CN112241671A - Personnel identity identification method, device and system - Google Patents

Personnel identity identification method, device and system Download PDF

Info

Publication number
CN112241671A
CN112241671A CN201910653548.9A CN201910653548A CN112241671A CN 112241671 A CN112241671 A CN 112241671A CN 201910653548 A CN201910653548 A CN 201910653548A CN 112241671 A CN112241671 A CN 112241671A
Authority
CN
China
Prior art keywords
target
face
model
person
identity information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201910653548.9A
Other languages
Chinese (zh)
Other versions
CN112241671B (en
Inventor
徐春光
张俊
贾童基
王俊
王晓辉
肖国华
杨海军
刘大煜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Merchants Bank Co Ltd
Hangzhou Hikvision System Technology Co Ltd
Original Assignee
China Merchants Bank Co Ltd
Hangzhou Hikvision System Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Merchants Bank Co Ltd, Hangzhou Hikvision System Technology Co Ltd filed Critical China Merchants Bank Co Ltd
Priority to CN201910653548.9A priority Critical patent/CN112241671B/en
Publication of CN112241671A publication Critical patent/CN112241671A/en
Application granted granted Critical
Publication of CN112241671B publication Critical patent/CN112241671B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/94—Hardware or software architectures specially adapted for image or video understanding
    • G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Library & Information Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Collating Specific Patterns (AREA)
  • Image Analysis (AREA)

Abstract

The embodiment of the invention provides a method, a device and a system for identifying personnel identities. The method is applied to a management server in a video monitoring system; the method comprises the following steps: acquiring a face image of a person to be recognized, and determining a face model of the face image as a model to be recognized; searching a target face model matched with the model to be recognized in the stored face models of all blacklist persons; when the target face model is found, uploading the target face model to a target server, so that the target server searches the corresponding face model as the target identity information of the target face model in the stored identity information of each blacklist person, and feeds the target identity information back to a management server; and receiving target identity information fed back by the target server as identity information of the person to be identified. By applying the scheme provided by the embodiment of the invention, the blacklist personnel appearing in the scene can be quickly and effectively identified based on the collected face images of the personnel.

