Detection method and device of lost target, computer equipment and medium

Abstract

The invention provides a lost target detection method and device, computer equipment and a medium, and the method comprises the steps: receiving a target lost detection request which comprises lost time information, lost position information and target image information; in response to the target missing detection request, determining the missing interval duration of the missing target based on the missing time information and the current time information; predicting a current position range of the lost target based on the lost interval duration and the lost position information of the lost target; acquiring first figure image data acquired by all camera devices associated with the current position range of the lost target; and matching the first figure image data with the face image data of the lost target to perform face recognition on the lost target. Therefore, the lost target is effectively identified, and the retrieval probability of the lost target is improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the technical field of target detection, and in particular, to a method and device for detecting a lost target, a computer device and a medium. BACKGROUND

[0002] In current urban life, the phenomenon of people being lost or abducted often occurs, and the detection of lost people becomes increasingly important.

[0003] In related technologies, when searching for a lost person, people mainly rely on manpower to directly search for the lost person, or use media such as a friend circle or social media to search for the lost person. However, this method requires a large number of people to search for the lost person, and the search process is extremely complex due to the random time of the lost person, which leads to a low probability of finding the lost person. SUMMARY

[0004] Embodiments described herein provide a method and device for detecting a lost target, a computer device and a medium, which overcome the above problems.

[0005] In a first aspect, according to the content of the present disclosure, a method for detecting a lost target is provided, comprising:

[0006] receiving a target lost detection request, wherein the target lost detection request comprises lost time information, lost location information and target image information, and the target image information is used to describe face image data of a lost target;

[0007] in response to the target lost detection request, determining a lost interval length of the lost target based on the lost time information and current time information;

[0008] based on the lost interval length of the lost target and the lost location information, predicting a current location range of the lost target;

[0009] obtaining first person image data collected by all camera devices associated with the current location range of the lost target;

[0010] matching the first person image data with the face image data of the lost target to perform face recognition on the lost target.

[0011] Optionally, the step of predicting the current location range of the lost target based on the lost interval length of the lost target and the lost location information comprises:

[0012] based on the lost interval length of the lost target and a preset walking speed, predicting a walking route length of the lost target;

[0013] A circular enclosure is constructed with the lost position information as the center and the length of the walking route of the lost target as the radius;

[0014] The current position range of the lost target is determined based on the circular enclosure.

[0015] Optionally, the first person image data collected by all the camera devices associated with the current position range of the lost target comprises:

[0016] The entity image data collected by all the camera devices associated with the current position range of the lost target is acquired.

[0017] The entity image data is subjected to portrait recognition to obtain the first person image data.

[0018] Optionally, the first person image data comprises a plurality of candidate face data.

[0019] The first person image data is matched with the face image data of the lost target to perform face recognition on the lost target, comprising:

[0020] Each of the candidate face data is matched with the face image data of the lost target.

[0021] If it is determined that there is target face data in the first person image data that has a matching degree higher than a preset threshold with the face image data of the lost target, the lost target is determined based on the target face data that has a matching degree higher than the preset threshold with the face image data of the lost target.

[0022] Optionally, the method further comprises:

[0023] If it is not determined that there is target face data in the first person image data that has a matching degree higher than a preset threshold with the face image data of the lost target, the current position range of the lost target is expanded.

[0024] Second person image data collected by all the camera devices associated with the current position range of the lost target is acquired.

[0025] The second person image data is matched with the face image data of the lost target to perform face recognition on the lost target again.

[0026] Optionally, the method further comprises:

[0027] It is detected whether there is abnormal image data in the first person image data and / or the second person image data.

[0028] If it is determined that there is abnormal image data in the first person image data and / or the second person image data, historical behavior data corresponding to the abnormal image data is acquired;

[0029] Based on the historical behavior data corresponding to the abnormal image data, an abnormal early warning prompt is generated.

[0030] Optionally, the method further comprises:

[0031] The type of the abnormal early warning prompt is acquired;

[0032] If the type of the abnormal early warning prompt is a preset type, an abnormal person supervision message is sent to a corresponding supervision device.

