invention is to provide a distributed system for video monitoring of the forest with efficient graphics data and to provide the possibility of flexible management of computing resources as well as for an automated method of detection of fire, performed by this system.

According to the relevant to this task aspect of the proposed video monitoring system of the forest. The proposed system contains a variety of video monitoring points, each of which contains a video camera on a high-rise building.

The video monitoring system of the forest also contains a subsystem management-monitoring and primary processing of video data containing one or more video servers. Each video server is assigned one or more points of video from the set to control the cameras these one or more points of video. Each server is associated with cameras assigned points video monitoring through a communication channel to fetch the video taken by these cameras. For example, video servers and video cameras designated points of video monitoring can be connected to high-speed virtual private network (VPN).

In addition, the proposed system includes: a storage subsystem and a secondary data containing one or more object servers; and one or more computer terminals. Mentioned video servers, object servers and computer terminals connected to the network connection.

Each video server is made with the perturbation�ability to: perform analysis of captured images to detect signs of fire, at revealing of signs of fire to form a data object of potential danger, identified a possible fire and to send the data object is a potential hazard in the storage subsystem and secondary processing of video data, preferably by requesting the retention of the data object is a potential hazard in the storage subsystem and secondary processing of video data.

Each object server is configured to: save and modify the data objects of potential danger and to send the data objects of potential danger in the use of computer terminals. Preferably, the object server receives the data objects of potential danger from the subsystem management-monitoring and primary processing of video data.

At each terminal computer includes a client application to provide operator interaction with the subsystem of management of monitoring and primary processing of video data and the storage subsystem and the secondary data. The client application configured to receive data objects of potential danger from the storage subsystem and the secondary data and represent the data objects of potential danger for the operator.

According to the embodiment of the subsystem management-monitoring and feathers�base of processing video data further comprises one or more databases, each video server is arranged to store the received video data, with reference to the associated descriptive metadata, the related database from one or more of these databases.

According to each embodiment of the video server contains a computer-implemented computer vision system for the implementation of video analysis. Computer vision system video server retrieves video data for analysis from the related database. Computer vision system video server while configured to form the data object is a potential hazard to identify signs of fire in the analyzed video data so that the generated data object of potential danger was tied to the video data, which showed signs of fire, and associated metadata describing the characteristics of shooting these video. A computer-implemented computer vision system is preferably made with the possibility of using computer vision algorithms that process the video information in accordance with the peculiarities of functioning of the chambers and the current shooting conditions and allows the detection of signs of fire.

According to each embodiment of the object server is additionally performed with the opportunity to use�gestu: to compare the received data object is a potential hazard with the previously stored data objects of potential danger in order to find data objects of potential danger, having a relationship with the received data object of potential danger. The results of comparing the object server is arranged to perform at least one of storing the received data object of potential danger, modifying at least one of previously stored data objects of potential danger and modifying the received data object of potential danger. Preferably, the object server is configured to, when identifying the previously stored data objects of potential danger of a data object of potential danger, essentially coincident with the received data object of potential danger, to adjust characteristics of an identified data object of potential danger based on the characteristics of the received data object of potential danger, without saving the received data object is a potential danger.

According to each embodiment of the object server is arranged to maintain all changes to all data objects of potential hazards that exist on it, including after the removal of the data objects of potential danger.

According to the embodiment of the subsystem management-monitoring and primary processing of video data further�individual contains a controller video servers, connected to the communication network, for controlling the operation of the video servers. Controller video servers configured to dynamically balance the load between the video servers. Controller video servers preferably contains diagnostic tools and analysis of the current and the average load on the video servers, and the load includes the computational load and network load graph. Video servers receive a list of video monitoring points assigned to them for maintenance, controller video servers. Controller video servers preferably configured to automatically perform dynamic remapping pixels video monitoring / video servers depending on the load on the video servers, while each video server is preferably configured to monitor its list of points of video monitoring for changes in the controller's video servers.

According to the embodiment of the proposed video monitoring system of the forest further comprises one or more servers environment users to control and configure the access of operators to the components and resources of the video monitoring system of the forest through the client application, as well as for routing, in conjunction with client applications, the data needed�IIR operators to work. Each client application is configured to dynamically determine, in cooperation with the server environment, users, and visualized for the operator information is available for the operator components and resources of the video monitoring system of the forest. The client application is configured to render to the operator a list of available operator for object servers, the list is available to the operator of the video servers and the list of available cameras that are serviced by these encoders. The client application is configured to provide the operator with the ability to access the video data received in real time from any one of the available video cameras, or the video data stored previously taken any of the available video cameras, and control the work of any of the available cameras.

According to each embodiment of the client application is configured to render to the operator a list of data objects of potential danger received from the object server; when you call the operator to any data object of potential danger from a list of data objects of potential danger, request stored video data in a database associated with the data object of potential danger, and associated metadon�s on the corresponding video server; to visualize the data object referred to the potential danger to the operator by visualizing the received video data and associated metadata; and provide the operator the possibility to confirm or not to confirm a possible fire, which signaled the rendered object data potential danger.

According to the embodiment of the implementation, the client application being configured to assign pixels of the video encoders and/or with a territorial area of responsibility of each of the object servers.

In accordance with implemented the proposed video monitoring system forest method for detection of fire by the video server of the plurality of video encoders: accept video data from at least one camera; perform analysis of the video data to detect signs of fire; at revealing of signs of fire form the data object of potential danger, identified a possible fire, with reference to the video data, which showed signs of fire, and, preferably, with additional reference to the metadata that describes the characteristics of shooting of video data; and sending the data object is a potential hazard in at least one of the object servers.

Through objects�tion server: accept the data object is a potential hazard; compare the received data object is a potential hazard with the previously stored data objects of potential danger; the results of comparing the carry out at least one to save the received data object of potential danger, modifying at least one of previously stored data objects of potential danger and modifying the received data object of potential danger;

and send one or more data objects of potential danger in at least one computer terminal.

Through a computer terminal: take the data objects of potential danger and represent data objects of potential danger for the operator.

According to the embodiment of the implementation of the detection results of the aforementioned comparison among the previously stored data objects of potential danger of a data object of potential danger, essentially coincident with the received data object of potential danger, modify the identified data object is a potential hazard based on the received data object of potential danger, without saving the received data object is a potential danger.

According to the embodiment of the proposed method additionally contains the stages at which, through the computer�minal: for the operator to visualize the list of data objects of potential danger, received from the object server; when you call the operator to any data object of potential danger from a list of data objects of potential danger, requesting video data associated with the data object of potential danger, and associated metadata in the appropriate video server; visualize the data object referred to the potential danger to the operator by visualizing the received video data and associated metadata; and provide the operator the opportunity to confirm or not to confirm a possible fire, which signaled the rendered object data potential danger.

A list of the drawings

The above and other aspects and advantages of the present invention are disclosed in the following detailed description, given with reference to the figures of drawings, on which:

Fig. 1 is a schematic partial illustration of the video monitoring system of the forest.

