CN117253292A

CN117253292A - Public place thief detection method, system, electronic equipment and storage medium

Info

Publication number: CN117253292A
Application number: CN202311388924.9A
Authority: CN
Inventors: 吴家湖; 柏林; 刘彪; 舒海燕; 袁添厦; 祝涛剑; 沈创芸; 王恒华; 方映峰
Original assignee: Guangzhou Gosuncn Robot Co Ltd
Current assignee: Guangzhou Gosuncn Robot Co Ltd
Priority date: 2023-10-24
Filing date: 2023-10-24
Publication date: 2023-12-19

Abstract

The invention discloses a method, a system, electronic equipment and a storage medium for detecting a thief in a public place, wherein the method for detecting the thief in the public place comprises the following steps: detecting a human body through a human body key point detection model, and calculating a human body frame through human body key points; calculating the intersection ratio between human frames, and cutting out the picture of the part between the thighs and the neck through the position information of the key points of the human hands; and inputting the cut pictures of the positions between the thighs and the neck into a Cls-UNet model to obtain a segmentation result and a classification result, and judging that the theft occurs under the condition that the segmentation result and the classification result meet preset conditions and the front-back frame relationship meets the preset conditions. The detection method provided by the invention adopts semantic segmentation UNet network Cls-Unet with a classification function and the like to carry out image analysis, and carries out image segmentation and classification on the cut pictures, so that the detection of theft is realized, the application range is wide, the detection method can be suitable for a large-space environment, and the shooting is clear and the cost is low.

Description

Public place thief detection method, system, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of robot detection, in particular to a method, a system, electronic equipment and a storage medium for detecting a thief in a public place.

Background

At present, in public places such as a train station waiting hall, a bus station, a bus, a shopping mall, a vegetable market, a square and the like, thieves are prevented from occurring mainly through a small-sized robot with a sensor and a convex mirror arranged in the bus, or a large number of cameras are arranged for monitoring or used for follow-up evidence collection, and detection of the thieves is achieved.

However, the above-described method of the prior art has a limited range of application of the small robot, and is suitable for use as a toy. The detection method for installing a large number of convex mirrors is not applicable to environments with large space, and the whole detection method is not in accordance with the actual use requirements. The monitoring picture of the camera is generally far away from the crowd, the shooting is unclear in many cases, the camera is basically fixed, and the installation quantity is large, so that the cost is high.

Disclosure of Invention

The invention aims to provide a novel technical scheme of a public place thief detection method, a public place thief detection system, electronic equipment and a storage medium, which at least can solve the problems that the application range is limited, the method cannot be applied to a large-space environment, shooting is unclear, the cost is high and the like in the prior art.

In a first aspect of the present invention, there is provided a method for detecting a thief in a public place, comprising:

detecting a human body through a human body key point detection model, and calculating a human body frame through the human body key points;

calculating the intersection ratio between the human frames, and cutting out the pictures of the positions between the thighs and the neck through the position information of the key points of the human hands;

inputting the cut pictures of the positions between the thighs and the necks into a Cls-UNet model to obtain a segmentation result and a classification result, and judging that the theft occurs under the condition that the segmentation result and the classification result meet preset conditions and the front-back frame relationship meets the preset conditions.

Optionally, the public place thief detection method further includes:

cutting out corresponding pictures of the head, the upper body and the lower body according to the position information of the key points of the human body;

judging whether to wear the hat or not through a classification model, and analyzing the colors of clothes and trousers through an HSV color space;

and sending out alarm sound to remind the stolen person according to the judging result of the classification model and the analysis result of the HSV color space.

Optionally, the public place thief detection method further includes: video when theft occurs is stored as evidence for evidence.

Optionally, the step of calculating the intersection ratio between the human frames includes:

storing a current frame, a previous N frame of the current frame, and a video frame of a next N frame of the current frame;

and after the N frames pass through the N frames, calculating the cross ratio of the N frames.

Optionally, a formula for calculating the intersection ratio between the human frames is:

wherein IoU represents the cross ratio, A, B represents the two human frames respectively;

the relation of the preset conditions met by the relation of the front frame and the rear frame is as follows:

wherein, when IoU of the previous N frame _t’ Equal to 0, ioU of the current frame _t IoU of the last N frame greater than 0 _t” When the value is equal to 0, the theft is judged to occur.

Optionally, the segmentation class of the Cls-UNet model includes: the hand, backpack, single shoulder bag, mobile phone and wallet, the classified number of classification is 2, wherein 0 indicates that the article is not stolen, 1 indicates that the article is stolen.