[0033] In a second aspect, according to the content of the disclosure, a missing target detection device is provided, comprising:

[0034] A receiving module is configured to receive a missing target detection request, wherein the missing target detection request comprises missing time information, missing location information, and target image information, and the target image information is used to describe face image data of a missing target;

[0035] A determining module is configured to determine a missing interval length of the missing target based on the missing time information and current time information in response to the missing target detection request;

[0036] A predicting module is configured to predict a current position range of the missing target based on the missing interval length of the missing target and the missing location information;

[0037] An acquiring module is configured to acquire first person image data collected by all camera devices associated with the current position range of the missing target;

[0038] A matching module is configured to match the first person image data with the face image data of the missing target to perform face recognition on the missing target.

[0039] In a third aspect, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the missing target detection method in any one of the above embodiments when executing the computer program.

[0040] In a fourth aspect, a computer readable storage medium is provided, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the missing target detection method in any one of the above embodiments.

[0041] The method for detecting a lost target provided by the embodiment of the application receives a target loss detection request, the target loss detection request comprising: loss time information, loss position information and target image information, the target image information being used to describe face image data of the lost target; in response to the target loss detection request, loss interval duration of the lost target is determined based on the loss time information and current time information; current position range of the lost target is predicted based on the loss interval duration of the lost target and the loss position information; first person image data collected by all camera devices associated with the current position range of the lost target is acquired; and the first person image data is matched with the face image data of the lost target to perform face recognition on the lost target. In this way, the current position range of the lost target is predicted by combining the loss interval duration of the lost target and the loss position information, and the image data of the lost target is matched with the image data collected by the camera devices in the range, so that the lost target can be effectively identified and the recovery probability of the lost target is improved.

[0042] The above description is only a summary of the technical solutions of the embodiments of the application. In order to more clearly understand the technical means of the embodiments of the application, the embodiments of the application can be implemented according to the content of the description, and in order to make the above and other purposes, characteristics and advantages of the embodiments of the application more obvious and easy to understand, the following specific embodiments of the application are described. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments will be briefly described below. It should be noted that the drawings described below only relate to some embodiments of the present disclosure, but not limit the present disclosure, wherein:

[0044] Figure 1 is a flow diagram of a method for detecting a lost target provided by the present disclosure.

[0045] Figure 2 is a structural diagram of a detection device for a lost target provided by the present disclosure.

[0046] Figure 3 is a structural diagram of a computer device provided by the present disclosure.

[0047] It should be noted that the elements in the drawings are schematic and not drawn to scale. DETAILED DESCRIPTION

[0048] In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions of the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of protection of the present disclosure.

[0049] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this present subject matter belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the specification and relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein. As used herein, the statement that two or more parts are "connected" or "coupled" together refer to an indirect or direct connection or coupling.

[0050] Reference herein 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 an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. A person of ordinary skill in the art will readily recognize from the disclosure herein, given the total volume of this application that one or more passages that are described as an embodiment is / are also an embodiment of another embodiment.

[0051] The term "and / or", merely used as a description of associated objects, means that there can be three kinds of relations, for example, A and / or B, which can represent: there is A, there are A and B, and there is B. In addition, the character " / " in this paper generally represents that the front and rear associated objects are a "or" relationship. Terms such as "first" and "second" are only used to distinguish one component (or part of a component) from another component (or another part of a component).

[0052] In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more (including two), and similarly, "a plurality of groups" means two or more groups (including two groups).

[0053] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings.

[0054] Figure 1 is a flowchart of a detection method of a lost target provided by an embodiment of the present disclosure, as shown in Figure 1 The specific process of the detection method of the lost target includes:

[0055] S110, receive a target missing detection request, the target missing detection request comprising missing time information, missing location information and target image information.

[0056] The target image information is used to describe the face image data of the missing target, such as a front face photo or a side face photo. The missing time information can be used to describe a time point or a time period when the missing person is found to be lost. The missing location information can be used to describe a location point or a location range where the missing person is found to be lost.

[0057] It should be noted that the application scenario of the embodiment can be a public security department or a criminal investigation department, and the target missing detection request can be a missing person detection request initiated by a department system through on-site or telephone contact with the relevant department by a reporting person.

[0058] S120, in response to the target missing detection request, determining a missing interval duration of the missing target based on the missing time information and current time information.