Fig. 2 - illustration of the requirements of the components of the system 100 of Fig. 1 in communication channels;

Fig. 3 is a General illustration of the video monitoring system of the forest according to the present invention;

Fig. 4 is an illustration of detection of a potentially dangerous object with two cameras;

Fig. 5 is an illustration of the General scheme of interaction of the client application with the components of the system 300 by f�G. 3;

Fig. 6 is an illustration of the territorial structure of the system 300 of Fig. 3;

Fig. 7 is a logical block diagram of the method of fire detection according to a preferred embodiment of the present invention;

Fig. 8 is an illustration of messaging for the example of Fig. 4;

Fig. 9, 10 - illustration of direct work with a video camera from a client application;

Fig. 11 is an illustration of a camera control via the video server;

Fig. 12 is an illustration of the commissioning of the new video server;

Fig. 13 is an illustration of the transfer of servicing of cameras from one video server to another.

Detailed description of the invention

According to the present invention proposed distributed architecture of the video monitoring system of the forest includes the following main components:

- distributed points videomonitoring;

- management subsystem-monitoring and primary processing of video data;

- the storage subsystem and the secondary data;

- computer terminals operators.

Aspects of the proposed architecture in terms of video monitoring points, each of which contains a network camera on a high-rise building similar to the respective aspects of classic video monitoring system 100 of the forest as disclosed above with reference to Fig. 1.

Also, low-level and�aspects of computer terminals from the structure of the proposed system are similar to corresponding aspects of workstations 120 operators of the system 100. However, as mentioned earlier, each terminal computer includes a client application to provide operator interaction with the subsystem of management of monitoring and primary processing of video data and a storage subsystem and a secondary data processing.

Below with reference to Fig. 3 will be described in detail a preferred embodiment of the distributed system 300 video monitoring of the forest according to the present invention.

Subsystem 320 management-monitoring and primary processing of video data includes one or more video servers 3210, which all together are considered as video servers farm.

Each video server 3210 assigned one or more points 310 video monitoring to control their cameras and get shooting their video. By "governance" in this case means, including inherent to the above classic video monitoring system of the forest aspects of the job for camcorder patrol, spatial orientation and zoom (e.g. pointing to a specific object on the ground), calibration, etc.

Because it means getting from cameras large amounts of data, including real-time video servers 3210 geographically placed so that the encoders were connected to the respective �310 glasses video monitoring using channels with sufficient bandwidth (e.g., a width of at least 4 Mbit/s, as above). Figuratively speaking, video servers 3210 placed in close logical proximity" from their respective points 310 video monitoring. For example, the video server 3210 may be known to a person skilled way connected with its designated points of video monitoring through a high speed virtual private network (VPN), where the speed between the video server and the array of cameras is 30 Mbps and above. In this case, the video server 3210 may be configured with the ability to adjust parameters such as the number of frames per second, the compression parameters of the video stream, the type of shoot with the camera information, etc., to provide the required bandwidth with video cameras.

Each of the video servers 3210 receives video data captured hosted by cameras.

Subsystem 320 management-monitoring and primary processing of video data may further include one or more databases 3220 data so that the video servers 3210 can store data and retrieve data from them. The term "database" in this case refers to the physical storage large capacity and stored therein data that is organized accordingly. Although base 3220 data in Fig. 3 shows the individual in relation to live video from�rorem 3210, for the specialist should be obvious that at least some of the bases 3220 data can be integrated with the respective video encoders 3210 (e.g., database data may be stored in storage device(s) from the server).

Each video server 3210 preferably stores the broadcast video data from the cameras in the related database(s) 3220 data.

According to a preferred embodiment of the when a route or route systems video server 3210 on the camcorder sends a command to the positioning of the camera to the preset position of the camera or repositioning of the camera to a new position shooting. Wherein the video server 3210 captures shooting parameters, such as the ID of the camera, the target azimuth angle, depression angle, revealing lens, the actual azimuthal angle, depression angle, revealing the lens, shooting time, etc. Upon reaching the desired camera position the camera is video and the captured video data is sent to the video server 3210.

The captured video data is then stored by the video server our database 3210 3220 data recorded together with the parameters that make up the metadata associated with the video, using the formats and/or data compression methods, which are widely known in the art. The above � other possible options components of descriptive metadata that can be logically organized by any suitable method known in particular in the field of programming (e.g., data structure).

According to a preferred embodiment of the preservation of video data is performed as follows. From the captured video data of the video server 3210 known manner captures a still image and records together in the database a predetermined number of frames of the video stream constituting the video, and two static images (full size and miniature), consisting of recorded still images. Static images can be saved in the database using any of the well-known formats, such as JPEG, TIF, PNG, etc., and the video can be respectively stored in the database using, for example, such well-known format such as MPEG, the duration (number of frames) of the video can be preconfigured or dynamically selected by the video server.

In accordance with the present invention, each video server 3210 is configured to analyze the captured video data to detect signs of fire.

This analysis, according to a preferred embodiment of the present invention, a system is� computer vision, realized in the structure of the video encoder 3210, in relation to video data that is extracted from the database 3220 data. As mentioned earlier, the use and possible hardware and software implementations of computer vision systems are widely known in various fields of engineering. The analysis can be performed on demand, continuously, on a schedule or otherwise.

Retrieve the required video data and metadata from a database can be accessed via the macropoker representing the unique identifiers of the camera, the patrol route and/or specific fact of shooting in the route that uniquely identifies the video, which was filmed with the camera. This set of identifiers forming the reference, uniquely identifies within the system every fact shooting each camera and allows you to get himself relevant video content and associated metadata, describing it.

A computer-implemented computer vision system analyzes the extracted content for signs of inflammation, i.e. the detection in multimedia content of potentially dangerous objects (VET), such as, for example, smoke, fire, etc., in accordance with the above statement and determine their geographic location. According to the present invention, the computer vision system form�servers configured by identifying signs of fire, to form a special data object of potential danger, characterizing the identified VET. It should be understood that Poo detected by the vision system in video do not necessarily correspond to the actual fire, but it may be the consequence of a false alarm of computer vision systems.

It should be noted that in the computer vision system can be used computer vision algorithms to ensure the detection of signs of inflammation and considering features used video cameras and shooting conditions.

According to a preferred embodiment of the formed object data potential hazards may include: name, which is automatically found for VET is formed from the name of the camera, with which he was found, and time at the time of detection; estimation of the coordinates of Poo; assessment of the area in which the can is Poo; the degree of assurance for VET, found by the vision system (so, finding signs of Poo when re-inspecting the site, increases the degree of confidence); status (unconfirmed person, verified person), etc.

The above and other possible parameters can be logically organized into a data object is a potential hazard for any�walking way known, in particular, in the field of programming (for example, in a structure or class).

Extracted metadata are also used in calculations performed by the computer vision system. In particular, upon detection of PIAs in the frame, the computer vision algorithm gives its coordinates in pixels, and to restore, where the VET could be in the area, need to know where and how the camera "looked" when shooting material constituting the analyzed content.