Description

Personnel identity identification method, device and system
Technical Field
The invention relates to the technical field of computers, in particular to a method, a device and a system for identifying personnel identities.
Background
At present, in order to ensure public safety, a video monitoring system is usually installed in public places such as banks, subway stations, railway stations, airports and the like, and the video monitoring system can acquire images of people appearing in the public places, so that the face images of the people can be obtained. The video acquisition equipment comprises a camera and a management server.
In general, to further identify whether a public place has a potential safety hazard, there is a need to identify blacklisted persons present in the scene. However, since the video monitoring system is widely used, how to quickly and effectively identify blacklist people appearing in a scene based on the collected face images of the people is a problem to be solved urgently.
Disclosure of Invention
The embodiment of the invention aims to provide a person identity identification method, a person identity identification device, a person identity identification system, a management server and a computer readable storage medium, so that blacklisted persons appearing in a scene can be quickly and effectively identified based on collected face images of all persons.
The specific technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a method for identifying a person, which is applied to a management server in a video monitoring system; the management server is connected with a pre-designated target server, the management server stores face models of all blacklist personnel, and the target server correspondingly stores the face models and identity information of all the blacklist personnel;
the method comprises the following steps:
acquiring a face image of a person to be recognized, and determining a face model of the face image as a model to be recognized;
searching a target face model matched with the model to be recognized in the stored face models of the blacklist persons;
when the target face model is found, uploading the target face model to the target server, so that the target server searches the stored identity information of each blacklist person for the target identity information of which the corresponding face model is the target face model, and feeds the target identity information back to the management server;
and receiving the target identity information fed back by the target server as the identity information of the personnel to be identified.
Optionally, in a specific implementation manner, the method further includes:
and when the time is found, outputting early warning prompt information.
Optionally, in a specific implementation manner, the method further includes:
receiving a processing opinion fed back by the target server; the processing opinion is generated and fed back by the target server based on the target identity information after determining the identity type of the person to be identified;
and outputting the target identity information and prompt information corresponding to the processing opinions.
Optionally, in a specific implementation manner, the face model is a feature vector of a face;
the step of searching the target face model matched with the model to be recognized in the stored face models of all blacklist persons comprises the following steps:
calculating the cosine value of the included angle between the model to be recognized and the stored face model of each blacklist person;
and when the calculated cosine value of the maximum included angle is larger than a preset threshold value, determining the face model of the blacklist personnel corresponding to the cosine value of the maximum included angle as a target face model matched with the model to be recognized.
In a second aspect, an embodiment of the present invention provides a personal identification apparatus, which is applied to a management server in a video monitoring system; the management server is connected with a pre-designated target server, the management server stores face models of all blacklist personnel, and the target server correspondingly stores the face models and identity information of all the blacklist personnel;
the device comprises:
the model acquisition module is used for acquiring a face image of a person to be recognized and determining a face model of the face image as a model to be recognized;
the model searching module is used for searching a target face model matched with the model to be recognized in the stored face models of the blacklist persons;
the model uploading module is used for uploading the target face model to the target server when the target face model is found, so that the target server searches the stored identity information of each blacklist person for the target identity information of which the corresponding face model is the target face model, and feeds the target identity information back to the management server;
and the information receiving module is used for receiving the target identity information fed back by the target server and taking the target identity information as the identity information of the person to be identified.
Optionally, in a specific implementation manner, the apparatus further includes:
and the information output module is used for outputting the early warning prompt information when the information is searched.
Optionally, in a specific implementation manner, the apparatus further includes:
the opinion receiving module is used for receiving the processing opinion fed back by the target server; the processing opinion is generated and fed back by the target server based on the target identity information after determining the identity type of the person to be identified;
and the information output module is used for outputting the target identity information and prompt information corresponding to the processing opinions.
Optionally, in a specific implementation manner, the face model is a feature vector of a face;
the model lookup module is specifically configured to:
calculating the cosine value of the included angle between the model to be recognized and the stored face model of each blacklist person; and when the calculated cosine value of the maximum included angle is larger than a preset threshold value, determining the face model of the blacklist personnel corresponding to the cosine value of the maximum included angle as a target face model matched with the model to be recognized.
In a third aspect, an embodiment of the present invention provides a personnel identification system, where the system includes a management server and a pre-designated target server in a video monitoring system; the management server is connected with the target server, the management server stores face models of all blacklist personnel, and the target server correspondingly stores face models and identity information of all the blacklist personnel;
the management server is configured to: acquiring a face image of a person to be recognized, and determining a face model of the face image as a model to be recognized; searching a target face model matched with the model to be recognized in the stored face models of the blacklist persons; when the target face model is found, uploading the target face model to the target server; receiving the target identity information fed back by the target server as the identity information of the person to be identified;
the target server is configured to: receiving the target face model sent by the management service; and searching the stored identity information of each blacklist person for target identity information of which the corresponding face model is the target face model, and feeding back the target identity information to the management server.
Alternatively, in one particular implementation,
the target server is further configured to: after the identity type of the person to be identified is determined based on the target identity information, generating a processing opinion corresponding to the identity type; transmitting the processing opinion to the management server;
the management server is further configured to: receiving the processing opinions fed back by the target server; and outputting the target identity information and prompt information corresponding to the processing opinions.
In a fourth aspect, an embodiment of the present invention provides a management server, which is characterized by including a processor, a communication interface, a memory, and a communication bus, where the processor and the communication interface complete communication between the memory and the processor through the communication bus;
a memory for storing a computer program;
a processor, configured to implement any one of the method steps of the person identification method according to the first aspect when executing a program stored in the memory.
In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and the computer program, when executed by a processor, implements the method steps in any one of the methods for identifying a person provided in the first aspect.