[0059] The missing time information can include a missing time point or a missing time period. The current time information is used to describe a specific current time point.

[0060] When the missing time information is a missing time point, determining the missing interval duration of the missing target based on the missing time information and the current time information can include determining the time interval between the current time point and the missing time point as the missing interval duration, or when the missing time point is not very certain (i.e., the reporting person is not sure whether the missing person is found to be lost at the time point), a preset duration can be added to the determined missing interval duration to update the missing interval duration, so as to reduce the confirmation error of the missing interval duration.

[0061] When the missing time information is a missing time period, determining the missing interval duration of the missing target based on the missing time information and the current time information can include determining the time interval between the current time point and the earliest time point in the missing time period as the missing interval duration.

[0062] S130, predicting a current location range of the missing target based on the missing interval duration of the missing target and the missing location information.

[0063] The current location range of the missing target is a rough location range reached by the missing target after walking for the missing interval duration from the missing location point / missing location range.

[0064] In some embodiments, predicting the current location range of the missing target based on the missing interval duration of the missing target and the missing location information includes:

[0065] The walking route length of the lost target is predicted based on the lost interval length of the lost target and the preset walking speed. A circular enclosure is constructed with the lost position information as the center and the walking route length of the lost target as the radius. The current position range of the lost target is determined based on the circular enclosure.

[0066] The walking route length of the lost target can be determined based on the product of the lost interval length of the lost target and the preset walking speed. The preset walking speed can be the walking speed of normal personnel or the moving speed of common vehicles (such as electric vehicles).

[0067] The current position range can be a circular range constructed by the circular enclosure, or an irregular enclosing range constructed according to the area occupied by the circular enclosure. For example, the area occupied by the circular enclosure (i.e., in an area) includes area A, area B, and area C. The area composed of area A, area B, and area C can be used as a current position range.

[0068] Thus, the circular enclosure is constructed with the lost position information as the center and the walking route length of the lost target as the radius, effectively predicting the location of the walking track of the lost personnel.

[0069] S140, acquiring first person image data collected by all camera devices associated with the current position range of the lost target.

[0070] The first person image data can be used to describe the face data of different environments collected by different camera devices.

[0071] In some embodiments, acquiring the first person image data collected by all camera devices associated with the current position range of the lost target includes:

[0072] Acquiring entity image data collected by all camera devices associated with the current position range of the lost target; performing portrait recognition on the entity image data to obtain the first person image data.

[0073] After acquiring the entity image data collected by all camera devices associated with the current position range of the lost target, the first person image data can be effectively obtained by performing portrait recognition on the entity image data, for example, by recognizing the face region and intercepting the face region.

[0074] S150, matching the first person image data with the face image data of the lost target.

[0075] By matching the first person image data with the face image data of the lost target, the face recognition of the lost target is performed.

[0076] In some embodiments, the first person image data comprises a plurality of candidate face data.

[0077] The matching of the first person image data and the face image data of the lost target comprises:

[0078] Each candidate face data is matched with the face image data of the lost target respectively, and if it is determined that there is target face data in the first person image data that matches the face image data of the lost target with a degree higher than a preset threshold, the lost target is determined based on the target face data that matches the face image data of the lost target with a degree higher than the preset threshold.

[0079] For example, the preset threshold is 90%, and the first person image data comprises candidate face data 1, candidate face data 2, candidate face data 3, candidate face data 4 and candidate face data 5, wherein only the candidate face data 2 matches the face image data of the lost target with a degree of 95%, and the candidate face data 2 is determined as the target face data.

[0080] The determination of the lost target based on the target face data that matches the face image data of the lost target with a degree higher than the preset threshold can comprise: matching the lost target from an identity database based on the target face data that matches the face image data of the lost target with a degree higher than the preset threshold, the identity database storing a mapping relationship between face data and corresponding identity information.

[0081] Thus, the face data collected by the camera device is matched with the face image data of the lost target, and the identity information of the lost target is effectively identified.

[0082] In addition, after the lost target is determined, a first warning prompt can be generated, and the first warning prompt can be used to describe that the lost target has been found, so as to facilitate subsequent work of relevant personnel.

