CN114298081A - Identification method, device, electronic device and storage medium for target behavior - Google Patents

Abstract

The application relates to an identity recognition method, an identity recognition device, electronic equipment and a storage medium for target behaviors, wherein the method comprises the following steps: determining identity coordinate information according to all the face information acquired in the current personnel arrangement mode and target behavior information matched with each face information; the target behavior information comprises behavior coordinates under a camera coordinate system, and the identity coordinate information comprises identities and corresponding behavior coordinates of all personnel under the camera coordinate system; when a face image matched with the current target behavior cannot be identified, acquiring a coordinate position corresponding to the current target behavior in a camera coordinate system; and matching the coordinate position with the identity coordinate information to obtain identity information corresponding to the current target behavior. Through the method and the device, the data volume of the captured effective behaviors is improved, and the accuracy of the analysis result obtained by supporting the data is ensured.

Description

Identification method, device, electronic device and storage medium for target behavior

technical field

The present application relates to the technical field of image processing, and in particular, to an identification method, apparatus, electronic device and storage medium for target behavior.

Background technique

With the progress of society, more and more attention is paid to user identification. However, in the current face recognition scene, it is impossible to use effective data as a support to indicate the accuracy of the recognition result. With the development of science and technology, through the technology of video collection, face recognition and behavior recognition, the target behavior of the target person can be collected. Follow-up application analysis, such as in the fields of security, attendance and door locks. The process is generally as follows: the behavior information of the target person and the corresponding face information are collected, and the identity corresponding to the behavior information is determined by comparing the face information with the pre-stored face pictures in the database, and finally saved in the database.

When performing identification in the above manner, the collected face image is compared with the pre-stored face image on the device. If the comparison is successful, it will be recorded, and if the comparison is unsuccessful, it will be discarded. However, under normal circumstances, behavior data is collected in many cases, but the face identified by the behavior data is invalid, for example, the target person bows his head in a certain period of time. In this case, the behavior data will be lost, resulting in only part of the data collected, and the final result of statistical analysis with this part of the data is less accurate.

SUMMARY OF THE INVENTION

Embodiments of the present application provide an identification method, device, electronic device, and storage medium for target behavior, so as to at least solve the problem of low accuracy of statistical analysis based on target behavior information in the related art.

In a first aspect, an embodiment of the present application provides a method for identifying a target behavior, including:

The identity coordinate information is determined according to all the face information collected under the current personnel arrangement and the target behavior information matched with each face information; the target behavior information includes the behavior coordinates in the camera coordinate system, and the identity coordinate information includes The identity of each person in the camera coordinate system and the corresponding behavioral coordinates;

When there is a face image that matches the current target behavior and cannot be recognized, obtain the coordinate position corresponding to the current target behavior in the camera coordinate system;

Matching the coordinate position with the identity coordinate information to obtain identity information corresponding to the current target behavior.

In some of these embodiments, according to all the face information collected under the current personnel arrangement and the target behavior information matched with each face information, determining the identity coordinate information includes:

Obtain face information in the current personnel arrangement, and identify the face information to obtain identity information;

Determine a plurality of potential position coordinates corresponding to the face information based on the target behavior information matched by the face information;

Based on the identity information and a plurality of the potential location coordinates, the identity coordinate information corresponding to the identity information is determined.

In some of the embodiments, determining the identity coordinate information corresponding to the identity information based on the identity information and a plurality of the potential location coordinates includes:

determining a coordinate frame based on a plurality of the potential location coordinates;

Based on the identity information and the coordinate interval in which the coordinate frame is located, the identity coordinate information corresponding to the identity information is determined.

In some of these embodiments, determining a coordinate frame based on a plurality of the potential location coordinates includes:

determining at least two first boundary coordinates based on a plurality of said potential location coordinates;

The first boundary coordinate is calibrated based on the preset offset value to obtain the corresponding second boundary coordinate;

A coordinate box is delineated based on the second boundary coordinates.

In some of the embodiments, acquiring the coordinate position corresponding to the current target behavior in the camera coordinate system includes:

Obtain the target behavior information corresponding to the current target behavior;

The target behavior information is input into the trained coordinate detection model to obtain the coordinate position corresponding to the current target behavior matched with the face image.

