Method and system for automatically finding three-dimensional images

FIELD: systems for automatic video surveillance of an object.

SUBSTANCE: system for automatic detection and tracking of individuals on basis of images and biometric identity recognition based on target list, realizes following operations: on basis of three-dimensional data about scene and two-dimensional data, characterizing optical flow, detection of objects-noises of scene is performed, static background objects are selected, and regular dynamic object-noises; on basis of comparison of two-dimensional and two-dimensional data about the scene in current frame with reference data on previous frames and a map of object-noises changes are determined on a scene, in three-dimensional zones of interest, preliminary check of presence of human-like objects is performed, zones of interest are determined more precisely and their changes are tracked: a contour of separate elements of human body is singled out, zones of interest are divided onto a set of sub-zones of interest for elements, detection of three-dimensional head of individual is performed and it is tracked in each zone of interest; face of individual is tracked in each zone of interest; images of detected face are normalized in terms of dimensions, angles and brightness; recognition is performed.

EFFECT: objectivity and stability of system operation.

1 dwg

 

The invention relates to systems for automatic video surveillance, expert systems, detection and recognition of objects and can be used in identity management systems on the target list in places where many people, particularly in the subway, airports, etc.

One of the peculiarities of the development of modern society is the increasing demand for automation of existing surveillance systems and the creation of a new class of intelligent systems of mass service, is designed for the following applications:

intelligent video surveillance:

detection and tracking of a person in the monitoring area;

- the selection of a person in a group of people in conditions of interference and overlapping entities;

- finding elements of the human body (body, head, face, eyes, mouth, facial features), the definition of its unique biometric characteristics (growth, the size of the head, facial features, anthropometric characteristics of the face);

- finding elements of the service user for short-term processes of tracking and recognition (for example, tracking store visitors);

- capture trajectories, the analysis of the dynamic characteristics of motion of the object;

biometric identification of a person:

cumulative extraction of biometric features of the user and creation of standards signature is caracterizada the uniqueness of the identity of the user;

- a man in search of a target list, and personal identification (for example, the person counterpart in the database of wanted criminals);

- restrict access to various objects, such as offices, warehouses, ATMs, military objects.

recognition of situations on stage:

- improving the throughput of the Queuing systems in crowded places (automatic check of the passport);

- prompt notification when a predefined event, the recognition of the criminal situation (the presence of people wearing masks on stage).

Numerous solutions to this problem with varying degrees of difficulty and reliability of results. In particular, in U.S. patent 6593852 [1] proposed a method, intelligent video surveillance, capable of detecting the intruder in a protected area monitoring, to recognize his identity, to find a path, to identify the trajectory in case of discrepancy between the trajectories on the metric or the detection of the unregistered user to generate a signal of a criminal situation. However, presented in the patent, the device can be used in places only a small gathering of people and because of dumarest applied technologies allows to identify three-dimensional biometric characteristics of the user.

U.S. patent 6700999 [2] op is saweet method and device for detecting and tracking multiple objects "human face". However, this method and apparatus can detect the face of a man only at close distances and require precise positioning in front of the camera, which does not allow to use this device for contactless and covert observation of people.

The closest analogue of the claimed invention is U.S. patent 6917703 [3], which discloses a method and apparatus generate the reference signs a person on the basis of the analysis of images using a Gabor transform and neural network, as well as the geometry of the graph of the face. The disadvantage of this solution is that during the formation of the standards it focuses on working only with images of persons of high quality, without overlapping external objects, images of faces in frontal view, and can be applicable only when the person is positioned his face in front of the camera.

Thus, the problem to which the invention is directed, is to establish a system for automated surveillance and detection, which would combine the objectivity and stability of the machine and intellectual approach to the assessment of the situation, peculiar to guard the man.

The technical result is achieved by developing a system of "Smart Guard"using more sophisticated methods for the monitoring and evaluation of the situation. This automated three main functions performed by the guard-man, namely, intelligent video surveillance, biometric identification on the target list, the recognition of the criminal situation.