[0083] In some embodiments, the method further comprises:

[0084] If it is not determined that there is target face data in the first person image data that matches the face image data of the lost target with a degree higher than the preset threshold, the current location range of the lost target is expanded, second person image data collected by all camera devices associated with the current location range of the lost target is obtained, and the second person image data is matched with the face image data of the lost target to perform face recognition on the lost target again.

[0085] The expansion of the current location range of the lost target can be, for example, a circular enclosure is reconstructed with the lost location information as the center and 2 times the length of the walking route of the lost target as the radius, so as to expand the current location range.

[0086] In the matching of the second person image data and the face image data of the lost target, each candidate face data included in the second person image data is matched with the face image data of the lost target respectively, and if it is determined that there is target face data in the second person image data that matches the face image data of the lost target with a degree higher than a preset threshold, the lost target is determined based on the target face data that matches the face image data of the lost target with a degree higher than the preset threshold.

[0087] Therefore, when it is determined that there is no target face data in the first person image data that matches the face image data of the lost target with a degree higher than a preset threshold, the search range of the lost person is expanded in the manner of expanding the current position range of the lost target, so as to further improve the recovery probability of the lost person.

[0088] If it is determined that there is no target face data in the second person image data that matches the face image data of the lost target with a degree higher than a preset threshold, a second early warning prompt is generated, and the second early warning prompt is used to indicate that the trace of the lost person cannot be found.

[0089] In the embodiment, a target loss detection request is received, the target loss detection request includes: lost time information, lost position information and target image information, the target image information is used to describe the face image data of the lost target; in response to the target loss detection request, the lost interval length of the lost target is determined based on the lost time information and the current time information; the current position range of the lost target is predicted based on the lost interval length of the lost target and the lost position information; the first person image data collected by all camera devices associated with the current position range of the lost target is acquired; and the first person image data is matched with the face image data of the lost target to perform face recognition on the lost target. In this way, the current position range of the lost target is predicted by the lost interval length of the lost target combined with the lost position information, and the image data of the lost target is matched by the image data collected by the camera devices in this range, so as to effectively identify the lost target and improve the recovery probability of the lost target.

[0090] In some embodiments, the method further includes:

[0091] It is detected whether there is abnormal image data in the first person image data and / or the second person image data; if it is determined that there is abnormal image data in the first person image data and / or the second person image data, historical behavior data corresponding to the abnormal image data is acquired; and an abnormal early warning prompt is generated based on the historical behavior data corresponding to the abnormal image data.

[0092] The abnormal image data is used to describe the person image data with abnormal behavior. For example, a person continuously checks the camera equipment for many times in a short time (e.g., half an hour), and the person image data corresponding to the person is the abnormal image data.

[0093] The historical behavior data corresponding to the abnormal image data can be the historical behavior data of the person in the abnormal image data, such as a criminal record or an arrest state. According to the severity of the historical behavior data corresponding to the abnormal image data, an abnormal warning prompt with different warning levels can be generated.

[0094] For example, if the historical behavior data corresponding to the abnormal image data is a criminal record, it is considered to be mild, and an abnormal warning prompt with a first warning level can be generated. If the historical behavior data corresponding to the abnormal image data is an arrest state, it is considered to be severe, and an abnormal warning prompt with a second warning level can be generated. The warning level of the second warning level is higher than that of the first warning level.

[0095] Thus, by monitoring the abnormal image data in the range in real time through the camera equipment, suspicious persons with abnormal behavior can be identified, and corresponding abnormal warning prompts can be generated, so that relevant persons can handle the prompts in time.

[0096] In some embodiments, the method further includes:

[0097] The type of the abnormal warning prompt is obtained, and if the type of the abnormal warning prompt is a preset type, an abnormal person supervision message is sent to a corresponding supervision device.

[0098] The type of the abnormal warning prompt can be to be handled or not to be handled, and the preset type can be to be handled. To be handled can be used to describe that the prompt event is relatively serious, and not to be handled can be used to describe that the prompt event is not serious.

[0099] Thus, when it is determined that the prompt event is relatively serious based on the type of the abnormal warning prompt, the abnormal person supervision message can be sent to the corresponding supervision device, so that the prompt event can be handled in time.