In some of the embodiments, matching the coordinate position with the identity coordinate information to obtain the identity information corresponding to the current target behavior includes:

matching the coordinate position with the behavior coordinate corresponding to the identity coordinate information;

When the coordinate position matches the behavior coordinate, the identity information corresponding to the behavior coordinate is determined as the identity information corresponding to the target behavior information.

In some of these embodiments, the target behavior information further includes at least one of the following:

Behavior picture, behavior identification, behavior type, behavior occurrence time.

In a second aspect, an embodiment of the present application provides a target behavior identification device, including:

The identity coordinate information determination unit is used to determine the identity coordinate information according to all the face information collected under the current personnel arrangement and the target behavior information matched with each face information; the target behavior information includes the behavior in the camera coordinate system Coordinates, the identity coordinate information includes the identity of each person in the camera coordinate system and the corresponding behavior coordinates;

a coordinate position obtaining unit, used for obtaining the coordinate position corresponding to the current target behavior in the camera coordinate system when there is a face image that matches the current target behavior and cannot be recognized;

An identity information identification unit, configured to match the coordinate position with the identity coordinate information to obtain identity information corresponding to the current target behavior.

In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, when the processor executes the computer program An identification method for realizing the target behavior described in the first aspect above.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the identification method for the target behavior described in the first aspect above.

Compared with the related art, the method for identifying the target behavior provided by the embodiment of the present application determines the identity coordinate information according to all the face information collected under the current personnel arrangement and the target behavior information matched with the face information, and uses The data collected under the current personnel arrangement is used to determine the identity coordinate information, and the potential value of the existing data is maximized. By obtaining the coordinate position corresponding to the current target behavior in the camera coordinate system when there is a face image matching the current target behavior that cannot be recognized; and matching the coordinate position with the identity coordinate information to obtain the current target behavior corresponding identity information. By using the identity coordinate information to match the target behavior information corresponding to the face information, the corresponding identity information is obtained, which significantly improves the identification rate of the target behavior information, increases the amount of data of the captured effective behavior, and ensures that the data The accuracy of the analytical results obtained by doing the support.

The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below in order to make other features, objects and advantages of the application more apparent.

Description of drawings

The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The schematic embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation of the present application. In the attached image:

1 is a schematic flowchart of an identification method for target behavior in one of the embodiments of the present application;

2 is a schematic flowchart of determining identity coordinate information in one of the embodiments of the present application;

3 is a schematic flowchart of determining the identity coordinate information corresponding to the identity information in one of the embodiments of the present application;

4 is a structural block diagram of an identification device for target behavior in one of the embodiments of the present application;

FIG. 5 is a schematic structural diagram of an electronic device in one embodiment of the present application.

Description of the drawings: 201, an identity coordinate information determination unit; 202, a coordinate position acquisition unit; 203, an identity information identification unit; 30, a bus; 31, a processor; 32, a memory; 33, a communication interface.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

Obviously, the accompanying drawings in the following description are only some examples or embodiments of the present application. For those of ordinary skill in the art, the present application can also be applied to the present application according to these drawings without any creative effort. other similar situations. In addition, it will also be appreciated that while such development efforts may be complex and lengthy, for those of ordinary skill in the art to which the present disclosure pertains, the techniques disclosed in this application Some changes in design, manufacture or production based on the content are only conventional technical means, and it should not be understood that the content disclosed in this application is not sufficient.

Reference in this application to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor a separate or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

Unless otherwise defined, the technical or scientific terms involved in this application shall have the usual meanings understood by those with ordinary skill in the technical field to which this application belongs. Words such as "a", "an", "an", "the" and the like mentioned in this application do not denote a quantitative limitation, and may denote the singular or the plural. The terms "comprising", "comprising", "having" and any of their variants referred to in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or process comprising a series of steps or modules (units) The apparatus is not limited to the steps or units listed, but may further include steps or units not listed, or may further include other steps or units inherent to the process, method, product or apparatus. Words like "connected," "connected," "coupled," and the like referred to in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "plurality" referred to in this application refers to two or more. "And/or" describes the association relationship between associated objects, indicating that there can be three kinds of relationships. For example, "A and/or B" can mean that A exists alone, A and B exist at the same time, and B exists alone. The character "/" generally indicates that the associated objects are an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only to distinguish similar objects, and do not represent a specific order for the objects.

The target behavior identification method described in this application can be applied to various application scenarios, including but not limited to attendance, administration, and performance, which are not specifically limited in this application.