The proposed system and method can solve the following tasks:

intelligent video surveillance:

- automatic collection of information about the three-dimensional images, describing a zone of observation;

- implementation of rapid detection, tracking person and summarizing information about three-dimensional objects in the monitoring area;

- the selection of a person in a group of people in conditions of interference and overlapping entities;

- finding elements of the human body (body, head, face, eyes, mouth, facial features), the measurement of its unique biometric characteristics (growth, the size of the head, facial features, anthropometric characteristics of the face);

- finding elements of the service user for short-term processes of tracking and recognition (for example, tracking store visitors);

- capture trajectories, the analysis of the dynamic characteristics of motion of the object;

- recognition of the physical and behavioral characteristics of the human face (the situation of a mass congestion of people, when for more accurate tracking of the object in addition to detection is the process recognize the avania);

- identification of the situation of the traffic channels in the access control system, operating as a queueing system;

- identification of the types of criminal situation through analysis of detected users and decision about the type of situation in the surveillance zone in accordance with the application.

biometric identification of a person:

cumulative extraction of biometric features of the user and creation of standards signatures that characterize the uniqueness of the individual user,

- a man in search of a target list, and personal identification (for example, the person counterpart in the database of wanted criminals).

recognition of situations on stage:

- improving the throughput of the Queuing systems in crowded places (for example, an automatic check of the passport);

- prompt notification when a predefined event, the recognition of the criminal situation (the presence of people wearing masks on stage, increased activity in the monitoring area, the attack camera offender).

At that, the essence of the proposed method is to perform the following sequence of operations:

- produce remote collection of three-dimensional and two-dimensional data from images, describing a zone of tracking based on the use of three-dimensional stereoscopic system, sotoyama the two or more optical sensors to a predetermined location;

on the basis of three-dimensional data of the stage and two-dimensional data characterizing optical flow, make the detection of objects-noise scene, allocate a static background objects and regular dynamic objects noises;

based on comparing three-dimensional and two-dimensional data about the scene at the current frame with the reference data for the previous frames and map objects-noise to determine the changes on the stage, forming a three-dimensional area of interest in the scene;

in the three-dimensional zones of interest produce preliminary checks humanoid objects, produce clarification of areas of interest and track their changes;

- make path selection of the individual elements of the human body, the area of interest is divided into multiple subbands of interest for elements that produce the specification of the position of the elements in space;

- make the detection of three-dimensional human head and the tracking of it in each of the zones of interest;

- produce tracking of human face in each of the zones of interest;

image of the detected face normalize the size, angles and light.

produce recognition on the target list according to the scenario of a biometric system.

The system implementing the inventive method includes the following devices:

- device remote sensing Yes the data in the form of three-dimensional and two-dimensional images, describing a zone of tracking is based on the use of three-dimensional sensor, consisting of two or more optical sensors with known their location;

device object detection-noise scene, processing the three-dimensional information about the scene and outstanding map of probable objects of noise;

device allocation of zones of interest, comparing the three-dimensional information about the scene with the reference data with the previous frame and with the map data objects-noise monitoring changes on stage, highlighting the three-dimensional region of interest;

- the device checks the availability of three-dimensional humanoid objects in the zone of interest and the correction zone of interest outstanding on the basis of the motion or shape of an object the subset of the selected areas of interest, containing a humanoid objects, and passes it to the device management tracking system;

device management system tracking and recognition of three-dimensional objects, forming a list of objects tracking, causing one or more devices tracking and estimation of the parameters of interest tracking, allocating and dividing objects tracking in areas of interest according to the results of their work, identifies the type of the situation at the scene, causing the forming device of biometric characteristics for object tracking, the results of formation of a set of signs mandatory UN paid is enabling the creation of a reference or recognition for object tracking; outstanding description of the recognized object and the list of candidate standards;

device tracking and estimation of the parameters of interest tracking, consisting of the following blocks:

-- block allocation parameters of a human figure;

-- block detection and tracking for three-dimensional human head in the area of interest;

-- block detection and tracking human face on the head;

-- block detection and tracking of facial features of the person;

-- block detection and prediction of the trajectory of human rights in the area of interest;