Optionally, the judging logic of the Cls-UNet model is configured to divide the Cls-UNet model into one of a backpack, a single-shoulder bag, a mobile phone and a wallet, and judges that the theft occurs when the classified class channel output of the Cls-UNet model is 1.

In a second aspect of the present invention, there is provided a public place thief detection system applied to the public place thief detection method described in the above embodiment, the detection system including:

the detection module detects a person through a human body key point detection model;

the first calculation module calculates a human body frame through the human body key points;

the second calculation module is used for calculating the cross-over ratio between the human frames;

the cutting module cuts out a picture of the part between the thighs and the neck through the position information of the key points of the hands of the human body;

the logic analysis module is used for inputting the cut pictures of the part between the thighs and the neck into the Cls-UNet model to obtain a segmentation result and a classification result, and judging that the theft occurs under the condition that the segmentation result and the classification result meet preset conditions and the relation between the front frame and the rear frame meets the preset conditions.

In a third aspect of the present invention, there is provided an electronic apparatus comprising: a processor and a memory in which computer program instructions are stored, wherein the computer program instructions, when executed by the processor, cause the processor to perform the steps of the public place thief detection method described in the above embodiments.

In a fourth aspect of the present invention, there is provided a computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the public place thief detection method described in the above embodiments.

According to the detection method for the thieves in the public places, the patrol robot is used for detecting key points of human bodies, the patrol robot can go deep into people, and a clearer image can be shot compared with a fixed camera. And the patrol robot can automatically move, so that the cost of the camera is saved. The intersection ratio between the human body frame and the human body frame is calculated through the human body key points, image analysis is carried out by adopting semantic segmentation UNet networks Cls-Unet and the like with a classification function, and image segmentation and classification are carried out on the cut pictures, so that theft detection is realized. The detection method for the thieves in the public places has the advantages of wide application range, suitability for large-space environments, clear shooting, low cost and suitability for large-area popularization and use.

Other features of the present invention and its advantages will become apparent from the following detailed description of exemplary embodiments of the invention, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.

FIG. 1 is a block flow diagram of a method for detecting a thief in a public place according to an embodiment of the present invention;

FIG. 2 is another flow diagram of a method of public place thieves detection according to an embodiment of the present invention;

fig. 3 is a schematic diagram of the operation of an electronic device according to an embodiment of the invention.

Reference numerals:

a processor 201;

a memory 202; an operating system 2021; an application 2022;

a network interface 203;

an input device 204;

a hard disk 205;

a display device 206.

Detailed Description

Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless it is specifically stated otherwise.

The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the invention, its application, or uses.

Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.

In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of exemplary embodiments may have different values.

It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.

In the description and claims of the present invention, the terms "first," "second," and the like, if any, may include one or more of those features, either explicitly or implicitly. In the description of the present invention, unless otherwise indicated, the meaning of "a plurality" is two or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.

In the description of the present invention, it should be understood that, if the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. are referred to, the positional relationship indicated based on the drawings is merely for convenience of description and simplification of the description, and does not indicate or imply that the apparatus or element referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the invention.

In the description of the present invention, it should be noted that the terms "mounted," "connected," and "connected" are to be construed broadly, unless otherwise specifically defined and limited. For example, the connection can be fixed connection, detachable connection or integrated connection; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.

The method for detecting the thieves in the public place according to the embodiment of the invention is specifically described below with reference to the accompanying drawings.

The detection method for the thieves in the public places according to the embodiment of the invention comprises the following steps:

s1, detecting a person through a human body key point detection model, and calculating a human body frame through human body key points;

s2, calculating the intersection ratio between human frames, and cutting out the picture of the position between the thighs and the neck through the position information of the key points of the human hands;

s3, inputting the cut pictures of the positions between the thighs and the neck, inputting a Cls-UNet model, obtaining a segmentation result and a classification result, and judging that the theft occurs under the condition that the segmentation result and the classification result meet preset conditions and the front-back frame relationship meets the preset conditions.

In other words, the detection method for the thieves in the public places can realize the function of shooting the thieves in the public places by utilizing technologies such as an image analysis and the like through the patrol robot. In the detection method of the thieves in public places, firstly, a patrol robot can be utilized to detect people through a human body key point detection model, and a human body frame is calculated through the human body key points. Human body key points are detected by the patrol robot, the patrol robot can go deep into the crowd, and a clearer image can be shot compared with a fixed camera. And the patrol robot can automatically move, so that the cost of the camera is saved.

Then, according to the calculated human body frames, the intersection ratio between the human body frames is calculated, and the picture of the position between the thighs and the neck is cut out according to the position information of the key points of the human body hands. The overlap ratio (IOU Intersection over Union) is mainly used to describe the overlapping degree of two frames, and the larger the overlapping area is, the larger the value of the IOU is.