This embodiment provides an identification method for target behavior. FIG. 1 is a flowchart of a method for identifying a target behavior according to an embodiment of the present application. As shown in FIG. 1 , the flowchart includes the following steps:

Step S11: Determine identity coordinate information according to all face information collected under the current personnel arrangement and target behavior information matched with each face information; the target behavior information includes behavior coordinates in the camera coordinate system, and the identity The coordinate information includes the identity of each person in the camera coordinate system and the corresponding behavioral coordinates.

Usually, under the fixed arrangement of personnel, the position of the same person in the same space will not change significantly, so the target behavior of personnel has a relatively fixed range of activities. In order to maximize the potential value of existing data, the face information and matching target behavior information under the current personnel arrangement can be collected to determine the identity coordinate information. The current personnel arrangement may be a fixed position of personnel arrangement, such as seats, formations, etc.; the identity coordinate information includes the identity of each person and the corresponding coordinate information, and the identity and the corresponding coordinate information are bound by binding the identity and the corresponding coordinate information. , which can be used as the identification basis for subsequent target behaviors.

In this embodiment, after the face information is collected, the corresponding identity information can be obtained through an image recognition technology. At the same time, obtain the target behavior information matching the face information, the target behavior information includes the behavior coordinates in the camera coordinate system, and the behavior coordinates may be the coordinates of the preset key points (such as head, mouth, etc.) corresponding to the person, or All coordinates or coordinate mean values corresponding to multiple preset key points (such as left and right wrists, etc.) can be customized and configured, which is not limited in this application. Optionally, the target behavior information also includes at least one of the following: behavior pictures, behavior signs (such as sitting, standing, raising hands, etc.), behavior types (such as posture, face orientation, etc.), behavior occurrence time, etc. The behavior information is identified and recorded, which is convenient for information traceability of the target behavior.

Step S12, when there is a face image that matches the current target behavior and cannot be recognized, obtain the coordinate position corresponding to the current target behavior in the camera coordinate system.

In the related art, when identifying the target behavior information, it often happens that the face recognition cannot obtain an effective identity (for example, when the target person bows his head, turns his head sideways, or turns his back to the camera), so that the collected target behavior information is invalid.

In this embodiment, when there is a face image that matches the current target behavior and cannot be recognized, it is also used as valid data and the corresponding coordinate position in the camera coordinate system is obtained. Specifically, a camera coordinate system where the image captured by the camera is located is established, and the coordinate position corresponding to the target behavior information is obtained by identifying and analyzing the data information in the target image captured by the camera. In some embodiments, the coordinate position may be the action coordinate in the corresponding camera coordinate system, so as to be consistent with the identity coordinate information, so as to facilitate matching with the identity coordinate information; in other embodiments, the coordinate position may also be Other self-defined location information obtained based on the current target behavior, as long as it can be matched with the identity coordinate information, is not limited in this application.

Step S13: Match the coordinate position with the identity coordinate information to obtain identity information corresponding to the current target behavior.

Specifically, in this embodiment, coordinate matching is performed between the coordinate position and the behavior coordinate in the identity coordinate information, and the identity information corresponding to the behavior coordinate when the matching is consistent is determined as the identity corresponding to the current target behavior information. The matching method may be that the coordinates are completely consistent, partially consistent, or that the coordinate position corresponding to the current target behavior falls within the coordinate range where the behavior coordinates are located, which is not specifically limited in this application.

The embodiments of the present application will be described and illustrated below through preferred embodiments.

To sum up, the method for identifying the target behavior provided by the embodiment of the present application determines the coordinate information of the identity by determining the coordinate information of the identity according to all the face information collected under the current personnel arrangement and the information of the target behavior matched with the information of each face. The coordinate information includes the identity of each person in the camera coordinate system and the corresponding coordinate information. The data collected under the current personnel arrangement is used to determine the identity coordinate information, which maximizes the potential value of the existing data. By obtaining the coordinate position corresponding to the current target behavior in the camera coordinate system when there is a face image matching the current target behavior that cannot be recognized; and matching the coordinate position with the identity coordinate information to obtain the current target behavior corresponding identity information. By using the identity coordinate information to match the target behavior information corresponding to the face information, the corresponding identity information is obtained, which significantly improves the identification rate of the target behavior information, increases the amount of data of the captured effective behavior, and ensures that the data The accuracy of the analytical results obtained by doing the support.