According to the present invention, the object data of potential hazards is formed with reference to the video data, which identified the appropriate VET. As mentioned earlier, our database 3220 data, video, video server 3210 stored multimedia data with the relevant metadata, where in the present case, the multimedia data preferably includes a video and two static images (full size and miniature), which depicted the VET revealed. For this purpose, the corresponding data object of potential danger additionally included a link to the associated multimedia data and associated metadata by which they can be retrieved from the database. A possible implementation of such a link described earlier.

Although the above has been described the preferred approach to snoozetime computer vision, it should be understood that potentially dangerous objects can be detected in other ways, for example manually by the operator when otsmatrivali video. In this case the corresponding data object of potential danger can be properly formed at the request of the operator installed on the terminal client application, providing the appropriate functionality.

Video servers 3210 is connected to the global network 360 communications, such as the Internet. The generated data object of potential danger is sent to the video server via the network 360 communications subsystem 330 storage and secondary processing of video data, preferably by requesting its preservation in the subsystem 330 storage and secondary processing of video data.

Subsystem 330 and secondary storage data includes one or more object servers 3310 connected to the network 360 with the ability to communicate with video servers 3210.

Each object 3310 server is arranged to store and to modify the received data objects of potential danger.

According to a preferred embodiment of the object in the server 3310 is provided by the device(s) storing data that stores the data objects of potential danger, and the object 3310 server compares the received volume�CT data of potential hazards with previously stored data objects of potential danger. The data object is a potential hazard may be received by the server 3310 from subsystem 320 management-monitoring and primary processing of video data, as described earlier, or from another component of system 300 video monitoring forests, for example, from the terminal 340 operator manual approach shown above. It should be noted that the functioning of the object servers 3310 does not depend on what a particular source, they accepted the data object is a potential danger.

At the specified receiving object 3310 server may adjust as newly received data object of potential danger, and existing objects data objects of potential danger if between incoming and how(and) any of the existing data objects of potential danger, the relationship identified.

In particular, when identifying the previously stored data objects of potential danger of the object data corresponding to (e.g., matches) the received data object of potential danger, the object server 3310 adjusts the characteristics of the identified data object on the basis of characteristics of the received data object. If the data objects corresponding to the received data object of potential danger, missing among the previously stored data objects of potential danger,�spine, then the object 3310 server stores in its storage device the received data object as a new data object of potential danger.

The above operation object servers 3310 further illustrated based on the example of detecting one VET with two cameras that are managed by different video servers, which is discussed with reference to Fig. 4.

During the analysis of the video stream, each of the two video servers makes the decision about being in the frame of the signs of a potentially dangerous object and creates a corresponding data object of potential danger. Further, each of them reports about the discovery of Poo object to the server by sending to it the generated data object of potential danger. The object server stores the received data object of potential danger, but on the basis of the second received data object of potential danger decides to clarify the characteristics of the stored first data object instead of storing the second data object of potential danger. In this case, when the specified correction of the characteristics may be adjusted, at least some of the parameters that make up the data object of potential danger, which is given above.

In the above example, apart from the fact that the object server does not save, p� fact, duplicate data objects, deriving the benefits of corrected parameters of the data objects of potential danger:

- reduced likelihood that the VET discovered are false positives in computer vision systems;

- increase the accuracy of the layout area of a potential fire;

- improving the accuracy of calculating the coordinates of the center of ignition, for example, by performing triangulation based on the known coordinates of two cameras, which caught fire, and two direction vectors on the fire.

It should be noted that each object server 3310 can be configured to maintain and store a history of all changes to the data objects of potential danger that it manages, including after the removal of objects (e.g., operator).

Each object 3310 server sends the stored data objects of potential danger on computer terminals 340 operators connected to the global network 360 communications, which sending can be performed on demand or automatically. A client application installed in each of the operator terminals 340, configured to receive data objects of potential danger from the subsystem 330 and secondary storage data � presentation of received data objects of potential danger for the operator, preferably, by visualizing on the display screen in the GUI associated with the client application.

According to a preferred embodiment, the client application configured to render to the operator in the appropriate area of your GUI interactive list of data objects of potential danger, obtained from the available object servers. The operator can select any data object of potential danger from their list, using known input device such as a mouse. When activated by the operator of the interactive element of the list associated with the selected object data of the potential danger, the client application sends via the network 360 to the appropriate video server a request for multimedia data associated with this object data and associated metadata.

As mentioned earlier, the data object is a potential hazard includes a reference to its associated captured video data and associated metadata. As a consequence, the link of the requested multimedia data such as video and picture Poo) are extracted from the video server database, together with descriptive metadata, and through the network 360 are transmitted to the terminal, where the user in the GUI of the client application can view them. For example, when polzovatelskom reviews archive video him in the GUI also provides metadata showing, in particular, when and where "seen" by the camera while recording a video. Also, when you view an interactive list of data objects of potential danger, the GUI can appropriately be submitted to the associated thumbnail image.

The client application additionally provides the operator the possibility, according to the results view, to confirm or not to confirm a possible fire, which signaled the rendered object data of the potential danger. This functionality can be obviously implemented in the GUI. Thus, in the structure of the data object of potential danger can be changed above status, which at its creation was by default set to "not confirmed person" to "confirmed the man."

In addition, in the GUI of the client application may be provided in a known manner remove functionality of the object(s) data of potential hazards in an interactive list (for example, if the operator determined that the data object corresponds to the potential dangers of false triggering of computer vision systems).

According to a preferred embodiment of the proposed system 300 video monitoring �ECA includes one or more servers 350 entourage users connected to the network 360 communications. Servers 350 environment provides users the ability to log in and store associated with the user data that the system needs to correctly set up the user environment when working. In other words, the server environment provide control and configuration of access of operators to the components and resources of the system 300 video monitoring forest through the client application installed nor their computers 340, and ensure, in conjunction with client applications, routing information needed by the operators to work.

The possible implementation of such a service environment users are widely known in the art (such as Active Directory from Microsoft Corporation).

Naturally, the proper interaction of operators with the components of system 300 may be arranged in a known manner and without the use of servers 350 environment users, however, their presence is preferred for optimal organization of remote work operators in the system.

Further, according to another preferred embodiment of the present invention subsystem 320 management-monitoring and primary processing of video data further comprises a controller 3230 video servers connected to the network 360 communications management function�the implementation of video servers farm 3210. The controller 3230 video servers configured to dynamically balance the load between the video servers video servers farm.

According to a preferred embodiment of the video server 3210 receives from the controller 3230 video servers list video monitoring points 310, assigned to him for service. The controller 3230 video servers configured to dynamically reassign points of the video encoders depending on the computational load on the video servers and the distribution graph of the data. The video server 3210 performs continuous monitoring of your list of points of video monitoring for its change controller 3230 video servers.

So, at the start of the video server 3210 defines the list of video monitoring (video cameras) for which he is responsible, and starts continuous monitoring of this list in case it changes in the course of further work. If the list of controlled video cameras change in the course of the video server, new threads are generated by control video cameras to video cameras, which were included in the boundaries of responsibility of a given video server, or destroyed existing threads, if any cameras are the responsibilities of the video server.