As can be seen from the above, with the method provided by the embodiment of the present invention, after the management server obtains the face image of the person to be recognized, the management server may first determine the face model of the face image, so that the target face model matched with the face image model of the person to be recognized may be searched in the stored face models of the blacklist persons. Obviously, upon finding, the management server may determine that the person to be identified is a blacklisted person. Further, in order to determine the identity information of the person to be identified, the management server may upload the target face model to the target server. Therefore, the target server can search the target identity information corresponding to the target face model and feed the target identity information back to the management server, so that the management server can acquire the identity information of the person to be identified.
Based on the above, by applying the method provided by the embodiment of the invention, whether the person corresponding to the face image is a blacklist person or not can be locally determined at the management server based on the acquired face image, and when the person corresponding to the face image is determined to be the blacklist person, the specific identity information of the person is determined through the target server. Therefore, through the matching of the management server and the target server, the blacklist people appearing in the scene can be quickly and effectively identified based on the collected face images of the people.
Further, the target server may communicate with different management servers in multiple scenes, and receive the face models sent by the different management servers, and based on this, in the embodiment of the present invention, it is locally determined whether a person corresponding to the face model is a blacklist person at each management server, and if it is determined that the person is the blacklist person, the face model is sent to the target server to obtain the identity information of the person, so that the calculation pressure of the target server may be effectively reduced, and since the data volume of the face model is much smaller than the data volume of the face graph, the pressure of the network bandwidth may also be reduced. Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for identifying a person according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an embodiment of step S102 in FIG. 1;
fig. 3 is a schematic flow chart of another method for identifying a person according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a personal identification apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a personnel identification system according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a management server according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, in order to ensure public safety, a video monitoring system is usually installed in public places such as banks, subway stations, railway stations, airports and the like, and the video monitoring system can acquire images of people appearing in the public places, so that the face images of the people can be obtained. The video acquisition equipment comprises a camera and a management server. In general, to further identify whether a public place has a potential safety hazard, there is a need to identify blacklisted persons present in the scene. However, since the video monitoring system is widely used, how to quickly and effectively identify blacklist people appearing in a scene based on the collected face images of the people is a problem to be solved urgently. In order to solve the above technical problem, an embodiment of the present invention provides a method for identifying a person.
First, a method for identifying a person according to an embodiment of the present invention is described below.
Fig. 1 is a schematic flow chart of a method for identifying a person according to an embodiment of the present invention. The method is applied to a management server in the video monitoring system.
The management server is in communication connection with a camera of the video monitoring system, and can acquire various images sent by the camera, for example, images acquired by the camera, for example, images obtained by processing the acquired images by the camera, and the like. In addition, the management server may be any type of electronic device, such as a notebook computer, a desktop computer, and the like, and the embodiments of the present invention are not limited thereto, and will be referred to as the management server hereinafter.
In the embodiment of the invention, the management server can be connected with a pre-designated target server, and the face model of each blacklist person is stored in the management server.
Correspondingly, the target server stores the face model and the identity information of each blacklist person. The target server may obtain the face model and the identity information of each blacklist person in a plurality of ways, which is not limited in the embodiments of the present invention.
Further, after the target server obtains and stores the face model and the identity information of each blacklist person, the stored face model of each blacklist person can be issued to the management server, so that the management server can store the face model of each blacklist person.
Preferably, the target server may update the stored face models and identity information of each blacklisted person periodically, for example, add new face models and identity information of blacklisted persons, or delete existing face models and identity information of blacklisted persons. Furthermore, after the target server updates the stored face models and identity information of the blacklist persons, the target server may send a face model update instruction to the management server, so that the management server updates the face models of the blacklist persons stored by the management server. Therefore, the face models of all blacklist persons stored in the target server and the management server can be kept consistent all the time.
The target server may store the face model and the identity information of each blacklist person in a plurality of ways, which is not limited in the embodiments of the present invention. For example, the target server may store the face model and the identity information of each blacklisted person in the form of a list, where each entry in the list includes the face model of a blacklisted person and the identity information of the blacklisted person.
In addition, the identity information of the blacklist people may include various information such as name, sex, age, native place, academic calendar, identity type, etc. of the blacklist people, and of course, the identity information of the blacklist people may also include other types of information, which is not limited in the embodiment of the present invention.
As shown in fig. 1, a method for identifying a person according to an embodiment of the present invention may include the following steps:
s101: acquiring a face image of a person to be recognized, and determining a face model of the face image as a model to be recognized;
it can be understood that the camera of the video monitoring system can directly send the collected images of the persons to the management server of the video monitoring system after collecting the images of the persons in the monitored place. Thus, the management server needs to perform face detection on the acquired person image so as to acquire a face image in the person image, namely, a face image of the person to be identified;
in addition, after the camera of the video monitoring system collects the images of the persons in the monitored place, the camera can firstly perform image processing on the collected images of the persons so as to obtain the face images in the images of the persons, and then the obtained face images are sent to the management server as the face images of the persons to be identified. Therefore, the management server can directly acquire the face image of the person to be recognized.
Based on this, the management server can acquire the face image of the person to be recognized in various ways. The embodiment of the present invention is not particularly limited.
Preferably, when the management server receives the acquired personnel images of the personnel sent by the camera, the management server can detect a face area from the received personnel images and obtain a face frame set after detecting the face area; then, based on the face frame set, a face image, that is, an image containing an area within the face frame, is extracted from the received person image.
It is understood that one or more face regions may exist in one person image, or no face region may exist; when one or more face regions exist, the corresponding number of face frames can be obtained, and then the corresponding number of face images can be obtained. The face frame set is a set related to at least one face frame, and the face frame is a rectangular frame surrounding a face area. Moreover, because the face frame can be represented by the coordinate information, the face frame set may specifically include at least one piece of coordinate information, and each piece of coordinate information may determine one face frame.
Optionally, for complete expression of the face image, the face frame may be expanded outward to obtain a new rectangle, and the image block surrounded by the new rectangle is extracted to obtain the face image. The specific implementation manner of the outward expansion may adopt any manner capable of implementing the region expansion, and the embodiment of the present invention is not particularly limited.