As shown in FIG. 2 , on the basis of the above-mentioned embodiments, in some of the embodiments, the identity coordinate information is determined according to all the face information collected under the current personnel arrangement and the target behavior information matched with each face information. include:

Step S111: Acquire face information in the current personnel arrangement, and identify the face information to obtain identity information. Specifically, a recognition algorithm based on facial feature points, a recognition algorithm based on an entire face image, a recognition algorithm based on a template, an algorithm for recognition using a neural network, etc. can be used for facial information recognition. The face recognition algorithm is a general algorithm, which is not described or limited in detail in this application.

Step S112: Determine a plurality of potential position coordinates corresponding to the face information based on the target behavior information matched with the face information. Specifically, after the identity coordinate information is determined, under the current arrangement of personnel, the location coordinates corresponding to each individual will inevitably change slightly within a certain range. Therefore, in order to adapt the identification method to the weak movement of the person, for the face information for which the identity information can be identified, a plurality of potential position coordinates can be further obtained based on the target behavior information matched with the face information. Among them, the potential position coordinates are the behavior coordinates of a certain target behavior corresponding to the same face information, and the selection and calculation methods of different potential position coordinates are the same.

Step S113: Determine identity coordinate information corresponding to the identity information based on the identity information and a plurality of the potential position coordinates.

Specifically, in this embodiment, the behavior coordinates corresponding to the current target behavior may be calculated based on a plurality of the potential position coordinates. The specific calculation method may directly take the mean value of a plurality of the potential position coordinates to obtain the behavior coordinates, or may perform further data screening based on the multiple potential position coordinates to calculate the behavior coordinates, which is not limited in this embodiment. Then, based on the identity information and the behavior coordinates corresponding to the current target behavior, the identity coordinate information is determined.

As shown in FIG. 3, on the basis of the foregoing embodiments, in some of the embodiments, based on the identity information and a plurality of the potential location coordinates, determining the identity coordinate information corresponding to the identity information includes:

Step S1131, determining a coordinate frame based on a plurality of the potential position coordinates.

In this embodiment, based on a plurality of the potential position coordinates, the coordinate interval in which the behavior coordinates are located can be obtained. Specifically, firstly, first boundary coordinates are determined based on a plurality of the potential position coordinates. A coordinate interval (P1[x1,y1], P2[x2,y2]) can be obtained according to at least two of the first boundary coordinates, so as to include all potential position coordinates. In some embodiments, the coordinate frame can be determined according to the two first boundary coordinates; in other embodiments, the maximum and minimum axial directions of the X and Y directions are respectively taken from the three or four first boundary coordinates. Coordinate value to get the corresponding coordinate interval. For example: when the multiple potential positions are (A1[1,0.5], A2[2,4], A3[3,2], A4[4,3]), then according to A1[1,0.5], A2[2,4] and A4[4,3] can determine the coordinate frame, and take the maximum and minimum axial coordinate values in the X and Y directions from the three or four first boundary coordinates, respectively, to obtain the corresponding coordinates interval(P1[1,4], P2[4,0.5]).

Then, the first boundary coordinates are calibrated based on the preset offset value to obtain corresponding second boundary coordinates, and a coordinate frame is delineated based on the second boundary coordinates. Since the coordinate interval delimited based on the first boundary coordinates is relatively rough, an offset process needs to be performed to further refine the range of the coordinate interval and ensure the accuracy of the recognition result. Specifically, in some embodiments, when the offset value takes the interval width of 1/4-1/8 times the coordinate interval, the accuracy is the highest. Exemplarily, in the coordinate interval (P1[x1,y1], P2[x2,y2]), x1 is translated to the right by (x2-x1)/8, x2 is translated to the left by (x2-x1)/8, and y1 is down Translate (y2-y1)/8, y2 translates up (y2-y1)/8. The final coordinate interval is optimized to (P1[x1+(x2-x1)/8, y1+(y2-y1)/8], P2[x2-(x2-x1)/8, y2-(y2-y1)/8]) . The offset value can be customized and configured, and the size of the offset value depends on the distribution of personnel under the current personnel arrangement.

Step S1132: Determine the identity coordinate information corresponding to the identity information based on the identity information and the coordinate interval in which the coordinate frame is located.