Continuous monitoring of the list allows the administrator�m system quickly transfer the processing chambers from one video server to another, thus balancing the load on the communication channels, the computational resources and, if necessary, replacing a failed video store partial use of available capacity multiple video servers running. This, in particular, in the case of available free resources video servers to reduce the time of malfunction of the camcorder due to defective processing of the video server to several tens of seconds.

For automatic (re)load-balancing between the video servers in the system 300 may provide diagnostic tools and analysis of the current and the average load on the video servers. Such diagnostic tools are widely known in the art and may be implemented as software, for example in the controller 3230 video servers.

On the operator's side in the system 300 video monitoring forest provides a variety of functionality for managing, configuring, and operating systems that are provided through the client application in the computer 340. In this case, under "client application" necessarily refers to the same client application that is used by the operator to work with data objects of potential danger according to the above statement, - e�about maybe a separate app which are available only to users with administrator privileges.

According to a preferred embodiment of the client application with such administrative authority may provide functionality to (re)appointment of cameras / video servers for maintenance, job multiple object servers and (re)assign areas of responsibility of each of the object servers, (re)assign to each operator a list of available object servers and the list of available video servers, etc. Corresponding configuration settings can be stored on servers, 350 environment, including in the form of a user profile that is downloaded from the server 350 of the environment on the computer 340 operator when logging in or when you start the computer 340. In the client application on the terminal 340 of the operator, respectively, provides the functionality of visualization in the GUI the list of available operator for object servers, the list available to the operator of the video servers and the list of available cameras that are serviced by these encoders. This visualization can be carried out in collaboration with the service environment users.

The definition of client application services and system components with which it must interact DL� execute custom tasks, may occur not only when the application starts or logical operator input to the system (e.g. downloadable from a server environment profile), but also to run constantly in the process of his work, so that the user application at any time had actual list (s).

According to a preferred embodiment of the video monitoring system of the forest can be structured on quotas by region basis. So, the region is assigned to provide services for its object the server(s), video camera, objects (e.g., towers, etc.), are determined by tracing its operators, and is assigned to a group of video servers, directly or indirectly, through determination of the cameras region. As a result, the user can gain access to system resources belonging only to the corresponding region.

The client application may also include functionality providing to the operator to exercise direct access to the video data received in real time from any one of the available video cameras, or the video data stored previously taken any of the available cameras in order to view them, as well as management functionality of any of the available cameras, what are the functional capability�, in General, typical of classical surveillance systems. In more detail this aspect is discussed below.

The General scheme of interaction of the client application with the components of the system 300, from the point of view of the received data shown in Fig. 5.

For the specialist should be obvious that the number, specific geographic location and operational characteristics of 310 points, video surveillance, video servers, 3210, bases 3220 data controller 3230, object servers, 3310, servers, 350 environment, operator terminals 340, in General, defines the technical and economic requirements of deployable video monitoring system of the forest. Low-level aspects of all of the servers system 300 is essentially similar to low-level aspects of server 140 classic video monitoring system 100 of the forest. Configuring these servers to perform their functions according to the present invention described above, by installing them specialized software, which in its execution require a corresponding server to perform the corresponding functions. This may be internally developed software, including using commercially and publicly available programming environments, libraries, APIs and packages, registered about�program ensuring or combination of the above. Networks of communication and exchange of data/signals can be realized on the basis of any appropriate network solutions and technologies.

Further, for sake of clarity, Fig. 6 shows an example of territorial location of the proposed system. The figure shows three geographically distinct from other groups of cameras. Obviously, if the video server was somewhere in one place, as in the case of a classical system of video monitoring of the forest, and communications infrastructure would have to provide transportation of video data from all cameras to this server. In fact, this would mean the need to have a high bandwidth channels across the country that de facto unwieldy. Therefore, in the proposed video monitoring system forest video servers placed in close logical proximity to the points of video monitoring and connected to local channels with high bandwidth. In this case, with the rest of the system (i.e. with a global network 360) video servers are connected by channels with not such a high throughput, since, in accordance with the above, due to the applied filtering of video information stream generated by the video server, an order of magnitude smaller in volume than the stream from the cameras. So, for a comfortable operation of the system, for podsoednineny� video server 3210 to the network 360 is sufficient channel width of 3 Mbps, whereas, according to the above, VPN, locally connecting the video server 3210 with a hosted video monitoring points 310, provides a throughput of 30 Mbps and above. At the expense of conforming to the present invention the data processing in the system, its proper functioning will be ensured, and when the width of the external channel from the video server to 512 kbps.

The possibility of territorial and logical distribution of video and object server according to the present invention not only provides flexibility when planning the deployment of the system based on existing communications infrastructure, but also allows to optimize the operating costs of maintaining the servers, as it allows to deploy services on the platforms on which the price/reliability/power infrastructure is optimal.

Below with reference to Fig. 7 describes a preferred variant implementation conforming to the present invention of a method 7000 automated fire detection, implemented in the system 300 video monitoring of the forest.

In step 7010 position the camera point 310 video monitoring in accordance with pre-determined route patrol site and start the video.

In step 7020 video server 3210 receives video data from the video camera and on stage 7030 performs the analysis of videoda�tion to detect signs of fire.

In the absence of fire (branch "No" in step 7040) may be running a second pass of the route (return to step 7010) or performed the repositioning of the camera on the new route.

At revealing of signs of fire (the branch "Yes" in step 7040) video server in step 3210 7050 generates the data object is a potential hazard identified for a possible fire hazard, with reference to the video data, found evidence of fire, and metadata that describes the characteristics of shooting video.

Then, in step 7060 video server 3210 sends the generated data object of potential danger in the object server 3310.

In step 7070 object 3310 server accepts the data object of potential danger, and in step 7080 matches the received object data with previously stored data objects of potential danger to identify among these data objects potential dangers corresponding to the received data object is a potential danger.

If such corresponding data objects of potential danger is not revealed (branch "No" in step 7090), the object server in step 3310 7100 stores the received data object.

If the identified object data potential dangers corresponding to (e.g., matches) the adopted data object (the branch "Yes" in step 7090), in step 710, the object server 3310 adjusts the parameters of the identified data object based on the parameters received data object of potential danger, without saving the received data object.

In step 7120 object 3310 server sends one or more data objects of potential danger in a computer terminal 340 operator.

In step 7130 in the GUI client application on a computer terminal 340 is visualized for the operator interactive list of data objects of potential danger received from the object server 3310.

In step 7140, the operator accesses a data object of potential danger of the visualized their list, resulting in step 7150 client application requests the multimedia data associated with this data object the potential hazards and associated metadata in the appropriate video server 3210.

In step 7160, the client application renders the received media data and associated metadata for analysis by the operator.

In step 7170, according to the results view, the operator by the client application confirms or does not confirm a possible fire, which is signaled by a data object of potential danger.

Fig. 8 illustrates the dynamic aspect of the example operation of the system when the same VET two cameras, video servers managed by different, which was discussed above with reference to Fig. 4.