Finally, the cut pictures of the positions between the thighs and the necks can be input into a Cls-UNet model, and image analysis is performed by adopting semantic segmentation UNet networks Cls-UNet with a classification function and the like, so that a segmentation result and a classification result are obtained. And under the condition that the segmentation result and the classification result meet the preset conditions and the relation between the front frame and the rear frame meets the preset conditions, the theft is judged to occur. The detection method for the thieves in the public places has the advantages of wide application range, suitability for large-space environments, clear shooting, low cost and suitability for large-area popularization and use.

Therefore, according to the detection method for the thieves in the public places, the patrol robot is used for detecting key points of human bodies, the patrol robot can go deep into the crowd, and a clearer image can be shot compared with a fixed camera. And the patrol robot can automatically move, so that the cost of the camera is saved. The intersection ratio between the human body frame and the human body frame is calculated through the human body key points, image analysis is carried out by adopting semantic segmentation UNet networks Cls-Unet and the like with a classification function, and image segmentation and classification are carried out on the cut pictures, so that theft detection is realized. The detection method for the thieves in the public places has the advantages of wide application range, suitability for large-space environments, clear shooting, low cost and suitability for large-area popularization and use.

In some embodiments of the present invention, the public place thief detection method further comprises:

Video when theft occurs is stored as evidence for evidence.

That is, in the public thief detection method, the corresponding pictures of the head, the upper body and the lower body can be cut out through the position information of the key points of the human body. And judging whether to wear the hat through a classification model, and analyzing the colors of the clothes and trousers through the HSV color space. In the invention, for people whether to take the hat or not, the head picture can be cut by adopting the result of detecting the head key points by the key points of the human body, and a classifier for wearing the hat or not can be trained. For the colors of clothes and trousers, the invention adopts the key point result of the body and the legs detected by the key points of the human body to cut out the upper half picture and the lower half picture, and the colors of the clothes and the trousers are identified by converting the upper half picture and the lower half picture into an HSV color space, and the color with the largest duty ratio is regarded as the color. And finally, sending out alarm sound to remind the stolen person according to the judging result of the classification model and the analysis result of the HSV color space. And simultaneously, video when the theft occurs is stored as evidence for evidence collection.

In order to remind a thief in time, the invention adopts the steps of identifying whether the thief and the thief wear a hat, what color of clothes and what color of trousers, and then making a sound to remind the thief, for example, a student wearing black trousers with white clothes, that something is stolen by a person wearing black trousers with the hat. Because the thief can walk away or run away quickly after getting things out, the thief can lock the thief from the crowd quickly after hearing the sound, and the thief can be helped to a great extent in time to stop the damage.

In some embodiments of the present invention, the step of calculating the intersection ratio between human frames includes:

storing video frames of the current frame, a previous N frame of the current frame, and a next N frame of the current frame;

after the N frame passes through the N frame, calculating the cross ratio of the N frame.

The formula for calculating the cross-over ratio between human frames is as follows:

wherein IoU represents the cross ratio, A, B represents two human frames respectively;

wherein IoU of the current N frame _t’ Equal to 0, ioU of the current frame _t IoU of the last N frame greater than 0 _t” When the value is equal to 0, the theft is judged to occur.

The segmentation classes of the Cls-UNet model include: the hand, backpack, single shoulder bag, mobile phone and wallet, the classified number of classification is 2, wherein 0 indicates that the article is not stolen, 1 indicates that the article is stolen.

That is, it should be noted that, through analysis, a thief will first approach the target person, then steal some items from the pocket or backpack of the target person, and finally leave the target person, so the thief can be identified by grasping these three key moments. The invention adopts the method of key points of human body to detect human body, analyzes the second moment in detail, combines the characteristics of three moments to carry out logic analysis, and finally identifies thieves.

In the process of calculating the cross-over ratio between human frames, the robot automatically stores the current frame, the previous N frame of the current frame and the video frame of the next N frame of the current frame. The video frame of the later N frame is the video frame at the current moment, and the video frame of the later N frame is the later N frame relative to the theft moment, namely the video frame of the later N frame passes through the N frame after the thief steals things, and the cross ratio of the later N frame is calculated after the later N frame passes through the N frame. The formula for calculating the cross-over ratio between human frames is as follows:

wherein IoU represents the cross ratio and A, B represents two human frames respectively. And alarming after meeting the conditions.