In this embodiment, the coordinate interval in which the coordinate frame is located is determined as the behavior coordinate of the target behavior information in the camera coordinate system, and is bound with the identity information corresponding to the target behavior information to obtain the identity coordinate information.

Through the above steps, a coordinate frame is determined based on a plurality of the potential position coordinates, the coordinate interval where the coordinate frame is located is taken as the behavior coordinate of the target behavior information in the camera coordinate system, and it is bound with the identity information corresponding to the target behavior information. It can adapt to the weak movement of people and improve the identification rate of target behavior information.

On the basis of the foregoing embodiments, in some of the embodiments, acquiring the coordinate position corresponding to the current target behavior in the camera coordinate system includes:

Obtain target behavior information corresponding to the current target behavior, input the target behavior information into the trained coordinate detection model, and obtain the coordinate position corresponding to the current target behavior matched with the face image.

In this embodiment, the coordinate position corresponding to the target behavior information can be identified through a trained coordinate detection model. Among them, the coordinate detection model can be obtained by establishing a video image training sample set containing the coordinate position labels corresponding to the target behavior information, and using the training sample set to train a preset detection model, and the preset detection model is an OpenPose, Detectron or AlphaPose model, etc. Open source model.

It should be noted that the steps shown in the above flow or the flow chart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical sequence is shown in the flow chart, in the In some cases, steps shown or described may be performed in an order different from that herein.

This embodiment also provides a target behavior identification device, which is used to implement the above embodiments and preferred implementations, and what has been described will not be repeated. As used below, the terms "module," "unit," "subunit," etc. may be a combination of software and/or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, implementations in hardware, or a combination of software and hardware, are also possible and contemplated.

4 is a structural block diagram of a target behavior identification device according to an embodiment of the present application, as shown in FIG.

The identity coordinate information determination unit 201 is used to determine the identity coordinate information according to all the face information collected under the current personnel arrangement and the target behavior information matched with each face information; the target behavior information includes the camera coordinate system. Behavior coordinates, the identity coordinate information includes the identity of each person in the camera coordinate system and the corresponding behavior coordinates;

The coordinate position obtaining unit 202 is used to obtain the coordinate position corresponding to the current target behavior under the camera coordinate system when there is a face image that matches the current target behavior and cannot be recognized;

The identity information identification unit 203 is configured to match the coordinate position with the identity coordinate information to obtain identity information corresponding to the current target behavior.

In some of these embodiments, the target behavior information further includes at least one of the following:

Behavior picture, behavior identification, behavior type, behavior occurrence time.

In some of these embodiments, the identity coordinate information determination unit 201 includes: an identity information acquisition module, a potential location coordinate acquisition module, and an identity coordinate acquisition module.

The identity information acquisition module is used to acquire the face information under the current personnel arrangement, and identify the face information to obtain the identity information;

A potential position coordinate acquisition module, configured to determine a plurality of potential position coordinates corresponding to the face information based on the target behavior information matched with the face information;

An identity coordinate acquisition module, configured to determine identity coordinate information corresponding to the identity information based on the identity information and a plurality of the potential position coordinates.

In some of the embodiments, the identity coordinate acquisition module includes: a coordinate frame determination module and an identity coordinate determination module.

a coordinate frame determination module, configured to determine a coordinate frame based on a plurality of the potential position coordinates;

The identity coordinate determination module is configured to determine the identity coordinate information corresponding to the identity information based on the identity information and the coordinate interval in which the coordinate frame is located.

In some of these embodiments, the coordinate frame determination module includes: a first boundary coordinate determination module, a second boundary coordinate determination module, and a coordinate frame delineation module.

a first boundary coordinate determination module, configured to determine at least two first boundary coordinates based on a plurality of the potential position coordinates;

A second boundary coordinate determination module, configured to calibrate the first boundary coordinate based on a preset offset value to obtain a corresponding second boundary coordinate;

A coordinate frame delineation module, configured to delineate a coordinate frame based on the second boundary coordinates.

In some of these embodiments, the coordinate position obtaining unit 202 includes: a target behavior information obtaining module and a coordinate position determining module.

The target behavior information acquisition module is used to acquire the target behavior information matched with the face information;

The coordinate position determination module is used for inputting the target behavior information into the trained coordinate detection model to obtain the coordinate position corresponding to the target behavior information matched with the face information.