PR�llorenna in this application two-stage scheme allows to perform the most demanding part of the job (actually, analysis of the video system computer vision) video servers, computing power which is scaled due to the commissioning of the new video servers and is balanced by redistributing responsibility for managing the cameras, which will be discussed in more detail below. In the second phase, decisions are made object servers on the basis of the results of processing performed by the video servers. This stage requires much less computing resources, and this fact allows us to reduce the inflow of notifications from a plurality of video servers on one object server and make decisions on the basis of information from hundreds and even thousands of cameras.

Below describes the additional functional aspects of the claimed the video monitoring system of the forest.

So, with reference to Fig. 9, 10 direct work is illustrated with a video camera from a client application on a computer operator.

As mentioned earlier, in addition to the long list of data objects of potential danger, the client application provides the operator with the opportunity to work directly with the video.

After initialization, the client application has the information about which of the available cameras are serviced by various video servers. All scripts are user multimedia data in �the system boil down to two modes of operation with the camera:

- get direct access to the camera in real time (Fig. 9);

- retrieve archived video data captured with a camera (Fig. 10).

Both of these modes lead to the implementation of the communication between the client and the video server.

In the case of direct access to the camcorder, the video server must be advised of the desire of the operator to obtain such access, because the video server itself obliged to stop their own work with the camera (to stop the repositioning of the camera video stream and eat), as well as to set the camera in a mode that prevents granting access to other users. Thus, the operation of the system according to the present invention (e.g., according to Fig. 7) is suspended.

The camera is controlled via a video server for unified access to cameras and access control (see Fig. 11). Indeed, direct access to the camera should be allowed to only one user, because in the opposite case may be provoked conflict management, but also because of the need to transmit two video streams can be overloaded channel access to the camera. At the same time that the server holds the camera in this mode is limited. If the user application does not confirm the extension of the location of the camera in the mode Pramogu� access the camera is considered to be transferred to automatic operation.

Also, many of the scenarios described in the system involve the display of the user multimedia archive of data collected from cameras and video encoders. With all of these scenarios lead to the implementation of one of two types of requests to the video server:

- obtaining descriptions of multimedia data satisfying formulated by the client application criteria (for example, data taken with a specific camera or route data associated with certain objects, etc.);

- getting themselves multimedia data (thumbnails, images, and video).

Unlike direct access, archive data can get multiple users at once. The number of users is limited only by the bandwidth of the data channel from the server.

Next, with reference to Fig. 12 shows the commissioning of the new store, to illustrate the scalability of the system.

As can be seen from Fig. 12, the process consists of two steps - configuring the video server, during which he addresses to the controller for the list of cameras for maintenance, and initialization of the video store, in which he determines the availability of video cameras, entrusted to him in service. During the first phase of informing the Kli�niskich applications about the fact the beginning of service of cameras, assigned to service the video server. In the second phase, the video server informs the client application about the status of cameras and willingness to fulfill the user's requests for cameras it serves.

If the system administrator has the option to bind the service of one or another camera to the video server, or to indicate that the camera is serviced by any server that has the resources, in which case the controller stores independently decides what the video server should serve such a camera.

For the operator this process is hidden. The operator will know only about the fact that the maintenance of the cameras as they become available to him.

In a similar way, and the commissioning of new cameras.

Next, with reference to Fig. 13 shows the transfer of the servicing of cameras from one video server to another to illustrate the robustness of the system.

As mentioned earlier, such a transfer is necessary to balance the load on the video servers when you change the conditions of their operation (for example, when reducing communication bandwidth) or when decommissioning servers with the transmission serviced cameras another video server(s).

Transfer service accompanied with a notification of the video server to the donor about what camcorder would you�Eden from the zone of its service, then the video server the donor immediately terminate the service of this camera, and notice the video server-acceptor that the list of accepted them video cameras also changed (see Fig. 13). In this case, for the operator of such a reconfiguration is accompanied by a short (a few tens of seconds) the output of the camera out of service.

The proposed distributed architecture of the video monitoring system has a certain degree of component commonality, which positively affects the reliability and cost of its operation. Indeed, due to the fast mover video servers cameras they serve, fast input/output of video servers from the system, as well as reconfiguration of the system for the purpose of redistribution of computational load. This fact has a direct impact on the cost of operating a farm video servers. Indeed, as video servers contain critical user and performance data, and the system has the ability to quickly change the scheme of service of video cameras, the requirements for secure video servers can be reduced, and the reliability of the overall system in this case will not be reduced due to the possibility of rapid replacement of defective video servers.

Although the Infor�recovery flexibility of the disclosed system signal and is accompanied by a corresponding complexity of its implementation (in comparison with classical systems), this complication does not affect the operating experience of the end users (operators), since the information about the logical and physical configuration of the monitoring system is hidden from the user. Users during operation operating concepts of the subject area, such as a camera, grounds, detected objects, while the client application together with the service environment perform correct routing of data required for the user to work.

Thus, the disclosed approach provides the following tasks and receipt of appropriate benefits:

- placement of the system components taking into account the heterogeneity of the communication infrastructure for data transmission with a lower overall load on the communication channels;

- flexible management of computational resources required for data analysis;

- execute multi-step data analysis, which is constantly generated by the cameras big data is filtered and analyzed in close logical proximity to the cameras, and further data processing, which occupy a significantly smaller volume compared to the original, requires less resources of the communication infrastructure;

- reduction of costs of operation of the system without reducing its reliability.

Invent�s has been disclosed above with reference to specific variations in its implementation. Within the substance of the above disclosure, for professionals can be obvious and other variants of implementation of the invention differs from those described in the present description. Accordingly, the invention should be considered limited in scope only by the following claims and its equivalents.

1. The video monitoring system of the forest that contains:
many video monitoring points, each of which contains a video camera on a high-rise building;
subsystem management-monitoring and primary processing of video data containing one or more video servers, each video server is assigned one or more points of video from the set to control the cameras these one or more points of the video monitoring system, and each server is associated with cameras assigned points video monitoring through a communication channel to fetch the video taken by these cameras.
the storage subsystem and the secondary data containing one or more object servers; and
one or more computer terminals,
wherein said video servers, object servers and computer terminals connected to a communication network,
each video server is capable of:
perform analysis of captured images to detect PR�signs of fire,
at revealing of signs of fire to form a data object of potential danger, identified a possible fire, and
to send the data object is a potential hazard in the storage subsystem and secondary processing of video data, wherein each object server is arranged to:
save and modify the data objects of potential danger, and
to send data objects of potential danger in computer terminals,
at each terminal computer includes a client application to provide operator interaction with the subsystem of management of monitoring and primary processing of video data and the storage subsystem and the secondary data, wherein the client application is configured to receive data objects of potential danger from the storage subsystem and the secondary data and represent the data objects of potential danger for the operator.

2. A system according to claim 1, in which the subsystem management-monitoring and primary processing of video data further comprises one or more databases, wherein each video server is arranged to store the received video data, with reference to the associated descriptive metadata, the related database from one or more of these databases.