-- unit detecting the orientation of the body in space;

- forming device biometric characteristics, consisting of the following blocks:

-- block the formation of a set of parameters passed to the signs;

-- block restrictions scene, distinguishing characteristics corresponding to the predicted behavior of the person on the scene;

-- block normalization of attributes with regard to distance and orientation in space;

-- block assessment of the representativeness of the characteristics that defines the type and quality selection of attributes with regard to normalization;

-- the block settings have been updated and assessment of the representativeness of the characteristics of the person;

- device identification, forming from the target list of possible standards and screening, taking into account the distance to the person about whom iently the body in space, quality surveys; conducting the comparison and filtering standards list with regard to thresholds for measures of similarity and reliability; issuing device control measure and the reliability of the similarity of the object with the standards from the list.

- DBMS that stores transmitted from the device management standards, clustersa their affordable distances, orientations, representativeness; organizing the access device identification to the standards and their characteristics, taking into account clustering; outstanding control device a list of credible references.

The main distinguishing features of the proposed method and system are:

- a device for detection and tracking of objects of different types and different levels of complexity (the human body, the human head, the face, the facial features (eyes, mouth)),

- a device for detection and tracking of face objects in large crowds of people,

- high adaptability to light, noise on the images, the background noise, the presence of external objects,

- the ability to detect the trajectory of the object

- implementation of consistent data collection and accumulation of biometric characteristics about objects in the monitoring area, the formation of the pattern on the basis of the trajectory and position of the person in certain angles,

- implementation of face recognition under partial the information about the object of interest, recognition in noise conditions and the presence of external objects,

- function introduction face recognition in the presence of overlapping behalf of external objects

additional identification of the persons in the target list (the list of suspicious persons),

- search reduction standards target list using the parametric organization target list and select from it,

- reduction of conducted calculations when compared with the benchmark target list,

- identification of the situation in the target list trajectories and behavioral characteristics of objects.

It should be noted the purpose of the components in the inventive detection system of three-dimensional objects and recognition for their presence in the target list, among which there are:

The remote data collection (three-dimensional and two-dimensional images), describing the area tracking is based on the use of three-dimensional sensor (for example, the stereoscopic system consisting of two or more optical sensors (e.g., video or still cameras)) with known position.

The device object detection-noise scene, which is designed to handle three-dimensional data about the scene and issuance of probable objects of noise; it carries out the detection of objects-noise scene, allocates static is sky objects and background regular dynamic objects-noise (regular motion).

The device checks the availability of three-dimensional humanoid objects in the zone of interest and the correction zone of interest, which allows you to perform the following functions:

- allocation of areas of interest

- detection of changes in the scene,

- detection of a human body according to the map of disparately,

- detection of the body motion,

- integration solutions for the detection of the person.

Highlight areas of interest is to compare the three-dimensional data about the scene with the reference data with the previous frame and with the map data objects-noise, tracking changes on stage, in the selection of three-dimensional zones of interest. The analysis is performed using accelerated stereocontrol. On the basis of the motion or shape of an object is given a subset of the selected areas of interest, containing possible humanoid objects, and transmitted to the integrated solver. Function integrated solution is used for decision-making in the area of monitoring one or more of the humanoid object. Further information about the presence and number of objects of type human body is specified in the device management system tracking and recognition of three-dimensional objects.

The device management system tracking and recognition of three-dimensional objects generates a list of object tracking, syvaet one or more tracking devices and estimation of the parameters of interest tracking according to the results of his work distinguishes and separates objects tracking (human bodies) in areas of interest, determines the type of the situation at the scene, causes the processing unit of biometric characteristics for object tracking, the results of formation of a set of signs initiates the creation of a reference or recognition for object tracking; gives a description of the recognized object (position, path) and a list of credible references.

Device tracking and estimation of the parameters of interest tracking consists of blocks:

- unit selection parameters of a human figure,

- block detection and tracking for three-dimensional human head in the area of interest,

- block detection and tracking human face on the head,

- block detection and tracking of facial features of the person (e.g., eyes, mouth),

- block detection and prediction of the trajectory of human rights in the area of interest,

- block detection of the orientation of the body (head) of the human in space.