[0100] In summary, the embodiment can mark the missing point and time of the missing person on the map and upload a recent front photo through the description of the reporting personnel. The system will automatically enlarge the search range according to the strategy. The system automatically generates a face comparison task, calls an algorithm platform, issues an algorithm to an edge box (the edge box is linked with a camera, which can be linked with 1-10 paths), and starts the face comparison service. According to the time dimension, the circle area is expanded, and the cameras corresponding to the algorithm boxes in the circle coverage area are issued (the Tianwang camera can be used). When the matching degree is greater than or equal to 90%, an alarm is generated, and at the same time, a circle area is expanded according to the time dimension with the alarm point as the center. The identification task of the previous circle is stopped by the system. The missing person only needs to face the camera, which is convenient and can also prevent criminals from being aware. Within half an hour, the missing person can be configured to include personnel who face the camera twice or more in the suspicious personnel alarm list. The busy people usually do not look at the camera and do not look at it multiple times. The suspicious personnel can automatically query the public security personnel database to retrieve the archives, and the system can view the identity information and archives of the identified personnel. The alarm level weight of the suspicious personnel list and the previous criminal record is +1. The alarm level weight of the suspicious personnel behavior in the historical video analysis is +1. The higher the weight, the higher the risk, and the system will pop up a window to remind the list to the front, and the case handling personnel can prioritize viewing and decision-making.

[0101] In addition, the embodiment also provides a missing target detection system, a population tracking business system, an algorithm platform and an edge box. The population tracking business system is responsible for collecting the information of the tracked person, the missing point, the face feature photo, the manual drawing area electronic fence, etc. Through automatic and manual creation of face recognition tasks, the algorithm platform is called to issue edge box algorithms and start the task. The edge box reports alarm information, map presentation and list presentation, etc. The algorithm platform can upload face recognition algorithms, personnel behavior recognition algorithms, etc. The exposed interface can realize the encapsulation and task issuance of the algorithm. The edge box is linked with 1-10 cameras, can receive algorithms and tasks issued by the algorithm platform, and can run the algorithm task to analyze the face matching degree, historical video analysis behavior and other algorithm running.

[0102] Among them, the historical video analysis behavior is a process of manual or intelligent intervention. For example, if a face alarm occurs at this point, the direction of the suspect's walking can be predicted (east-west or north-south, etc.) through analysis of historical videos. Then, the tracking circle can draw a semicircle in the direction in front of the alarm point, and the task is issued in this semicircle, which optimizes the task issuance.

[0103] Corresponding to a specific application scenario, the system marks the missing point coordinates and time of the missing person on the map through the description of the reporter, and uploads a recent front photo. The system will automatically enlarge the search range according to the time strategy. For example, within 12 hours of the missing person, the radius circle increases by 2 kilometers per half hour; within 12-24 hours, the radius circle increases by 5 kilometers per half hour; within 24-48 hours, the radius circle increases by 20 kilometers per half hour; and more than 48 hours, the radius circle increases by 50 kilometers per half hour; the camera edge box within the task issuing circle range. The system automatically generates a face comparison task, calls the algorithm platform to issue an algorithm to the edge box (the edge box is linked with the camera, which can be linked with 1-10), and starts the face comparison task.

[0104] Figure 2 A structure diagram of a missing target detection device is provided for the embodiment. The missing target detection device can include a receiving module 210, a determining module 220, a prediction module 230, an acquisition module 240, and a matching module 250.

[0105] The receiving module 210 is configured to receive a target missing detection request, wherein the target missing detection request includes missing time information, missing location information, and target image information, and the target image information is used to describe the face image data of the missing target.

[0106] The determining module 220 is configured to determine the missing interval duration of the missing target based on the missing time information and the current time information in response to the target missing detection request.

[0107] The prediction module 230 is configured to predict the current position range of the missing target based on the missing interval duration of the missing target and the missing location information.

[0108] The acquisition module 240 is configured to acquire first person image data collected by all camera devices associated with the current position range of the missing target.

[0109] The matching module 250 is configured to match the first person image data with the face image data of the missing target to perform face recognition on the missing target.