Moreover, any manner of detecting the face region from the image may be adopted as a specific implementation manner of detecting the face region from the received person image. For example, a face region may be detected from a received person image using a pre-trained face detection model. The network types of the face detection model can be various, for example: MTCNN (Multi-task shielded connected Networks) network, SSH (single stage header) network, but is not limited thereto.
Furthermore, in step S101, after the face image of the person to be recognized is acquired, the management server may determine a face model of the person to be recognized based on the face image, and use the face model as the model to be recognized. The management server may determine the face model of the person to be recognized based on the face image in various ways, which is not limited in the embodiments of the present invention.
For example, after a face image of a person to be recognized is acquired, the management server may determine target feature information of a face in the face image. The target feature information may include key point information.
The key point information is coordinate information of each key point of the face area. Since the coordinate information of each key point is x-axis coordinate information and y-axis coordinate information, the coordinate information of each key point is 2-dimensional information. Based on this, the key point information is multi-dimensional information, and twice the number of the key points is the dimension of the key information, for example: the number of the respective keypoints is 106, and then the dimension of the keypoint information is 212 dimensions. Further, the identification of the key point information may be performed in any manner capable of identifying the key point information, for example: and identifying the key point information of the face in the face image through a pre-trained key point identification model.
S102: searching a target face model matched with the model to be recognized in the stored face models of all blacklist persons;
after the step S101 is executed and the model to be recognized is obtained, the management server may search the stored face models of each blacklist person for a target face model matching the model to be recognized.
The management server may search a target face model matched with the model to be recognized in the stored face models of each blacklist person in a plurality of ways, which is not specifically limited in the embodiments of the present invention.
Optionally, in a specific implementation manner, the model to be recognized determined by the management device is a feature vector of a face of the person to be recognized, and the face model of each blacklist person stored by the management server is a feature vector of a face of each blacklist person.
Based on this, as shown in fig. 2, the way for the management server to search the stored face models of each blacklist person for the target face model matching the model to be recognized may include the following steps:
s201: calculating the cosine value of the included angle between the model to be recognized and the stored face model of each blacklist person;
s202: and when the calculated cosine value of the maximum included angle is larger than a preset threshold value, determining the face model of the blacklist personnel corresponding to the cosine value of the maximum included angle as a target face model matched with the model to be recognized.
Specifically, in this specific implementation manner, when the management server generates the model to be recognized, the management server may perform face modeling based on image data of a face image included in a face image of a person to be recognized, so as to extract the face model, and determine the face model as the model to be recognized. Because the model to be recognized is a multi-dimensional vector, the model to be recognized is a feature vector of a human face.
Similarly, in this specific implementation manner, the target server may obtain, for each blacklist person, a face image of the blacklist person, and further perform face modeling based on image data of a face included in the face image of the blacklist person, so as to extract a face model of the blacklist person. Because the face model of the blacklist person is a multidimensional vector, the face model of the blacklist person stored by the target server is a feature vector. Correspondingly, the face model of each blacklisted person stored by the management server is also a feature vector.
Thus, in this specific implementation manner, for each stored face model of the blacklist person, the management server may calculate the cosine value of the included angle between the model to be recognized and the face model of the blacklist person. Specifically, for each stored face model of the blacklisted person, the management server may calculate the cosine value of the included angle between the model to be recognized and the face model of the blacklisted person according to the following formula.
Figure BDA0002136099340000101
Wherein cos (theta) is a cosine value of an included angle between the model to be recognized and the face model of the blacklist person. The cosine value of the included angle, A is a model to be recognized, B is a face model of the blacklist person, AiIs the value of the element of the ith element in the model A to be recognized, BiThe element value of the ith element in the face model B of the blacklist person is shown.
According to the correlation property of the cosine value of the included angle of the vector and the value of the cosine value of the included angle as [0,1], in the specific implementation manner, the closer the calculated cosine value of the included angle is to 1, the higher the similarity between the model to be recognized and the face model of the blacklist person is, that is, the more the model to be recognized and the face model of the blacklist person are matched.
Therefore, when the calculated maximum included angle cosine value is larger than the preset threshold value, the management server can determine the face model of the blacklist person corresponding to the maximum included angle cosine value as the target face model matched with the model to be recognized.
S103: when the target person face model is found, uploading the target person face model to a target server, so that the target server finds the target identity information of which the corresponding face model is the target person face model in the stored identity information of each target person, and feeds the target identity information back to a management server;
s104: and receiving target identity information fed back by the target server as identity information of the person to be identified.
Thus, after the step S102 is executed, and the target face model matched with the model to be recognized is determined, the management server may determine that the person to be recognized is a blacklist person, and therefore, the management server needs to further determine various kinds of identity information of the person to be recognized.
Based on this, the management server may continue to perform step S103, and upload the target face model to the target server.
Thus, after receiving the target face model, the target server may search, from the stored face models and identity information of each blacklist person, for target identity information of the target face model corresponding to the face model, which may indicate that the searched target identity information is identity information of a person to be identified. Further, the target server can feed back the searched target identity information to the management server.
Further, the management server may execute the step S104, receive the target identity information sent by the target server, and use the received target identity information as the identity information of the person to be identified.
As can be seen from the above, by applying the method provided by the embodiment of the present invention, whether a person corresponding to the face image is a blacklist person or not can be locally determined at the management server based on the collected face image, and when the person is determined to be a blacklist person, the specific identity information of the person is determined by the target server. Therefore, through the matching of the management server and the target server, the blacklist people appearing in the scene can be quickly and effectively identified based on the collected face images of the people.
Further, the target server may communicate with different management servers in multiple scenes, and receive the face models sent by the different management servers, and based on this, in the embodiment of the present invention, it is locally determined whether a person corresponding to the face model is a blacklist person at each management server, and if it is determined that the person is the blacklist person, the face model is sent to the target server to obtain the identity information of the person, so that the calculation pressure of the target server may be effectively reduced, and since the data volume of the face model is much smaller than the data volume of the face graph, the pressure of the network bandwidth may also be reduced.
In addition, when the management server executes the step S102 and finds the target face model matching the model to be recognized in the stored face models of the respective blacklist persons, the management server may determine that the person to be recognized is the blacklist person.
Based on this, in order to ensure the safety of public places and eliminate potential safety hazards as early as possible, optionally, in a specific implementation manner, when the potential safety hazards are found, early warning prompt information is output.