3.A system according to claim 2, in which each video server contains computer-implemented vision system for the implementation of video analysis, and computer vision system video server retrieves video data for analysis of related databases, computer vision system video server configured to generate a data object of potential danger on the identification of signs of fire in the analyzed video data so that the generated data object of potential danger was tied to the video data, which showed signs of fire, and associated metadata that describes the characteristics of challenging video data.

4. A system according to claim 3, in which computer-implemented computer vision system is configured to use computer vision algorithms to ensure the detection of signs of fire on different types of cameras and in different shooting conditions.

5. A system according to claim 1, in which each video server is capable of sending the generated data object is a potential hazard in the storage subsystem and secondary processing of video data to request the retention of the data object is a potential hazard in the storage subsystem and secondary processing of video data.

6. A system according to claim 1, in which each object �the server further configured to: compare the received data object is a potential hazard with the previously stored data objects of potential danger in order to identify potential data objects danger of having a relationship with the received data object of potential danger, and the results of the comparison to perform at least one of the following: save the received data object of potential danger, to modify at least one of previously stored data objects of potential danger, to modify the received data object is a potential danger.

7. A system according to claim 6, in which each object server further configured to, when identifying the previously stored data objects of potential danger of a data object of potential danger, essentially coincident with the received data object of potential danger, to adjust characteristics of an identified data object of potential danger based on the characteristics of the received data object of potential danger, without saving the received data object is a potential danger.

8. A system according to claim 1, in which the object server receives a data object of potential danger from the subsystem management-monitoring and primary processing of video data.

9. A system according to claim 1, in which each object server is arranged to maintain all changes to all data objects of potential hazards that exist on it, including after UD�management of data objects of potential danger.

10. A system according to claim 1, in which the video servers and cameras assigned video monitoring points connected to high-speed virtual private network (VPN).

11. A system according to claim 1, in which the subsystem management-monitoring and primary processing of video data further comprises a controller video servers connected to a communication network, for controlling the operation of video encoders, wherein the controller server is configured to dynamically balance the load between servers.

12. A system according to claim 11, in which the controller stores contains diagnostic tools and analysis of the current and the average load on the video servers, wherein the load includes the computational load and the load of network traffic.

13. A system according to claim 12, in which the video servers receive a list of video monitoring points assigned to them for maintenance, controller video servers, controller video servers configured to automatically perform dynamic remapping pixels video monitoring / video servers depending on the load on the video servers, each video server is capable of monitoring its list of points of video monitoring for changes in the controller's video servers.

14. A system according to claim 1, further�individual contains one or more servers environment users to control and configure the access of operators to the components and resources of the video monitoring system of the forest through the client application, as well as for routing, in conjunction with client applications, the data they need to work.

15. A system according to claim 14, in which each client application is configured to dynamically determine, in cooperation with the server environment, users, and visualized for the operator information is available for the operator components and resources of the video monitoring system of the forest, while the client application is configured to render to the operator a list of available operator for object servers, the list is available to the operator of the video servers and the list of available cameras that are serviced by these video servers, and a client application configured to provide the operator with the ability to access the video data received in real time from any one of the available video cameras, or the stored video data, previously taken any of the available video cameras, and control the work of any of the available cameras.

16. A system according to claim 3, in which each client application configured to render to the operator a list of data objects of potential danger received from the object server; when you call the operator to any data object of potential danger from a list of data objects of potential danger of supra�and develop stored video data in the database, associated with this data object the potential hazards and associated metadata in the appropriate video server; to visualize the data object referred to the potential danger to the operator by visualizing the received video data and associated metadata; and provide the operator the possibility to confirm or not to confirm a possible fire, which signaled the rendered object data potential danger.

17. A system according to claim 1, in which the client application is arranged to assign points video monitoring / video servers.

18. A system according to claim 1, in which the client application is executed with a territorial area of responsibility of each of the object servers.

19. Method of fire detection, implemented in the video monitoring system of the forest, containing: a plurality of cameras; a plurality of video servers, each video server maintains one or more of the plurality of video cameras; one or more object servers; and a variety of computer terminals, containing phases in which: through the video server of the plurality of video servers:
accept video data from at least one camera, perform video analysis to detect signs of fire,
at revealing of signs of fire forming is�jut a data object of potential danger, identified potential fire, with reference to the video data, which showed signs of fire, and
send the data object is a potential hazard in at least one of the object servers; object through the server:
accept the data object of potential danger, compare the received data object is a potential hazard with the previously stored data objects of potential danger,
the results of the comparison performed by at least one of the following:
save the received data object of potential danger,
modify at least one of previously stored data objects of potential danger,
modify the passed data object of potential danger, and
send one or more data objects of potential danger in at least one computer terminal; and by means of a computer terminal:
accept data objects of potential danger and represent data objects of potential danger for the operator.

20. A method according to claim 19, in which the data object is a potential hazard form additionally with reference to the metadata that describes the characteristics of shooting video.

21. A method according to claim 19, wherein, when identifying the results of the comparison among the previously saved objects d�nnyh potential danger of a data object of potential danger, essentially coincident with the received data object of potential danger, modify the identified data object is a potential hazard based on the received data object of potential danger, without saving the received data object is a potential danger.

22. A method according to claim 20, additionally containing phases in which, through a computer terminal for the operator to visualize the list of data objects of potential danger received from the object server; when you call the operator to any data object of potential danger from a list of data objects of potential danger are requesting video data associated with the data object of potential danger, and associated metadata in the appropriate video server; visualize the data object referred to the potential danger to the operator by visualizing the received video data and associated metadata; and provide the operator the opportunity to confirm or not to confirm a possible fire, which signaled the rendered object data of the potential danger.



 

Same patents:

FIELD: physics, video.

SUBSTANCE: invention relates to generation of simulated video. The method includes installing a plurality of cameras in different directions in a location to record images of vehicles from different angles which are indexed; receiving source video input from a single-direction camera; generating a stream of video fragments of vehicles; correlating the vehicles in the video fragments with the corresponding stored images of vehicles using a sliding window with normalised cross correlation; retrieving images at another angle which correspond to the stored images of vehicles; merging the retrieved images into simulated video which displays vehicles moving in a different direction; generating simulated video with a different frame frequency than the frame frequency of the input source video to reduce blur and dimness of the input source video and rendering the simulated video.

EFFECT: obtaining simulated traffic video having high frame frequency, high resolution and multiple views by processing video from single-direction cameras having a low frame frequency and low resolution.

14 cl, 7 dwg

FIELD: physics.

SUBSTANCE: tracking assistance device for assistance to the monitoring person in tracking of the moving object displayed on the monitoring screen on which the types of display for real time imaging of captured images made by the respective cameras are located in the image of the map representing a monitored zone according to the actual arrangement of cameras is offered, which comprises: the targeting unit to be tracked which in response to the input operation performed out by the monitoring person in one of types of imaging for designation of moving object to be tracked establishes the designated moving object as the target to be tracked; the prediction unit which predicts the following type of imaging on which the moving targeted object to be tracked will appear next time, on the basis of the information of tracking obtained by processing of the captured images; and the unit of indication of imaging type which indicates the next type of imaging in the monitoring screen.