Assuming that the video frequency of the robot camera is 30FPS, N frames take N/30 seconds, where N defaults to 30. When IoU of the two human frames is greater than 0, it is considered that theft is suspected. Then, the upper body parts of the two parts are cut out according to the position information of the key points of the hands, and whether the theft occurs is judged by a newly designed classifier.

If the classifier determines that theft has occurred. Then pass throughAfter 10 frames they are analyzed IoU, if IoU of the first N frame is equal to 0, ioU of the current frame is greater than 0, ioU of the last N frame is equal to 0, as shown in the above equation, the theft is comprehensively judged to occur. IoU _t IoU representing two human target frames of current frame relative to theft moment _t’ IoU of two human body target frames of the N frame relative to the theft moment _t” IoU for the two human target frames of the last N frames relative to the theft moment.

In some embodiments of the invention, the segmentation class of the Cls-UNet model includes: the hand, backpack, single shoulder bag, mobile phone and wallet, the classified number of classification is 2, wherein 0 indicates that the article is not stolen, 1 indicates that the article is stolen. The judging logic of the Cls-UNet model is divided into hands, and is divided into any one of a backpack, a single shoulder bag, a mobile phone and a wallet, and when the classified class channel output of the Cls-UNet model is 1, the theft is judged to occur.

In other words, since the theft is special, a common classification network may generate more false positives, the invention innovatively modifies a semantic segmentation network UNet to be a segmentation network with a classification function, and the new network is named as Cls-UNet, so that more information can be provided for judging the theft. Compared to the common UNet, the input of Cls-UNet is consistent with UNet, and the output is added with a dimension for displaying its category. The number of divided categories is 5: the hand bag, the backpack, the single shoulder bag, the mobile phone and the wallet are respectively arranged; the number of classified categories is 2: 0 and 1, respectively (0 means that something is not stolen, 1 means something is stolen, and the ratio of a certain value in the class channel is more than 80%, and the class is the value). The final judgment logic is divided into hands, and is divided into any one of a backpack, a single shoulder bag, a mobile phone and a wallet, and when the class channel output is 1, the theft is judged to occur.

In summary, according to the public place thief detection method provided by the embodiment of the invention, the patrol robot is used for detecting key points of human bodies, and can go deep into the crowd, so that a clearer image can be shot compared with a fixed camera. And the patrol robot can automatically move, so that the cost of the camera is saved. The intersection ratio between the human body frame and the human body frame is calculated through the human body key points, image analysis is carried out by adopting semantic segmentation UNet networks Cls-Unet and the like with a classification function, and image segmentation and classification are carried out on the cut pictures, so that theft detection is realized. The detection method for the thieves in the public places has the advantages of wide application range, suitability for large-space environments, clear shooting, low cost and suitability for large-area popularization and use.

According to a second aspect of the present invention, there is provided a public place thief detection system, which is applied to the public place thief detection method in the above embodiment, the detection system including a detection module, a first calculation module, a second calculation module, a clipping module, and a logic analysis module. The detection module detects the person through the human body key point detection model. The first calculation module calculates a human body frame through the human body key points. The second calculation module is used for calculating the cross-over ratio between the human frames. The clipping module clips out the picture of the part between the thighs and the neck through the position information of the key points of the hands of the human body. The logic analysis module is used for inputting the cut pictures of the part between the thighs and the neck into the Cls-UNet model to obtain a segmentation result and a classification result, and judging that the theft occurs under the condition that the segmentation result and the classification result meet the preset conditions and the front-back frame relationship meets the preset conditions.

According to the public place thief detection system provided by the embodiment of the invention, the patrol robot is used for detecting the key points of the human body, and can go deep into the crowd, so that a clearer image can be shot compared with a fixed camera. And the patrol robot can automatically move, so that the cost of the camera is saved. The intersection ratio between the human body frame and the human body frame is calculated through the human body key points, image analysis is carried out by adopting semantic segmentation UNet networks Cls-Unet and the like with a classification function, and image segmentation and classification are carried out on the cut pictures, so that theft detection is realized. The detection method for the thieves in the public places has the advantages of wide application range, suitability for large-space environments, clear shooting, low cost and suitability for large-area popularization and use.

According to a third aspect of the present invention, there is also provided an electronic apparatus comprising: a processor 201 and a memory 202, wherein computer program instructions are stored in the memory 202, which, when executed by the processor 201, cause the processor 201 to perform the steps of the public place thief detection method in the above-described embodiments.

Further, as shown in fig. 3, the electronic device further comprises a network interface 203, an input device 204, a hard disk 205, and a display device 206.

The interfaces and devices described above may be interconnected by a bus architecture. The bus architecture may include any number of interconnected buses and bridges. One or more central processing units 201 (CPUs), in particular represented by processor 201, and various circuits of one or more memories 202, represented by memories 202, are connected together. The bus architecture may also connect various other circuits together, such as peripheral devices, voltage regulators, and power management circuits. It is understood that a bus architecture is used to enable connected communications between these components. The bus architecture includes, in addition to a data bus, a power bus, a control bus, and a status signal bus, all of which are well known in the art and therefore will not be described in detail herein.

The network interface 203 may be connected to a network (e.g., the internet, a local area network, etc.), and may obtain relevant data from the network and store the relevant data in the hard disk 205.

Input device 204 may receive various instructions entered by an operator and send to processor 201 for execution. The input device 204 may include a keyboard or pointing device (e.g., a mouse, a trackball, a touch pad, or a touch screen, among others).

A display device 206 may display results obtained by the execution of instructions by the processor 201.

The memory 202 is used for storing programs and data necessary for the operation of the operating system 2021, and data such as intermediate results in the calculation process of the processor 201.

It will be appreciated that the memory 202 in embodiments of the invention can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. The nonvolatile memory may be Read Only Memory (ROM), programmable Read Only Memory (PROM), erasable Programmable Read Only Memory (EPROM), electrically Erasable Programmable Read Only Memory (EEPROM), or flash memory, among others. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. The memory 202 of the apparatus and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory 202.

In some implementations, the memory 202 stores the following elements, executable modules or data structures, or a subset thereof, or an extended set thereof: an operating system 2021 and application programs 2022.

The operating system 2021 contains various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application programs 2022 include various application programs 2022, such as a Browser (Browser), for implementing various application services. The program implementing the method of the embodiment of the present invention may be contained in the application program 2022.

The above-described processor 201 performs the steps of the public place thief detection method according to the above-described embodiment when calling and executing the application 2022 and data stored in the memory 202, specifically, a program or instructions stored in the application 2022.

The method disclosed in the above embodiment of the present invention may be applied to the processor 201 or implemented by the processor 201. The processor 201 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 201 or by instructions in the form of software. The processor 201 may be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention. A general purpose processor may be a microprocessor or the processor 201 may be any conventional processor 201 or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 202, and the processor 201 reads the information in the memory 202 and, in combination with its hardware, performs the steps of the method described above.

It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For a hardware implementation, the processing units may be implemented within one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units designed to perform the functions of the application, or a combination thereof.

For a software implementation, the techniques herein may be implemented with modules (e.g., procedures, functions, and so on) that perform the functions herein. The software codes may be stored in the memory 202 and executed by the processor 201. The memory 202 may be implemented within the processor 201 or external to the processor 201.

Specifically, the processor 201 is further configured to read the computer program and perform the steps of predicting a stake pocket method and outputting answers to questions asked by the user.

In a fourth aspect of the present invention, there is also provided a computer-readable storage medium storing a computer program which, when executed by the processor 201, causes the processor 201 to perform the steps of the public place thief detection method of the above-described embodiment.

In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may be physically included separately, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in hardware plus software functional units.

The integrated units implemented in the form of software functional units described above may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium, and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform part of the steps of the transceiving method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

While certain specific embodiments of the invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the invention. It will be appreciated by those skilled in the art that modifications may be made to the above embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.

Claims

1. A method for detecting a thief in a public location, comprising:

2. The method for detecting a thief in a public place as in claim 1, further comprising:

3. The method for detecting a thief in a public place according to claim 2, further comprising: video when theft occurs is stored as evidence for evidence.

4. The method of detecting a thief in a public place according to claim 1, wherein the step of calculating the intersection ratio between the human frames includes:

5. The method for detecting a thief in a public place according to claim 4, wherein the formula for calculating the intersection ratio between the human frames is:

6. The method of claim 1, wherein the classification of the Cls-UNet model comprises: the hand, backpack, single shoulder bag, mobile phone and wallet, the classified number of classification is 2, wherein 0 indicates that the article is not stolen, 1 indicates that the article is stolen.

7. The method according to claim 6, wherein the determining logic of the Cls-UNet model is configured to determine that theft occurs when the determining logic is configured to divide the Cls-UNet model into one of a backpack, a rucksack, a mobile phone, and a wallet, and the classified class channel output of the Cls-UNet model is 1.

8. A public place thief detection system for use in the public place thief detection method of any one of claims 1-7, the detection system comprising:

9. An electronic device, comprising: a processor and a memory in which computer program instructions are stored, wherein the computer program instructions, when executed by the processor, cause the processor to perform the steps of the public place thief detection method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, causes the processor to perform the steps of the public place thief detection method as claimed in any one of claims 1-7.