In this specific implementation manner, when the management server finds a target face model matching the model to be recognized from the stored face models of each blacklist person, the management server may output the early warning prompt information in various manners.
The early warning prompt information can be only output to managers in the public place, all persons in the public place, a certain specific person in the public place and the like. When the early warning prompt information is output to a manager in a public place and/or a specific person in the public place, the manager and/or the specific person can take various measures to ensure the safety of the public place and eliminate the potential safety hazard of the public place.
In addition, the early warning prompt message can be a voice prompt message, can also be a text prompt message displayed in a display screen, and can also simultaneously comprise the voice prompt message and the text prompt message.
In this specific implementation, the manner of presentation of the warning presentation information and the person to whom it is directed are not limited.
Further, optionally, in a specific implementation manner, as shown in fig. 3, on the basis of including S101 to S104, the method for identifying a person provided in the embodiment of the present invention may further include the following steps:
s105: receiving a processing opinion fed back by a target server;
the processing opinion is generated and fed back by the target server based on the target identity information after the target server determines the identity type of the person to be identified;
s106: and outputting the target identity information and prompt information corresponding to the processing opinions.
In this specific implementation manner, after receiving the target face model, the target server may search, from the stored face models and identity information of each blacklist person, for target identity information of the target face model corresponding to the face model, which may indicate that the searched target identity information is identity information of a person to be identified. Furthermore, the target server may determine the identity type of the person to be identified based on the target identity information, that is, the target server may obtain the identity type of the person to be identified from the searched target identity information.
It can be understood that, for blacklist persons with different identity types, a manager in a public place can adopt different measures to ensure the safety of the public place, so that after the identity type of a person to be identified is determined, the target server can generate a processing opinion corresponding to the determined identity type, and feed the processing opinion back to the management server.
Therefore, the management server can receive the processing opinions sent by the target server and further display the target identity information and the prompt information corresponding to the processing opinions sent by the management server.
When the manager in the public place and/or a specific person in the public place check that the target is the identity information and the prompt information corresponding to the processing opinions, the measures indicated in the processing opinions can be taken to ensure the safety of the public place and eliminate the potential safety hazard of the public place.
It should be noted that, the target server may feed back the target identity information and the processing opinion to the management server at the same time.
Corresponding to the personnel identity identification method provided by the embodiment of the invention, the embodiment of the invention provides a personnel identity identification device.
Fig. 4 is a schematic structural diagram of a personal identification apparatus according to an embodiment of the present invention. The device is applied to a management server in a video monitoring system; the management server is connected with a pre-designated target server, the management server stores the face model of each blacklist person, and the target server correspondingly stores the face model and the identity information of each blacklist person.
As shown in fig. 4, the apparatus may include the following modules:
the model obtaining module 410 is configured to obtain a face image of a person to be recognized, and determine a face model of the face image as a model to be recognized;
the model searching module 420 is used for searching a target face model matched with the model to be recognized from the stored face models of the blacklist persons;
the model uploading module 430 is configured to upload the target face model to the target server when the target face model is found, so that the target server searches for target identity information of which the corresponding face model is the target face model from the stored identity information of each blacklist person, and feeds back the target identity information to the management server;
and the information receiving module 440 is configured to receive the target identity information fed back by the target server, where the target identity information is used as identity information of the person to be identified.
As can be seen from the above, by applying the method provided by the embodiment of the present invention, whether a person corresponding to the face image is a blacklist person or not can be locally determined at the management server based on the collected face image, and when the person is determined to be a blacklist person, the specific identity information of the person is determined by the target server. Therefore, through the matching of the management server and the target server, the blacklist people appearing in the scene can be quickly and effectively identified based on the collected face images of the people.
Further, the target server may communicate with different management servers in multiple scenes, and receive the face models sent by the different management servers, and based on this, in the embodiment of the present invention, it is locally determined whether a person corresponding to the face model is a blacklist person at each management server, and if it is determined that the person is the blacklist person, the face model is sent to the target server to obtain the identity information of the person, so that the calculation pressure of the target server may be effectively reduced, and since the data volume of the face model is much smaller than the data volume of the face graph, the pressure of the network bandwidth may also be reduced. Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above advantages at the same time.
Optionally, in a specific implementation manner, the apparatus may further include the following modules:
and the information output module is used for outputting the early warning prompt information when the information is searched.
Optionally, in a specific implementation manner, the apparatus may further include the following modules:
the opinion receiving module is used for receiving the processing opinion fed back by the target server; the processing opinion is generated and fed back by the target server based on the target identity information after the target server determines the identity type of the person to be identified;
and the information output module is used for outputting the target identity information and prompt information corresponding to the processing opinions.
Optionally, in a specific implementation manner, the face model may be a feature vector of a face;
in this specific implementation manner, the model searching module 420 may be specifically configured to:
calculating the cosine value of the included angle between the model to be recognized and the stored face model of each blacklist person; and when the calculated cosine value of the maximum included angle is larger than a preset threshold value, determining the face model of the blacklist personnel corresponding to the cosine value of the maximum included angle as a target face model matched with the model to be recognized.
Corresponding to the personnel identity identification method provided by the embodiment of the invention, the embodiment of the invention provides a personnel identity identification system.
Fig. 5 is a schematic structural diagram of a personnel identification system according to an embodiment of the present invention. As shown in fig. 5, the system includes a management server 510 and a pre-designated target server 520 in the video surveillance system.
The management server 510 is connected with the target server 520, the management server 510 stores face models of blacklist persons, and the target server 520 correspondingly stores face models and identity information of the blacklist persons;
the management server 510 is configured to: acquiring a face image of a person to be recognized, and determining a face model of the face image as a model to be recognized; searching a target face model matched with the model to be recognized in the stored face models of all blacklist persons; when the target face model is found, uploading the target face model to a target server 520; receiving target identity information fed back by the target server 520 as identity information of a person to be identified;