In some of these embodiments, the identity information identification unit 203 includes: a matching module and an identity identification module.

a matching module, configured to match the coordinate position with the behavioral coordinates corresponding to the identity coordinate information;

An identity recognition module, configured to determine the identity information corresponding to the behavior coordinate as the identity information corresponding to the target behavior information when the coordinate position matches the behavior coordinate.

It should be noted that each of the above modules may be functional modules or program modules, and may be implemented by software or hardware. For the modules implemented by hardware, the above-mentioned modules may be located in the same processor; or the above-mentioned modules may also be located in different processors in any combination.

In addition, the method for identifying the target behavior in the embodiment of the present application described in conjunction with FIG. 1 may be implemented by an electronic device. FIG. 5 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application.

The electronic device may include a processor 31 and a memory 32 storing computer program instructions.

Specifically, the above-mentioned processor 31 may include a central processing unit (CPU), or a specific integrated circuit (Application Specific Integrated Circuit, ASIC for short), or may be configured as one or more integrated circuits implementing the embodiments of the present application.

Among other things, the memory 32 may include mass storage for data or instructions. By way of example and not limitation, the memory 32 may include a Hard Disk Drive (HDD), a floppy disk drive, a Solid State Drive (SSD), flash memory, optical disk, magneto-optical disk, magnetic tape, or universal serial bus (Universal SerialBus, abbreviated as USB) drive or a combination of two or more of these. Memory 32 may include removable or non-removable (or fixed) media, as appropriate. Where appropriate, memory 32 may be internal or external to the data processing device. In certain embodiments, the memory 32 is a non-volatile (Non-Volatile) memory. In a specific embodiment, the memory 32 includes a read-only memory (Read-Only Memory, referred to as ROM for short) and a random access memory (Random Access Memory, referred to as RAM for short). In a suitable case, the ROM can be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, referred to as PROM), an erasable PROM (Erasable Programmable Read-Only Memory, referred to as EPROM), an electrically erasable PROM. Except for PROM (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), Electrically Rewritable ROM (Electrically Alterable Read-Only Memory, referred to as EAROM) or flash memory (FLASH) or a combination of two or more of these. In appropriate cases, the RAM may be Static Random-Access Memory (SRAM for short) or Dynamic Random Access Memory (DRAM for short), where DRAM may be a fast page Mode dynamic random access memory (Fast Page Mode Dynamic Random Access Memory, referred to as FPMDRAM), Extended Date Out Dynamic Random Access Memory (Extended Date Out Dynamic Random Access Memory, referred to as EDODRAM), Synchronous Dynamic Random Access Memory (Synchronous Dynamic Random Access Memory) Random-Access Memory, referred to as SDRAM) and so on.

The memory 32 may be used to store or cache various data files required for processing and/or communication use, and possibly computer program instructions executed by the processor 31 .

The processor 31 reads and executes the computer program instructions stored in the memory 32 to implement any one of the target behavior identification methods in the foregoing embodiments.

In some of these embodiments, the electronic device may also include a communication interface 33 and a bus 30 . Among them, as shown in FIG. 5 , the processor 31 , the memory 32 , and the communication interface 33 are connected through the bus 30 and complete the mutual communication.

The communication interface 33 is used to implement communication between modules, apparatuses, units, and/or devices in the embodiments of the present application. The communication interface 33 can also implement data communication with other components such as: external devices, image/data acquisition devices, databases, external storage, and image/data processing workstations.

The bus 30 includes hardware, software, or both, coupling the components of the electronic device to each other. The bus 30 includes, but is not limited to, at least one of the following: a data bus (Data Bus), an address bus (Address Bus), a control bus (Control Bus), an expansion bus (Expansion Bus), and a local bus (Local Bus). By way of example and not limitation, the bus 30 may include an Accelerated Graphics Port (AGP) or other graphics buses, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (Front Side Bus) , referred to as FSB), Hyper Transport (Hyper Transport, referred to as HT) interconnect, Industry Standard Architecture (Industry Standard Architecture, referred to as ISA) bus, wireless bandwidth (InfiniBand) interconnect, Low Pin Count (Low Pin Count, LPC) bus, memory bus, Micro Channel Architecture (MCA) bus, Peripheral Component Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local Bus (VLB) bus or other suitable bus or a combination of two or more of these. Where appropriate, bus 30 may include one or more buses. Although embodiments of this application describe and illustrate a particular bus, this application contemplates any suitable bus or interconnect.