In the block selection parameters figure produce a sequential search on the map features (Gabor, disparity, color) hypotheses about the figure of one person, and also specify the distance of the object to the camera. The adoption of the decision on recognition of the whole human figure is the recognition of the main structural parts of the body: head, shoulders, arms, legs, elouise. Using block detection and tracking for three-dimensional human head detects the signal head on the cards Gabor features (vertical and horizontal), at distances of the object to the camera there is the possibility of using color segmentation. Using block detection and tracking human face on the head make the analysis of the card features the following:

- a person are based on the analysis of the facial geometry and location of local features;

When forming decisions about detection of persons using at least one of the three view models face:

representation using local features in clusters of traits: (eyebrows, eyes, and nostrils, moustache, mouth, chin), (cheeks and nose);

representation using color segmentation;

representation by analyzing maps of disparately analysis of convexity of the set of corresponding points.

When following the search of a person conducted in the specified area of interest (based on the previous status of the person), check the consistency found a local hell - if an object is detected with a low degree of confidence, start the procedure of detection:

Device for the formation of biometric characteristics consists of the following blocks:

block normalization signs that receives from the detection unit detected the prize is Aki and depending on the distance and orientation in space produces over images of the sequential procedure of normalization: approval of dimensions, the elimination of the slope, alignment light:

- block the formation of a set of parameters to generate the pattern, which is obtained normalized features extracts certain types of parameters (e.g., principal components, signs of Gabor),

unit restrictions scene highlights the characteristics corresponding to the predicted behavior of the person on the stage, taking into account the detected noise and scene geometry,

- block assessment of the representativeness of the characteristics that defines the type, quality, completeness of the basis and the representativeness of the selected attributes with regard to normalization,

block set update parameters and assessment of the representativeness of the signs.

Device identification, intended for generating the list of candidate standards from the target list and sieving it with regard to the distance to the person, the orientation of the body in space, the quality of shooting; for the comparison and filtering standards list with regard to thresholds for measures of similarity and reliability; to issue device control measure and the reliability of the similarity of the object with the standards from the list.

System database management (DBMS)that stores transmitted from the control unit patterns, clusters them available distances, orientations, representativeness; organizes access blagoraspolojeniya personality to the standards and their characteristics, taking into account clustering; generates the control unit a list of credible references. The inventive method and system are illustrated by the scheme of interaction of the devices in the system.

The drawing shows a diagram of the interaction of elements and devices:

1. Stereoscopic system;

2. 2D camera;

3. the remote data collection:

3.1. 3D image;

3.2. 2D image;

4. the device object detection-noise scene:

4.1. map traits of interest noises;

4.2. the detector background objects;

4.3. the detector regular dynamic objects;

5. the device highlight areas of interest:

5.1. the detector changes on the scene;

6. the device checks the availability of three-dimensional humanoid objects in the zone of interest and correcting areas of interest:

6.1. the detector body in 3D;

6.2. the detector body movement;

6.3. integrated solver for the detection of the person;

7. the device management system tracking and recognition:

7.1. generator list object tracking;

7.2. detector type situation on the scene;

8. device tracking and estimation of the parameters of interest tracking, consisting of the following blocks:

8.1. block allocation parameters of a human figure;

8.2. the block detection and tracking for three-dimensional human head;

8.3. the block detection and tracking human face on the head;

8.4. the detection unit is to predict the trajectory of the person;

8.5. the detection unit orientation of the body in space;

8.6. the block detection and tracking of facial features of the person;

9. device for the formation of biometric characteristics, consisting of the following blocks:

9.1. unit restrictions scene;

9.2. the unit normalization of signs;

9.3. the evaluation unit representativeness of signs;

9.4. block the formation of a set of parameters;

9.5. the block settings have been updated and assessment of the representativeness of the characteristics of the person;

10. device identification:

10.1. filter standards by the distance to the person;

10.2. filter reference orientation in space;

10.3. filter standards for quality shooting;

10.4. filter as similarities and reliability;

11. DBMS standards:

11.1. Database standards;

11.2. management and optimization of selecting the samples from the database.

From the known solutions, the invention is distinguished by the following features:

- detailed and cumulative detection of objects of interest by finding the following three-dimensional objects: the body, head, face, elements of the human face,

detection of noise objects (background and dynamic objects in the scene)

multiple detection of persons and the list is tracking in the crowd (when a cluster of 3 or more persons),

- tracking the face of a specific person at different floors by using the project information list tracking and the list of detected faces,

- adaptability and stability of the detection system objects in relation to external objects (glasses, beard, mask), lighting, camera angles, which is achieved through the use of three-dimensional sensors, several types of representations of the face and procedures for detecting and generalization characteristics of persons in different angles,

- expert evaluation of information about detected objects: informativeness, representativeness, reliability of the detection and recognition,

- face recognition on stage in the identification mode on the target list,

- face recognition in terms of the overlapping faces of external objects in the scene,

- recognition of the situation of the traffic channels in the access control systems (such as Queuing systems) to improve the bandwidth of operation of a biometric system,

- recognition of the criminal situation and protection of biometric recognition systems from unauthorized access in case of penetration of the registered user from unauthorized users or dangerous objects, which is achieved by the hidden presence of all possible users and certain types of interaction objects on the stage,

- the use of static and dynamic signatures of both physical and behavioral bio is etnicheskih characteristics for face recognition.

Preferred implementations of the method and system can be used to automate existing surveillance systems and the creation of a new class of intelligent systems of mass service, is designed for the following types of applications: intelligent video surveillance user, biometric personal identification on the target list, the recognition of the criminal situation.

Devices included in the inventive system, implemented in the form of sensors three-dimensional and two-dimensional images and the card device, which includes at least one or more signal processors.

The invention is intended for added protection, security systems, including biometric, and can improve intelligence, reliability, and accuracy of the systems using the following technologies:

- hidden and contactless monitoring of a user;

detection of a person in the monitoring area;

- clarification of details of the object - the search head, the man's face without explicit interaction scenario;

- tracking movements of objects;

- identification of trajectories of objects, recognition of the type of situation in the scenario of a biometric system (criminal situation, system load, different types of user behavior is of the motor);

- the identification of the user in the target list as it gets closer to the cameras;

- recognition of criminal situations and automatic generation of suspicious persons in the target list (WATCH LIST);

- quick search on the database.

- indexing and clustering the database for fast search database.

1. Automatic detection and tracking of humans in images from multiple sources and biometric identification on the target list, which is a list of suspicious persons, consisting of the following devices:

the remote data collection in the form of three-dimensional and two-dimensional images, describing a zone of tracking is based on the use of three-dimensional sensor, consisting of two or more optical sensors with known their location;

the device object detection-noise scene, processing the three-dimensional information about the scene and outstanding map objects-noise;

device allocation of zones of interest, comparing the three-dimensional information about the scene with the reference data with the previous frame and with the map data objects noises made with the possibility of tracking changes in the scene and highlight the three-dimensional zones of interest;

the device checks the availability of three-dimensional humanoid volume is tov in the zone of interest and the correction zone of interest, outstanding on the basis of the motion or shape of an object the subset of the selected areas of interest, containing a humanoid objects, and passes it to the device management tracking system;

the device management system tracking and recognition of three-dimensional objects, forming a list of objects tracking, causing one or more devices tracking and estimation of the parameters of interest tracking, allocating and dividing objects tracking in areas of interest according to the results of their work, identifies the type of the situation at the scene, causing the forming device of biometric characteristics for object tracking, the results of formation of a set of signs initiating the creation of a reference or recognition for object tracking; outstanding description of the recognized object and the list of candidate standards;

device tracking and estimation of the parameters of interest tracking, consisting of the following blocks:

block allocation parameters of a human figure;

the block detection and tracking for three-dimensional human head in the area of interest;

the block detection and tracking human face on the head;

the block detection and tracking of facial features of the person;

the block detection and prediction of the trajectory of human rights in the area of interest;

the detection unit Orient the AI of the human body in space;