target server 520 is configured to: receiving a target face model sent by the management service 510; and searching for target identity information of which the corresponding face model is the target face model from the stored identity information of each blacklist person, and feeding the target identity information back to the management server 510.
As can be seen from the above, by applying the method provided by the embodiment of the present invention, whether a person corresponding to the face image is a blacklist person or not can be locally determined at the management server based on the collected face image, and when the person is determined to be a blacklist person, the specific identity information of the person is determined by the target server. Therefore, through the matching of the management server and the target server, the blacklist people appearing in the scene can be quickly and effectively identified based on the collected face images of the people.
Further, the target server may communicate with different management servers in multiple scenes, and receive the face models sent by the different management servers, and based on this, in the embodiment of the present invention, it is locally determined whether a person corresponding to the face model is a blacklist person at each management server, and if it is determined that the person is the blacklist person, the face model is sent to the target server to obtain the identity information of the person, so that the calculation pressure of the target server may be effectively reduced, and since the data volume of the face model is much smaller than the data volume of the face graph, the pressure of the network bandwidth may also be reduced. Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above advantages at the same time.
Alternatively, in one particular implementation,
the target server 520 may further be configured to: after the identity type of the person to be identified is determined based on the target identity information, generating a processing opinion corresponding to the identity type; transmitting the processing opinions to the management server 510;
the management server 510 may also be used to: receiving the processing opinions fed back by the target server 520; and outputting the target identity information and prompt information corresponding to the processing opinions.
Corresponding to the method for identifying a person identity provided by the above embodiment of the present invention, an embodiment of the present invention further provides an electronic device, as shown in fig. 6, including a processor 601, a communication interface 602, a memory 603, and a communication bus 604, where the processor 601, the communication interface 602, and the memory 603 complete communication with each other through the communication bus 604,
a memory 603 for storing a computer program;
the processor 601 is configured to implement the method for identifying a person according to the embodiment of the present invention when executing the program stored in the memory 603.
Specifically, the personnel identity identification method is applied to a management server in a video monitoring system; the management server is connected with a pre-designated target server, the management server stores the face model of each blacklist person, and the target server correspondingly stores the face model and the identity information of each blacklist person;
the personnel identity identification method comprises the following steps:
acquiring a face image of a person to be recognized, and determining a face model of the face image as a model to be recognized;
searching a target face model matched with the model to be recognized in the stored face models of all blacklist persons;
when the target face model is found, uploading the target face model to a target server, so that the target server searches the corresponding face model as the target identity information of the target face model in the stored identity information of each blacklist person, and feeds the target identity information back to a management server;
and receiving target identity information fed back by the target server as identity information of the person to be identified.
It should be noted that other implementation manners of the method for identifying a person, which are implemented by the processor 601 executing the program stored in the memory 603, are the same as the embodiments of the method for identifying a person, which are provided in the foregoing embodiments of the method, and are not described herein again.
As can be seen from the above, by applying the method provided by the embodiment of the present invention, whether a person corresponding to the face image is a blacklist person or not can be locally determined at the management server based on the collected face image, and when the person is determined to be a blacklist person, the specific identity information of the person is determined by the target server. Therefore, through the matching of the management server and the target server, the blacklist people appearing in the scene can be quickly and effectively identified based on the collected face images of the people.
Further, the target server may communicate with different management servers in multiple scenes, and receive the face models sent by the different management servers, and based on this, in the embodiment of the present invention, it is locally determined whether a person corresponding to the face model is a blacklist person at each management server, and if it is determined that the person is the blacklist person, the face model is sent to the target server to obtain the identity information of the person, so that the calculation pressure of the target server may be effectively reduced, and since the data volume of the face model is much smaller than the data volume of the face graph, the pressure of the network bandwidth may also be reduced. Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above advantages at the same time.
The communication bus mentioned in the management server may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
Corresponding to the person identification method provided by the embodiment of the invention, the embodiment of the invention also provides a computer readable storage medium, and the computer program is executed by a processor to realize the person identification method provided by the embodiment of the invention.
Specifically, the personnel identity identification method is applied to a management server in a video monitoring system; the management server is connected with a pre-designated target server, the management server stores the face model of each blacklist person, and the target server correspondingly stores the face model and the identity information of each blacklist person;
the personnel identity identification method comprises the following steps:
acquiring a face image of a person to be recognized, and determining a face model of the face image as a model to be recognized;
searching a target face model matched with the model to be recognized in the stored face models of all blacklist persons;
when the target face model is found, uploading the target face model to a target server, so that the target server searches the corresponding face model as the target identity information of the target face model in the stored identity information of each blacklist person, and feeds the target identity information back to a management server;
and receiving target identity information fed back by the target server as identity information of the person to be identified.
It should be noted that other implementation manners of the person identification method implemented when the computer program is executed by the processor are the same as the embodiment of the person identification method provided in the foregoing method embodiment section, and are not described again here.
As can be seen from the above, by applying the method provided by the embodiment of the present invention, whether a person corresponding to the face image is a blacklist person or not can be locally determined at the management server based on the collected face image, and when the person is determined to be a blacklist person, the specific identity information of the person is determined by the target server. Therefore, through the matching of the management server and the target server, the blacklist people appearing in the scene can be quickly and effectively identified based on the collected face images of the people.
Further, the target server may communicate with different management servers in multiple scenes, and receive the face models sent by the different management servers, and based on this, in the embodiment of the present invention, it is locally determined whether a person corresponding to the face model is a blacklist person at each management server, and if it is determined that the person is the blacklist person, the face model is sent to the target server to obtain the identity information of the person, so that the calculation pressure of the target server may be effectively reduced, and since the data volume of the face model is much smaller than the data volume of the face graph, the pressure of the network bandwidth may also be reduced. Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above advantages at the same time.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, the system embodiment, the management server embodiment and the computer-readable storage medium embodiment, since they are substantially similar to the method embodiment, the description is relatively simple, and the relevant points can be referred to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims (12)