[0110] In the embodiment, the prediction module 230 is specifically configured to:

[0111] predict the walking route length of the missing target based on the missing interval duration of the missing target and a preset walking speed, construct a circular enclosure with the missing location information as the center and the walking route length of the missing target as the radius, and determine the current position range of the missing target based on the circular enclosure.

[0112] In the embodiment, the acquisition module 240 is specifically configured to:

[0113] acquire entity image data collected by all camera devices associated with the current location range of the lost target; and perform portrait recognition on the entity image data to obtain first person image data.

[0114] In this embodiment, the first person image data includes a plurality of candidate face data.

[0115] The matching module 250 is specifically configured to:

[0116] match each candidate face data with the face image data of the lost target respectively; and if it is determined that there is target face data in the first person image data that has a matching degree higher than a preset threshold with the face image data of the lost target, determine the lost target based on the target face data that has a matching degree higher than the preset threshold with the face image data of the lost target.

[0117] In this embodiment, the matching module 250 is specifically configured to:

[0118] If it is not determined that there is target face data in the first person image data that has a matching degree higher than a preset threshold with the face image data of the lost target, expand the current location range of the lost target; acquire second person image data collected by all camera devices associated with the current location range of the lost target; and match the second person image data with the face image data of the lost target to perform face recognition on the lost target again.

[0119] In this embodiment, the method further includes a detection module and a generation module.

[0120] The detection module is configured to detect whether there is abnormal image data in the first person image data and / or the second person image data.

[0121] The acquisition module 240 is further configured to acquire historical behavior data corresponding to the abnormal image data if it is determined that there is abnormal image data in the first person image data and / or the second person image data.

[0122] The generation module is configured to generate an abnormal warning prompt based on the historical behavior data corresponding to the abnormal image data.

[0123] In this embodiment, the method further includes a sending module.

[0124] The acquisition module 240 is further configured to acquire a prompt type of the abnormal warning prompt.

[0125] The sending module is configured to send an abnormal person supervision message to a corresponding supervision device if the prompt type of the abnormal warning prompt is a preset type.

[0126] The lost target detection device provided by the present disclosure can execute the method embodiments, and the specific implementation principles and technical effects can be referred to the method embodiments, which will not be described here again.

[0127] The present application also provides a computer device. For details, please refer to Figure 3 , Figure 3 The basic structure block diagram of the computer device is shown in the figure.

[0128] The computer device includes a memory 310 and a processor 320 which are connected to each other through a system bus. It should be noted that only the computer device with the memory 310 and the processor 320 is shown in the figure, but it should be understood that all the components shown are not required to be implemented, and more or less components can be alternatively implemented. Among them, the computer device herein is a device capable of automatically performing numerical calculation and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0129] The computer device can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing devices. The computer device can interact with the user through a keyboard, a mouse, a remote controller, a touchpad or a voice control device.

[0130] The memory 310 includes at least one type of readable storage medium, including non-volatile memory or volatile memory, for example, flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. The RAM can include static RAM or dynamic RAM. In some embodiments, the memory 310 can be an internal storage unit of the computer device, for example, a hard disk or a memory of the computer device. In other embodiments, the memory 310 can also be an external storage device of the computer device, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, or a flash card, etc. equipped on the computer device. Of course, the memory 310 can include both an internal storage unit and an external storage device of the computer device. In the present embodiment, the memory 310 is generally used to store an operating system and various application software installed on the computer device, for example, program codes of the above-described method, etc. In addition, the memory 310 can also be used to temporarily store various data that has been output or will be output.

[0131] The processor 320 is generally used to perform the overall operation of the computer device. In the present embodiment, the memory 310 is used to store program codes or instructions, which include computer operation instructions, and the processor 320 is used to execute the program codes or instructions stored in the memory 310 or process data, for example, run the program codes of the above-described method.

[0132] In this document, the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus system can be a system of address, data, control, and the like. For ease of representation, only one thick line is shown in the figure, but it does not mean that there is only one bus or only one type of bus.

[0133] Another embodiment of the present application also provides a computer readable medium, which can be a computer readable signal medium or a computer readable medium. The processor in the computer reads the computer readable program code stored in the computer readable medium, so that the processor can perform the function actions specified in each step or combination of steps in the above method; and generates a device that implements the function actions specified in each block or combination of blocks in the block diagram.

[0134] The computer readable medium includes, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any appropriate combination of the foregoing, for storing program codes or instructions, and the program codes include computer operation instructions. The processor is used to execute the program codes or instructions of the above method stored in the memory.

[0135] The definition of the memory and the processor can refer to the description of the foregoing computer device embodiment, which will not be repeated here.

[0136] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiment described above is only schematic, for example, the division of the module or unit is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, indirect coupling or communication connection between the units or devices, which can be electrical, mechanical or other forms.

[0137] The function units or modules in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software function unit.

[0138] If the integrated unit is implemented in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0139] In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of both hardware and software, and any combination thereof. In the device claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The mere fact that certain measures are recited in mutually different claims does not indicate that a combination of these measures cannot be used to advantage. The use of relative terms such as "first", "second" and "third", etc. does not connote any prioritization, but such terms are used to distinguish a certain feature from another feature with the same name. The steps of the above-described methods shall not be understood as necessarily limited to the order in which they are presented.

[0140] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; even though the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting a lost target, characterized in that, include: Receive a target missing detection request, the target missing detection request including: missing time information, missing location information and target image information, the target image information being used to describe the face image data of the missing target; In response to the target missing detection request, the missing interval of the missing target is determined based on the missing time information and the current time information; Based on the missing target's missing interval and missing location information, predict the current location range of the missing target; Obtain first person image data collected by all camera devices associated with the current location range of the missing target; The first person image data is matched with the face image data of the missing target to perform face recognition on the missing target.

2. The method according to claim 1, characterized in that, The step of predicting the current location range of the lost target based on the missing target's missing interval and missing location information includes: Based on the missing target's missing interval and preset walking speed, predict the length of the missing target's walking route; A circular enclosing circle is constructed with the missing location information as the center and the walking route length of the missing target as the radius; The current location range of the lost target is determined based on the circular enclosing circle.

3. The method according to claim 1, characterized in that, The acquisition of first person image data collected by all camera devices associated with the current location range of the missing target includes: Obtain entity image data from all camera devices associated with the current location range of the lost target; Human image data is obtained by performing facial recognition on the entity image data.

4. The method according to claim 3, characterized in that, The first person image data includes: multiple candidate face data; The step of matching the first person image data with the missing target's facial image data to perform facial recognition on the missing target includes: Each candidate face data is matched with the face image data of the missing target; If it is determined that there is a target face data in the first person image data that matches the face image data of the missing target with a degree higher than a preset threshold, then the missing target is determined based on the target face data that matches the face image data of the missing target with a degree higher than the preset threshold.

5. The method according to claim 4, characterized in that, Also includes: If no target face data with a matching degree higher than a preset threshold is found in the first person image data, the current location range of the missing target is expanded. Obtain second-person image data from all camera devices associated with the current location range of the missing target; The second person image data is matched with the face image data of the missing target to perform face recognition on the missing target again.

6. The method according to claim 5, characterized in that, Also includes: Detect whether there is abnormal image data in the first person image data and / or the second person image data; If it is determined that there is abnormal image data in the first person image data and / or the second person image data, then the historical behavior data corresponding to the abnormal image data is obtained. An anomaly warning is generated based on the historical behavior data corresponding to the abnormal image data.

7. The method according to claim 6, characterized in that, Also includes: Obtain the alert type of the abnormality warning; If the abnormal warning prompt type is a preset type, then an abnormal personnel monitoring message is sent to the corresponding monitoring device.

8. A device for detecting a lost target, characterized in that, include: The receiving module is used to receive a target missing detection request, which includes: missing time information, missing location information and target image information, wherein the target image information is used to describe the face image data of the missing target; The determination module is used to determine the missing interval duration of the missing target based on the missing time information and the current time information in response to the target missing detection request; The prediction module is used to predict the current location range of the lost target based on the missing interval duration and the missing location information; The acquisition module is used to acquire first person image data collected by all camera devices associated with the current location range of the missing target; The matching module is used to match the first person image data with the face image data of the missing target in order to perform face recognition on the missing target.

9. A computer device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method for detecting a lost target as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method for detecting a lost target as described in any one of claims 1 to 7.

Images