device for the formation of biometric characteristics, consisting of the following blocks:

block the formation of a set of parameters passed to the signs;

unit restrictions scene, distinguishing characteristics corresponding to the predicted behavior of the person on the scene;

the unit normalization of attributes with regard to distance and orientation in space;

the evaluation unit representativeness of characteristics that identifies the type and quality selection of attributes with regard to normalization;

the block settings have been updated and assessment of the representativeness of the characteristics of the person;

device identification, forming from the target list of possible standards and screening it with regard to the distance to the person, the orientation of the body in space, quality surveys; conducting the comparison and filtering standards list with regard to thresholds for measures of similarity and reliability; issuing device control measure and the reliability of the similarity of the object with the standards from the list.

DBMS that stores transmitted from the device management standards, clustersa their affordable distances, orientations, representativeness; organizing the access device identification to the standards and their characteristics, taking into account clustering; outstanding control device spies is possible standards.



 

Same patents:

FIELD: video encoding, in particular, methods and devices for ensuring improved encoding and/or prediction methods related to various types of video data.

SUBSTANCE: the method is claimed for usage during encoding of video data in video encoder, containing realization of solution for predicting space/time movement vector for at least one direct mode macro-block in B-image, and signaling of information of space/time movement vector prediction solution for at least one direct mode macro-block in the header, which includes header information for a set of macro-blocks in B-image, where signaling of aforementioned information of space/time movement vector prediction solution in the header transfers a space/time movement vector prediction solution into video decoder for at least one direct mode macro-block in B-image.

EFFECT: creation of improved encoding method, which is capable of supporting newest models and usage modes of bi-directional predictable (B) images in a series of video data with usage of spatial prediction or time distance.

2 cl, 17 dwg

FIELD: mobile robot, such as cleaner robot, and, in particular, device for tracking movement of mobile robot.

SUBSTANCE: suggested device for tracking movement of mobile robot includes: video camera for filming an individual object; unit for tracking movement and creation of image for setting support one in an image for current moment by means of filming of individual object by video camera and creation of image in current moment, for which support zone is set; unit for selecting image of difference of pixels of image support zone limit based on difference between pixels present only at limit of support zone of aforementioned images; and micro-computer for tracking movement of separate object on basis of selected image of difference.

EFFECT: decreased time of pixel comparison operation and increased efficiency of room perception.

5 cl, 4 dwg

FIELD: system for encoding moving image, in particular, method for determining movement vector being predicted, of image block in B-frame in process of decoding of moving image.

SUBSTANCE: in accordance to method, at least one movement vector is produced for at least one block, different from current block, while aforementioned at least one block is related to one, at least, supporting frame in a row of supporting frame, movement vector is predicted for current block on basis of received one, at least, movement vector, while prediction operation includes also operation of comparison of value of order number of B-frame to value of order number of one, at least, supporting frame, while movement vector for current block and aforementioned one, at least, movement vector are vectors of forward movement.

EFFECT: increased efficiency.

2 cl, 1 dwg

FIELD: technology for processing images of moving objects, possible use, in particular, in theatric art, show business when registration/recording is necessary or repeated reproduction of scenic performance.

SUBSTANCE: method includes inserting enumeration system for each object and performing projection of enumerated objects onto plane, while projection is displayed in form of graph with trajectories of movement of enumerated objects in each staging.

EFFECT: spatial-temporal serial graphic display of scenic action for its further identification and repeated reproduction.

2 dwg

FIELD: device and method for recognizing gestures in dynamics from a series of stereo frames.

SUBSTANCE: method includes producing a series of stereo-images of object, on basis of which map of differences in depths is formed. System is automatically initialized on basis of probability model of upper portion of body of object. Upper portion of body of object is modeled as three planes, representing body and arms of object and three gauss components, representing head and wrists of object. Tracking of movements of upper part of body is performed with utilization of probability model of upper part of body and extraction of three-dimensional signs of performed gestures.

EFFECT: simplified operation of system, high precision of gesture interpretation.

3 cl, 12 dwg

FIELD: movement detection systems, technical cybernetics, in particular, system and method for detecting static background in video series of images with moving objects of image foreground.

SUBSTANCE: method contains localization of moving objects in each frame and learning of background model with utilization of image remainder.

EFFECT: increased speed and reliability of background extraction from frames, with possible processing of random background changes and camera movements.

4 cl, 14 dwg

FIELD: television.

SUBSTANCE: support frame is assigned with sign, showing information about direction of support frame, and during determining of predicted vector of movement of encoded block averaging operation is performed with use of vectors of movement of neighboring blocks, during which, if one of aforementioned blocks has movement vectors, information about direction of support frames is received, to which these movement vectors are related, and one of movement vectors is selected with reference to received information about direction, than averaging operation is performed with use of selected movement vector to receive subject movement vector of encoded block.

EFFECT: higher precision, higher reliability.

3 cl, 1 dwg, 3 ex

The invention relates to a method and apparatus for identification and localization of areas with relative movement in the scene and to determine the speed and oriented direction of this relative movement in real time

The invention relates to the field of image processing and can be used in automated systems management traffic, for monitoring and documenting the landing maneuvers at airports, in robotics and in a more General approach can serve as a subsystem for systems with a higher level of interpretation, which are detected, segmented and can be observed moving objects, and automatically defined parameters

The invention relates to a video system technology and can be used when designing a digital coding device for video telephony, video conferencing, digital television broadcasting standard and high definition

FIELD: control-measuring criminalistics equipment, possible use for determining remoteness of sweat-fat hand marks.

SUBSTANCE: method for determining remoteness of sweat-fat hand mark includes detection of mark, for example by means of dactyloscopic powder, photometry of image of papillary lines in all mark points, digitization of image of mark together with background surrounding it, construction of brightness histogram relatively to mark and relatively to background, determining of average quadratic brightness deviation relatively to mark and relatively to background, production of their relation and comparison to calibration curve produced using a test object.

EFFECT: increased precision when determining remoteness of mark.

7 dwg

FIELD: technology for biometric control and authentication.

SUBSTANCE: on basis of registered biometric data only those characteristic data are received, which are unambiguously reproducible. Then on basis of these unambiguously reproducible characteristic data additional set of access key parameters is generated, which represents personal identification code, or on basis of which such an identification code can be generated.

EFFECT: when implemented for recognition and reading of biometric data, fingerprints in particular, higher reliability and resistance to interference during identification of persons.

4 cl, 1 dwg

FIELD: computer science.

SUBSTANCE: device has image sensor, block for separating frame and string pulses, generator, analog-digital converter, and also has digital signal processor and block for controlling executive implements of robot. Digital signal processor performs processing of image, going as follows: increase of brightness and contrast of image, transferring semi-tone image to two-gradation one, singling out contours, objects, determining position of objects. On basis of received data control block for robot implements drives trajectory of robot displacement, selects necessary command and forms controlling signals.

EFFECT: higher efficiency.

1 dwg

The invention relates to the field of computer engineering and can be used for automatic image analysis

The invention relates to computer technology and can be used in vision systems for input and processing of information transmitted in the computer

The invention relates to computing

FIELD: computer science.

SUBSTANCE: device has image sensor, block for separating frame and string pulses, generator, analog-digital converter, and also has digital signal processor and block for controlling executive implements of robot. Digital signal processor performs processing of image, going as follows: increase of brightness and contrast of image, transferring semi-tone image to two-gradation one, singling out contours, objects, determining position of objects. On basis of received data control block for robot implements drives trajectory of robot displacement, selects necessary command and forms controlling signals.

EFFECT: higher efficiency.

1 dwg

FIELD: technology for biometric control and authentication.

SUBSTANCE: on basis of registered biometric data only those characteristic data are received, which are unambiguously reproducible. Then on basis of these unambiguously reproducible characteristic data additional set of access key parameters is generated, which represents personal identification code, or on basis of which such an identification code can be generated.

EFFECT: when implemented for recognition and reading of biometric data, fingerprints in particular, higher reliability and resistance to interference during identification of persons.

4 cl, 1 dwg

Up!