1. A personnel identity identification method is characterized in that the personnel identity identification method is applied to a management server in a video monitoring system; the management server is connected with a pre-designated target server, the management server stores face models of all blacklist personnel, and the target server correspondingly stores the face models and identity information of all the blacklist personnel;
the method comprises the following steps:
acquiring a face image of a person to be recognized, and determining a face model of the face image as a model to be recognized;
searching a target face model matched with the model to be recognized in the stored face models of the blacklist persons;
when the target face model is found, uploading the target face model to the target server, so that the target server searches the stored identity information of each blacklist person for the target identity information of which the corresponding face model is the target face model, and feeds the target identity information back to the management server;
and receiving the target identity information fed back by the target server as the identity information of the personnel to be identified.
2. The method of claim 1, further comprising:
and when the time is found, outputting early warning prompt information.
3. The method of claim 1, further comprising:
receiving a processing opinion fed back by the target server; the processing opinion is generated and fed back by the target server based on the target identity information after determining the identity type of the person to be identified;
and outputting the target identity information and prompt information corresponding to the processing opinions.
4. The method according to any one of claims 1 to 3, wherein the face model is a feature vector of a face;
the step of searching the target face model matched with the model to be recognized in the stored face models of all blacklist persons comprises the following steps:
calculating the cosine value of the included angle between the model to be recognized and the stored face model of each blacklist person;
and when the calculated cosine value of the maximum included angle is larger than a preset threshold value, determining the face model of the blacklist personnel corresponding to the cosine value of the maximum included angle as a target face model matched with the model to be recognized.
5. A personnel identification device is characterized in that the personnel identification device is applied to a management server in a video monitoring system; the management server is connected with a pre-designated target server, the management server stores face models of all blacklist personnel, and the target server correspondingly stores the face models and identity information of all the blacklist personnel;
the device comprises:
the model acquisition module is used for acquiring a face image of a person to be recognized and determining a face model of the face image as a model to be recognized;
the model searching module is used for searching a target face model matched with the model to be recognized in the stored face models of the blacklist persons;
the model uploading module is used for uploading the target face model to the target server when the target face model is found, so that the target server searches the stored identity information of each blacklist person for the target identity information of which the corresponding face model is the target face model, and feeds the target identity information back to the management server;
and the information receiving module is used for receiving the target identity information fed back by the target server and taking the target identity information as the identity information of the person to be identified.
6. The apparatus of claim 5, further comprising:
and the information output module is used for outputting the early warning prompt information when the information is searched.
7. The apparatus of claim 5, further comprising:
the opinion receiving module is used for receiving the processing opinion fed back by the target server; the processing opinion is generated and fed back by the target server based on the target identity information after determining the identity type of the person to be identified;
and the information output module is used for outputting the target identity information and prompt information corresponding to the processing opinions.
8. The apparatus according to any one of claims 5-7, wherein the face model is a feature vector of a face;
the model lookup module is specifically configured to:
calculating the cosine value of the included angle between the model to be recognized and the stored face model of each blacklist person; and when the calculated cosine value of the maximum included angle is larger than a preset threshold value, determining the face model of the blacklist personnel corresponding to the cosine value of the maximum included angle as a target face model matched with the model to be recognized.
9. A personnel identification system is characterized by comprising a management server and a preassigned target server in a video monitoring system; the management server is connected with the target server, the management server stores face models of all blacklist personnel, and the target server correspondingly stores face models and identity information of all the blacklist personnel;
the management server is configured to: acquiring a face image of a person to be recognized, and determining a face model of the face image as a model to be recognized; searching a target face model matched with the model to be recognized in the stored face models of the blacklist persons; when the target face model is found, uploading the target face model to the target server; receiving the target identity information fed back by the target server as the identity information of the person to be identified;
the target server is configured to: receiving the target face model sent by the management service; and searching the stored identity information of each blacklist person for target identity information of which the corresponding face model is the target face model, and feeding back the target identity information to the management server.
10. The system of claim 9,
the target server is further configured to: after the identity type of the person to be identified is determined based on the target identity information, generating a processing opinion corresponding to the identity type; transmitting the processing opinion to the management server;
the management server is further configured to: receiving the processing opinions fed back by the target server; and outputting the target identity information and prompt information corresponding to the processing opinions.
11. A management server is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing the communication between the processor and the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1 to 4 when executing a program stored in the memory.
12. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 4.
CN201910653548.9A 2019-07-19 2019-07-19 Personnel identity recognition method, device and system Active CN112241671B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910653548.9A CN112241671B (en) 2019-07-19 2019-07-19 Personnel identity recognition method, device and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910653548.9A CN112241671B (en) 2019-07-19 2019-07-19 Personnel identity recognition method, device and system