The electronic device may execute the method for identifying the target behavior in the embodiment of the present application based on the acquired program instruction, so as to realize the method for identifying the target behavior described in conjunction with FIG. 1 .

In addition, in combination with the method for identifying the target behavior in the foregoing embodiments, the embodiment of the present application may provide a computer-readable storage medium for implementation. Computer program instructions are stored on the computer-readable storage medium; when the computer program instructions are executed by the processor, any one of the target behavior identification methods in the foregoing embodiments is implemented.

It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all Information and data authorized by the user or fully authorized by the parties.

The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity, all possible combinations of the technical features in the above-described embodiments are not described. However, as long as there is no contradiction between the combinations of these technical features, All should be regarded as the scope described in this specification.

The above-mentioned embodiments only represent several embodiments of the present application, and the descriptions thereof are specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims (10)

1. An identity recognition method for target behaviors, comprising:

determining identity coordinate information according to all the face information acquired in the current personnel arrangement mode and target behavior information matched with each face information; the target behavior information comprises behavior coordinates under a camera coordinate system, and the identity coordinate information comprises identities and corresponding behavior coordinates of all personnel under the camera coordinate system;

when a face image matched with the current target behavior cannot be identified, acquiring a coordinate position corresponding to the current target behavior in a camera coordinate system;

and matching the coordinate position with the identity coordinate information to obtain identity information corresponding to the current target behavior.

2. The method for identifying the identity of the target behavior according to claim 1, wherein determining the identity coordinate information according to all the face information collected in the current people arrangement mode and the target behavior information matched with each face information comprises:

acquiring face information under a current personnel arrangement mode, and identifying the face information to obtain identity information;

determining a plurality of potential position coordinates corresponding to the face information based on the target behavior information matched with the face information;

and determining identity coordinate information corresponding to the identity information based on the identity information and the plurality of potential position coordinates.

3. The method of claim 2, wherein determining identity coordinate information corresponding to the identity information based on the identity information and a plurality of the potential location coordinates comprises:

determining a coordinate frame based on a plurality of the potential location coordinates;

and determining identity coordinate information corresponding to the identity information based on the identity information and the coordinate interval in which the coordinate frame is located.

4. The method of claim 3, wherein determining a coordinate frame based on the plurality of potential location coordinates comprises:

determining at least two first boundary coordinates based on a plurality of the potential location coordinates;

calibrating the first boundary coordinate based on a preset offset value to obtain a corresponding second boundary coordinate;

defining a coordinate frame based on the second boundary coordinates.

5. The method for identifying the identity of the target behavior according to claim 1, wherein obtaining the coordinate position corresponding to the current target behavior in a camera coordinate system comprises:

acquiring target behavior information corresponding to the current target behavior;

and inputting the target behavior information into a trained coordinate detection model to obtain a coordinate position corresponding to the current target behavior matched with the face image.

6. The identity recognition method of the target behavior according to claim 1, wherein matching the coordinate position with the identity coordinate information to obtain the identity information corresponding to the current target behavior comprises:

matching the coordinate position with a behavior coordinate corresponding to the identity coordinate information;

and when the coordinate position is matched with the behavior coordinate, determining the identity information corresponding to the behavior coordinate as the identity information corresponding to the target behavior information.

7. The method for identifying the target behavior according to claim 1, wherein the target behavior information further comprises at least one of the following:

behavior picture, behavior identification, behavior type and behavior occurrence time.

8. An apparatus for identifying a target behavior, comprising:

the identity coordinate information determining unit is used for determining identity coordinate information according to all the face information acquired in the current personnel arrangement mode and target behavior information matched with each face information; the target behavior information comprises behavior coordinates under a camera coordinate system, and the identity coordinate information comprises identities and corresponding behavior coordinates of all personnel under the camera coordinate system;

the coordinate position acquisition unit is used for acquiring a coordinate position corresponding to the current target behavior in a camera coordinate system when a face image matched with the current target behavior cannot be identified;

and the identity information identification unit is used for matching the coordinate position with the identity coordinate information to obtain identity information corresponding to the current target behavior.

9. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and the processor is configured to execute the computer program to perform the method for identifying an identity of a target activity of any one of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method of identification of a target activity according to any one of claims 1 to 7.

Images