EFFECT: ensuring of continuous tracking, even when interruption or error occurs during tracking, reduction of loading in tracking of moving object.

5 cl, 17 dwg

FIELD: radio engineering, communication.

SUBSTANCE: invention relates to communication engineering and can be used for industrial television, for video surveillance of objects in surrounding space and combined generation of colour, spectrozonal and thermal images. The method comprises, after splitting input radiation flux into two identical streams, passing said streams through two broadband optical filters, the first having a spectral characteristic overlapping a spectral portion in the visible spectral region, and forming the radiation flux at the output of the first optical filter; the spectral characteristic of the second optical filter overlaps the spectral portion in the visible and near infrared IK1 spectral region; and forming radiation flux at the output of the second optical filter, followed by generating colour television video signals, generating spectrozonal television video signals, further setting up a third channel, for which input radiation flux is transmitted through an infrared lens, obtaining thermal imaging video signals corresponding to detection areas of the thermal portion of the spectral region, further amplifying and performing separate and combined digital processing of the generated video signals, displaying said signals for visual perception of images or automatic analysis of video information.

EFFECT: improved video information support and efficiency of the surveillance process and reliability of analysing objects of multi-component images.

6 cl, 2 dwg

FIELD: physics.

SUBSTANCE: method is carried out by generating television image signals of different spectral regions, which includes detecting an input radiation flux F'(λ) within a wide spectral interval from λ1 to λn; generating therefrom three separate radiation fluxes F1(λ), F2(λ) and F3(λ); generating in a first channel of radiation flux F1(λ) in the visible spectral region colour television video signals UR(t), UG(t) and UB(t); generating in a second channel of radiation flux F2(λ) in the visible and near-infrared spectral region spectrozonal television video signals UΔλ1(t), UΔλ2(t) and UΔλ3(t); generating in a third channel, based on the radiation flux F3(λ) in the thermal infrared spectral region, thermal imaging video signals UΔλ4(t) and UΔλ5(t). Before generating image signals, in the first channel, the radiation flux F1(λ) is further split into three identical fluxes; in the second channel, the radiation flux F2(λ) is further split into three identical fluxes; and in the third channel, the radiation flux F3(λ) is further split into two identical fluxes; each separate flux is then passed through a separate optical filter. The spectral characteristic of the optical filter for the first channel corresponds to detection zones of light flux in the red (R), green (G) and blue (B) regions of the visible spectral region; for the second channel, the spectral characteristic of the optical filter corresponds to selected detection zones Δλ1, Δλ2 and Δλ3 of radiation flux in the visible and near-infrared spectral regions and for the third channel corresponds to detection zones Δλ4 and Δλ5 in the thermal infrared spectral region. Further, the method includes separate conversion of each radiation flux into an image signal, after which the obtained groups of video signals for the first, second and third channels are amplified, followed by conversion of analogue video signals to digital, digital aperture processing of the video signals and gamma correction of the video signals and using the colour television UR(t), UG(t) and UB(t), spectrozonal television UΔλ1(t), UΔλ2(t) and UΔλ3(t) and thermal imaging UΔλ4(t) and UΔλ5(t) digital video signals for combined processing thereof. The method further includes an operation for subtraction or summation of video signals with each other, replacing part of the image of one video signal with part of the image of another, changing the polarity of video signals, dividing the video signals into low-frequency and high-frequency components, followed by displaying original and newly generated video signals on video monitor screens for visual perception of images and automatic analysis.

EFFECT: high resolution of television images and enabling real-time change of detection zones of radiation flux for viewing objects in different spectral regions of the optical spectrum.

4 cl, 1 dwg

FIELD: physics, video.

SUBSTANCE: invention relates to camera control means. The method comprises acquiring first information used to control a first area specified within a full image captured by a camera unit; acquiring second information used to control a second area specified within the full image; controlling mechanical movement of the camera unit based on the first information input; acquiring an image of the first area from the full image captured by the camera unit and extracting an image of the second area from the first area based on the second information.

EFFECT: high range of the obtained image.

18 cl, 20 dwg

FIELD: radio engineering, communication.

SUBSTANCE: invention relates to wireless communication engineering. A vehicle communication system comprises a processor for authenticating a communication service provider. If a communication service provider is authenticated, the processor can use a lookup table to determine the access point number (APN), as well as the name of a user and password for providing a wireless Internet connection through a wireless device. If the communication service provider is not authenticated or more than one APN and/or the user name/password combination is associated with said communication service provider, the processor operates to carry out an assumption and verification process to determine the right login information.

EFFECT: providing a safe wireless connection between a remote network and a vehicle.

16 cl, 5 dwg

FIELD: weapons and ammunition.

SUBSTANCE: device includes a unit of video/audio recording which, by its output through memory unit and data transfer unit, is connected to the unit of standalone remote server, which, by its input/output, is connected to the unit of automatic restoration of video sequence, the data transfer unit by its input is connected to control assembly and memory unit and by its output is connected to analysis and control block, which is connected to control assembly by its input/output, control assembly by its output is connected to the unit of video/audio recording and to the unit of geolocation and by its inputs it is connected to power supply unit and gun safety lock unit, the unit of geolocation by its output is connected to the memory unit.

EFFECT: enhancing small arms of self-protection and providing information security.

2 cl, 2 dwg

FIELD: physics, video.

SUBSTANCE: invention relates to panoramic television surveillance. The result is achieved due to that surveillance is carried out by a television system through a television camera with all-round view in a region close to a hemisphere, i.e., in a spatial angle of 360 degrees on the azimuth and tens of degrees on the elevation angle. Panoramic colour or black and white images are automatically transmitted to the server of a local area network depending on the time of the day, wherein monochromatic video signals are detected therein with a high signal-to-noise ratio.

EFFECT: providing an operator with a colour image during the day and a black and white image during the evening and night in automatic switching mode and with a high signal-to-noise ratio for a monochromatic image.

4 cl, 11 dwg

FIELD: physics; control.

SUBSTANCE: invention relates to video monitoring systems and a control method therefor. The video monitoring system comprises a signal interface gateway which receives, respectively, control signals from a digital video monitoring system and/or a matrix video system in an analogue video monitoring system and accordingly converts the control signals from the digital video monitoring system and/or control signals from the matrix video system. Said conversion includes creating a relationship table in the signal interface gateway which represents relationships between channels of the digital video monitoring system and channels of the matrix video system, and performs conversion of the control signals according to the relationship table.

EFFECT: providing mutual control of an analogue video monitoring system and a digital video monitoring system.

6 cl, 10 dwg

FIELD: radio engineering, communication.

SUBSTANCE: television camera includes a first digital television signal (DTS) sensor, a second DTS which is frequency- and phase-synchronised with the first DTS through a receiver synchronisation signal (RSS), as well as a multiplexer, wherein the photodetector target of the first DTS sensor is mated through a fibre-optic coupling with peripheral light guides with bundles of fibre-optic caps, and its central light guide bundles are matted with the photodetector target of the second DTS sensor, and operations for demultiplexing an input video signal and units for converting a "circular" frame into "rectangular" frames are performed in a server in a programmed manner.

EFFECT: number of video signal sensors in the device, compared to the prototype, is reduced to two and enabling use of CCD arrays as photodetectors, said arrays having in the central region of the target, technological defects which cause white spot type image distortions.

4 cl, 7 dwg

FIELD: physics.

SUBSTANCE: method comprises panoramic surveillance in the area of the guarded facility by forming an image which provides simultaneous all-round view in a region close to a hemisphere, i.e. in a spatial angle of 360° on the azimuth and tens of degrees on the elevation.

EFFECT: enabling panoramic surveillance of an area of a guarded facility.

5 cl, 9 dwg

FIELD: physics, video.

SUBSTANCE: invention relates to video surveillance, primarily of open spaces, with fire hazard monitoring and can be used to monitor forest areas in regions with underdeveloped infrastructure. The method comprises video monitoring of a protected area; selecting mobile regions on the obtained image; comparing said regions with reference images from a library of images and making a decision on burning based on the similarity of the obtained images and the available images; wherein mobile objects are selected on the image by breaking down the whole image into rectangular blocks; the shifting of blocks over time is diagnosed from the shift of the centre of a block; separate mobile blocks are merged by spatial clusterisation; time clusterisation of mobile objects is carried out based on a criterion of the intersection of trajectories of separate blocks with each other, wherein the shape of a mobile object is reconstructed by cutting off short edges, joining adjacent boundary points and smoothing the obtained boundaries, wherein the internal region of the object is reconstructed on the obtained boundary, and clusterisation of the selected mobile object is carried out on the normal component of optical flux.

EFFECT: high probability of recognising signs of fire on an open area owing to early detection of fire from smoke traces and air currents.

3 cl, 1 dwg

FIELD: physics; control.

SUBSTANCE: invention relates to video monitoring systems and a control method therefor. The video monitoring system comprises a signal interface gateway which receives, respectively, control signals from a digital video monitoring system and/or a matrix video system in an analogue video monitoring system and accordingly converts the control signals from the digital video monitoring system and/or control signals from the matrix video system. Said conversion includes creating a relationship table in the signal interface gateway which represents relationships between channels of the digital video monitoring system and channels of the matrix video system, and performs conversion of the control signals according to the relationship table.

EFFECT: providing mutual control of an analogue video monitoring system and a digital video monitoring system.

6 cl, 10 dwg

FIELD: physics, signalling.

SUBSTANCE: invention relates to security signalling, particularly, to video surveillance means for detection and identification of trespassers that penetrate through security borders and actuate the detection means. Proposed system consists of central control board and sets of remotely addressed video cameras connected with central control board via switchboard channel. Switchboard channel is composed by digital data transmission network via two-way serial communication interface.

EFFECT: higher reliability owing to higher quality of video pictures, around-the-clock video surveillance with IR-floodlight illumination of video camera coverage area.

13 cl, 5 dwg

FIELD: physics, video.

SUBSTANCE: invention relates to video surveillance systems using means of recognising hazardous at a secure facility. The device comprises at least one video camera which is capable of converting a video signal to a digital video signal, a video signal storage unit, a unit for converting the digital video signal to a sequence of images on a video monitor screen, and further includes a manipulator of a control unit of the conversion unit which is such that movement of the manipulator corresponds to change in images on the video monitor screen, and the direction and rotational speed of the wheel corresponds to the sequence and rate of change of successive images; the device includes an event analyser which picks up events from the digital video signal which require the attention of the operator, and generates a labelling signal upon picking up an event which requires the attention of the operator; the device further includes an event display in form of a wheel, which is such that its rotation corresponds to the rotation of the manipulator of the control unit, and the event display displays images of labels of events recorded by the camera which require the attention of the operator.

EFFECT: high reliability of security and accuracy of recognition.

8 cl, 3 dwg

FIELD: radio engineering, communication.

SUBSTANCE: playback control system comprises: a video recording means, a motion detecting means and a video playback means, wherein the video recording means is capable of recording video surveillance; the motion detecting means is capable of recognising a video image in real time and labelling a time index for a dynamic frame (dynamic frames) of the video when recording using the video recording means; and the video playback means is capable of obtaining the time index from the motion detecting means and playback the dynamic frame(s) of the video surveillance record in accordance with the time index when playing back the video surveillance record.

EFFECT: shorter time for playing back a video surveillance record without loss of significant information.

8 cl, 2 dwg

FIELD: physics.

SUBSTANCE: computer includes a video card; in the television camera, a first television signal sensor (TSS) is based on an array of charge-coupled devices with "row-frame transfer", and the use of an additional pulse former for clock powering of the photodetector enables summation of charge signals in the memory section accumulated in the photodetector section thereof. As a result, the signal-to-noise ratio for a general view image increases in proportion to the increase in energy of the useful signal thereof, i.e. the number of accumulation frames.

EFFECT: high quality of the general view image due to a higher signal-to-noise ratio at the output of the array of charge coupled devices of the first television signal sensor owing to summation, in the memory section thereof, of charge packets formed in the photodetector section.

5 cl, 10 dwg, 2 tbl

FIELD: information technology.

SUBSTANCE: method includes a setup step where an operator creates a model of the environment by determining the number of cells corresponding to regions of said environment, and then creates a "cell/sensor" connection by defining for each sensor at least one possible position associated with at least one cell. For each position, the operator assigns the sensor a control estimate for the associated cell. The method also includes a working step where a control system, in order to execute a surveillance function, finds those sensors that can be used to execute the requested surveillance function and control said sensors based on control estimates and the "cell/sensor" connections.

EFFECT: high reliability of surveillance systems, particularly video surveillance systems, by providing dynamic adaptation each time a sensor cannot be used by the system.

9 cl, 6 dwg

FIELD: information technology.

SUBSTANCE: passenger carriage video monitoring system has at least one video camera mounted such that it is capable of scanning at least part of the interior of the passenger carriage. The video camera is connected to a video recorder to which a monitoring and control unit is reversibly connected. The video recorder can be connected to a data transmission system and a monitor mounted in the guard's compartment.

EFFECT: safer transportation of passengers.

7 cl

FIELD: information technology.

SUBSTANCE: apparatus for detecting and monitoring hazard with a built-in display system is meant for use in a public safety system and warning on emergency situations, adapted for detecting and identifying hazards in the surrounding medium, as well as displaying information of interest relating to the hazard or other public information.

EFFECT: detecting hazard and endangering activities at early stages thereof.

25 cl, 3 dwg

FIELD: video surveillance.

SUBSTANCE: method includes video surveillance of controlled object state, while into television cable main of object high-frequency television modulated signal is sent, while to receive signal concerning state of S objects, each of which includes group of N video surveillance blocks, including camera and microphone, video-audio signals from each group of N video surveillance blocks are combined along low frequency, received complex video signal is converted from each group of N video surveillance blocks into high-frequency television modulated signal and it is synchronized with unified cable main - coaxial television cable, in arbitrary groups combination, via which received independent S signals are sent to input of visualization and/or recording systems.

EFFECT: higher efficiency.

3 cl, 2 dwg

Up!