Publications (2)

Publication Number Publication Date
CN112241671A true CN112241671A (en) 2021-01-19
CN112241671B CN112241671B (en) 2024-05-03

Family

ID=74168334

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910653548.9A Active CN112241671B (en) 2019-07-19 2019-07-19 Personnel identity recognition method, device and system

Country Status (1)

Country Link
CN (1) CN112241671B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112989225A (en) * 2021-03-26 2021-06-18 北京市商汤科技开发有限公司 Data updating method and device, computer equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101404107A (en) * 2008-11-19 2009-04-08 公安部第三研究所 Internet bar monitoring and warning system based on human face recognition technology
CN106022317A (en) * 2016-06-27 2016-10-12 北京小米移动软件有限公司 Face identification method and apparatus
CN106611151A (en) * 2015-10-23 2017-05-03 杭州海康威视数字技术股份有限公司 A human face identification method and apparatus
CN107730672A (en) * 2017-09-26 2018-02-23 四川仪岛科技有限公司 A kind of face identification unit gate control system and control method
CN109800642A (en) * 2018-12-15 2019-05-24 深圳壹账通智能科技有限公司 Personnel identity information acquisition method, device, computer equipment and storage medium
WO2019134245A1 (en) * 2018-01-03 2019-07-11 平安科技（深圳）有限公司 Number arrangement method, server, and storage medium based on human face recognition

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101404107A (en) * 2008-11-19 2009-04-08 公安部第三研究所 Internet bar monitoring and warning system based on human face recognition technology
CN106611151A (en) * 2015-10-23 2017-05-03 杭州海康威视数字技术股份有限公司 A human face identification method and apparatus
CN106022317A (en) * 2016-06-27 2016-10-12 北京小米移动软件有限公司 Face identification method and apparatus
CN107730672A (en) * 2017-09-26 2018-02-23 四川仪岛科技有限公司 A kind of face identification unit gate control system and control method
WO2019134245A1 (en) * 2018-01-03 2019-07-11 平安科技（深圳）有限公司 Number arrangement method, server, and storage medium based on human face recognition
CN109800642A (en) * 2018-12-15 2019-05-24 深圳壹账通智能科技有限公司 Personnel identity information acquisition method, device, computer equipment and storage medium

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112989225A (en) * 2021-03-26 2021-06-18 北京市商汤科技开发有限公司 Data updating method and device, computer equipment and storage medium

Also Published As

Publication number Publication date
CN112241671B (en) 2024-05-03

Similar Documents

Publication Publication Date Title
US11195284B2 (en) Target object tracking method and apparatus, and storage medium
CN108733819B (en) Personnel archive establishing method and device
CN109871815B (en) Method and device for inquiring monitoring information
CN109426785B (en) Human body target identity recognition method and device
CN108563651B (en) Multi-video target searching method, device and equipment
US10489637B2 (en) Method and device for obtaining similar face images and face image information
CN110660078B (en) Object tracking method, device, computer equipment and storage medium
CN111654700B (en) Privacy mask processing method and device, electronic equipment and monitoring system
CN111724496A (en) Attendance checking method, attendance checking device and computer readable storage medium
US20220301317A1 (en) Method and device for constructing object motion trajectory, and computer storage medium
CN111368619A (en) Method, device and equipment for detecting suspicious people
CN109784220B (en) Method and device for determining passerby track
CN112820071A (en) Behavior identification method and device
US20230410221A1 (en) Information processing apparatus, control method, and program
US20200084416A1 (en) Information processing apparatus, control method, and program
CN110505438B (en) Queuing data acquisition method and camera
CN112241671B (en) Personnel identity recognition method, device and system
CN113568934A (en) Data query method and device, electronic equipment and storage medium
CN110795980A (en) Network video-based evasion identification method, equipment, storage medium and device
US11527091B2 (en) Analyzing apparatus, control method, and program
US20220130174A1 (en) Image processing apparatus, control method, and non-transitory storage medium
CN112689120A (en) Monitoring method and device
CN112333182B (en) File processing method, device, server and storage medium
CN115391596A (en) Video archive generation method and device and storage medium
CN111831841B (en) Information retrieval method, device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant