Factory theft object detection method and device, electronic equipment and medium
By setting multiple theft target areas within the factory camera's range and configuring type parameters, combined with human and vehicle mode switching and multi-dimensional detection, the problem of high false alarm and false alarm rates in factory security systems has been solved, achieving more accurate detection of theft targets.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN STARCAM TECH
- Filing Date
- 2026-03-03
- Publication Date
- 2026-06-19
AI Technical Summary
Existing factory security systems have high false alarm and false negative rates in theft detection, cannot distinguish between normal movement of people and vehicles and unauthorized theft, and cannot meet the differentiated needs of different areas of the factory.
Multiple theft target detection areas are set within the factory camera range, corresponding theft target type parameters are configured, and the control mode is switched according to the detection of people and vehicles. The comprehensive judgment is made by combining the duration of movement, displacement threshold and target contour matching degree, and authorized movement mark detection is added.
It effectively reduces the false alarm rate and false negative rate of theft detection in factories, improves the accuracy and adaptability of security, and meets the security needs of different areas of the factory.
Smart Images
Figure CN122241250A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of security technology, specifically to a method, device, electronic device, and storage medium for detecting objects stolen from factories. Background Technology
[0002] Network cameras ("IP cameras", or IPCs for short) are front-end acquisition devices for factory video surveillance. They enable real-time image transmission via a network and can be used with back-end storage devices to complete image acquisition across the entire factory, providing raw image data for theft detection.
[0003] Motion detection technology is commonly used for security monitoring and automatic alarms in unattended areas of factories. It involves front-end cameras capturing images at different frame rates, and a back-end processor calculating and comparing image changes using algorithms. When movement is detected in the image, the system triggers corresponding actions. Currently, most motion detection processing methods used in factory security are single-area processing modes, allowing only one detection area to be set. Furthermore, the sensitivity and processing methods within this area use a set of universal parameters, without customized configurations for different theft target areas within the factory.
[0004] Meanwhile, factories typically experience routine personnel operations and vehicle material transport. Existing detection technologies do not differentiate between personnel and vehicle detection modes, using the same set of motion detection parameters. This easily leads to false alarms, misinterpreting normal personnel operations and compliant vehicle transport as theft. Furthermore, thieves can easily evade detection by exploiting the mixed nature of these environments, resulting in missed detections. In addition, existing technologies simply judge movement on screen without considering the type of theft target or authorized movement indicators. This makes it difficult to accurately identify unauthorized movement and fails to meet the differentiated theft detection needs of different areas such as raw material areas, finished product areas, and precision tool areas. The high false alarm and missed detection rates make it unsuitable for the refined and targeted security and theft detection requirements of factories. To address these issues, this application is proposed to improve the accuracy of factory theft detection and enhance the practicality and adaptability of factory security products. Summary of the Invention
[0005] This application provides a method, electronic device, apparatus, and storage medium for detecting theft objects in a factory, which can meet the differentiated theft detection needs of different areas in a factory, effectively reduce the false alarm rate and false negative rate of theft detection in the factory, and improve the precision of factory security.
[0006] In a first aspect, embodiments of this application provide a method for detecting objects stolen from factories, including: At least two theft target detection areas are pre-defined within the range captured by the factory camera, and corresponding theft target type parameters are configured for each theft target detection area; Based on the preset human and vehicle detection switching control method and the corresponding switching threshold, the current mode is switched to human detection mode or vehicle detection mode. In each mode, the theft detection parameters of each theft target detection area are set separately. Read the theft detection parameters corresponding to the current mode from the theft detection parameters of each theft target detection area, and fuse them with the theft target type parameters of that area to obtain the fused detection parameters; Based on the fused detection parameters, determine whether the images captured by the cameras in each theft target detection area have shown an unauthorized movement detection event of the theft target.
[0007] Optionally, in some embodiments of this application, the theft detection parameters include movement duration parameters, movement displacement threshold parameters, and target contour matching degree parameters; In the step of determining whether an unauthorized movement detection event of a theft object has occurred in the images captured by the camera in each theft target detection area, if the target in the detection area meets any of the following conditions: the movement duration exceeds the movement duration parameter, the movement displacement reaches the movement displacement threshold parameter, or the matching degree between the target contour and the corresponding theft target type parameter reaches the target contour matching degree parameter, and no authorized movement identifier is detected, then it is determined that there is an unauthorized movement detection event of a theft object.
[0008] Optionally, in some embodiments of this application, the human and vehicle detection switching control method includes a timed switching method; When the human and vehicle detection switching control mode is a timed switching mode, the step of switching the current mode to human detection mode or vehicle detection mode includes the following sub-steps: Compare the current time with the preset switching threshold. If the current time reaches the preset first switching threshold, then switch to human detection mode; If the current time reaches the preset second switching threshold, then switch to vehicle detection mode.
[0009] Optionally, in some embodiments of this application, the human and vehicle detection switching control method includes an automatic switching method; When the human and vehicle detection switching control mode is automatic switching mode, the step of switching the current mode to human detection mode or vehicle detection mode includes the following sub-steps: The system compares the proportion of people and vehicles in the current captured image with a preset switching threshold, and also incorporates real-time signals from factory access control and gate systems for further analysis. If the proportion of human features in the current image is higher than the preset third switching threshold, and there is no vehicle passage signal at the access control / gate, then switch to human detection mode; If the proportion of vehicle features in the current image is higher than the preset third switching threshold, or if there is a vehicle passage signal at the access control / gate, then switch to vehicle detection mode.
[0010] Optionally, in some embodiments of this application, before the step of switching the current mode to a human detection mode or a vehicle detection mode according to a preset human and vehicle detection switching control method and the corresponding switching threshold, the following steps are further included: The pedestrian and vehicle detection switching control mode is set, which includes the timed switching mode, the automatic switching mode, and the default mode; When the human and vehicle detection switching control mode is in the default mode, the human and vehicle detection switching function is turned off, and the same set of theft detection parameters is used by default for both human and vehicle.
[0011] Optionally, in some embodiments of this application, in the sub-step of comparing the proportion of human and vehicle features in the currently captured image with a preset switching threshold, Regarding the proportion of human features, these human features are identified and statistically analyzed through human body contour features and gait features. Regarding the proportion of vehicle features, these features are identified and statistically analyzed through vehicle model features and license plate features, and verified by combining them with RFID vehicle identification signals from the factory area.
[0012] Optionally, in some embodiments of this application, after determining whether an unauthorized movement detection event of a theft object has occurred in the images captured by cameras in each theft target detection area based on the fused detection parameters, the method further includes: The steps for handling theft detection in cases of unauthorized movement of stolen objects.
[0013] Secondly, embodiments of this application provide a factory theft detection device, comprising: The configuration module is used to pre-set at least two theft target detection areas within the range captured by the factory camera, and to configure corresponding theft target type parameters for each theft target detection area; The switching module is used to switch the current mode to either human detection mode or vehicle detection mode according to the preset human and vehicle detection switching control mode and the corresponding switching threshold. In each mode, the theft detection parameters of each theft target detection area are set separately. The reading module is used to read the theft detection parameters corresponding to the current mode from the theft detection parameters of each theft target detection area, and fuse them with the theft target type parameters of the area to obtain the fused detection parameters; The judgment module is used to determine, based on the fused detection parameters, whether the images captured by the cameras in each theft target detection area have shown an unauthorized movement detection event of the theft object.
[0014] Accordingly, this application also provides an electronic device, including a memory, a processor, and a processor program stored in the memory and executable on the processor, wherein the processor executes the program as described in any of the methods above.
[0015] This application also provides a storage medium storing a processor program that, when executed by a processor, implements any of the methods described above.
[0016] This application provides a method, apparatus, electronic device, and storage medium for detecting theft targets in a factory. At least two theft target detection areas are pre-defined within the field of view of a factory camera. After configuring corresponding theft target type parameters for each detection area, the current mode is switched to either a human detection mode or a vehicle detection mode based on a pre-defined human / vehicle detection switching control method and corresponding switching threshold. In each mode, the theft detection parameters for each detection area are set independently. The theft detection parameters corresponding to the current mode are read from the theft detection parameters of each detection area and fused with the theft target type parameters of that area to obtain fused detection parameters. Finally, the fused detection parameters are used to obtain the fused detection parameters. The parameters determine whether unauthorized movement of the stolen object has occurred in the images captured by the cameras in each theft target detection area. In the factory theft object detection scheme provided in this application, theft detection parameters for multiple areas are set separately. Each area is selected by index for drawing the area and setting parameters such as movement duration, movement displacement threshold, and target contour matching degree. At the same time, corresponding theft target type parameters are configured for each area. In addition, multi-dimensional theft detection parameters are added, and a comprehensive judgment is made by combining movement duration, movement displacement threshold, and target contour matching degree. An authorized movement identification detection step is also added to avoid judging normal factory operations and compliant vehicle transportation as theft, thereby improving detection accuracy. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is a flowchart illustrating the factory theft detection method provided in this application embodiment; Figure 2 This is a schematic diagram of the structure of the factory theft detection device provided in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation
[0019] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0020] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.
[0021] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.
[0022] The following describes in detail the embodiments involved in this application. It should be noted that the order of description of the embodiments in this application is not intended to limit the priority of the embodiments.
[0023] This application provides a method, apparatus, storage medium, and smart terminal for detecting objects stolen from factories. Specifically, the method for detecting objects stolen from factories according to this application can be executed by a smart terminal or a server, wherein the smart terminal can be a terminal. The terminal can be a smartphone, tablet computer, laptop computer, touch screen, game console, personal computer (PC), personal digital assistant (PDA), or other smart terminal. The terminal may also include a client, which can be a media playback client or a real-time factory theft detection client, etc.
[0024] This application provides a method for detecting objects stolen from a factory, which can be executed by an electronic device or a server. This application example illustrates the method using an electronic device. The electronic device includes a touchscreen display and a processor. The touchscreen display presents a graphical user interface (GUI) and receives user commands applied to the GUI. When the user operates the GUI via the touchscreen display, the GUI can control local content on the electronic device or control content on the server side in response to the received commands.
[0025] The factory theft detection solution provided in this application allows for separate settings of theft detection parameters for multiple areas. Each area is selected by index for drawing and setting parameters such as movement duration, movement displacement threshold, and target contour matching degree. At the same time, corresponding theft target type parameters are configured for each area. In addition, multi-dimensional theft detection parameters are added, and a comprehensive judgment is made by combining movement duration, movement displacement threshold, and target contour matching degree. Furthermore, an authorized movement marker detection step is added to avoid classifying normal factory operations and compliant vehicle transportation as theft, thereby improving detection accuracy.
[0026] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the priority of the embodiments.
[0027] A method for detecting theft objects in a factory includes: pre-setting at least two theft target detection areas within the field of view of a factory camera, and configuring corresponding theft target type parameters for each theft target detection area; switching the current mode to either a human detection mode or a vehicle detection mode according to a pre-set human and vehicle detection switching control method and the corresponding switching threshold, wherein the theft detection parameters for each theft target detection area are set separately in each mode; reading the theft detection parameters corresponding to the current mode from the theft detection parameters of each theft target detection area, and fusing them with the theft target type parameters of that area to obtain fused detection parameters; and determining, based on the fused detection parameters, whether an unauthorized movement detection event of a theft object has occurred in the images captured by the camera in each theft target detection area.
[0028] In the following description, numerous technical details are presented to facilitate the reader's understanding of this application. However, those skilled in the art will understand that the technical solutions claimed in the claims of this application can be implemented even without these technical details and with various variations and modifications based on the following embodiments.
[0029] To make the objectives, technical solutions, and advantages of this application clearer, the implementation methods of this application will be described in further detail below.
[0030] The first embodiment of this application relates to a method for detecting objects of theft in a factory. This method is the core method for detecting theft in a factory and is suitable for various security monitoring scenarios in factories. The specific steps are as follows: In step 101, at least two theft target detection areas are pre-defined within the range of the factory cameras, and corresponding theft target type parameters are configured for each detection area. It can be understood that the factory cameras can cover core factory areas such as raw material warehouses, finished product processing workshops, precision tool rooms, and material transport channels. Theft target detection areas can be defined according to the factory's security priorities, and the theft target type parameters can be configured according to the actual types of items in each area. For example, the raw material area can be configured with parameters for "metal raw materials and chemical raw materials," the finished product area with parameters for "finished equipment and packaged finished products," and the tool room with parameters for "precision instruments and power tools."
[0031] Then proceed to step 102, where the current mode is switched to either human detection mode or vehicle detection mode according to the preset human and vehicle detection switching control method and the corresponding switching threshold. In each mode, the theft detection parameters for each theft target detection area are set separately.
[0032] It is understandable that the switching threshold is a pre-set parameter value used to determine whether the human and vehicle detection mode should be switched, and it can be customized according to the actual production operation of the factory.
[0033] The pedestrian and vehicle detection switching control method includes a timed switching method. When the pedestrian and vehicle detection switching control method is a timed switching method, the steps to switch the current mode to pedestrian detection mode or vehicle detection mode include the following sub-steps: Compare the current time with the preset switching threshold. If the current time reaches the preset first switching threshold, then switch to human detection mode; If the current time reaches the preset second switching threshold, then switch to vehicle detection mode.
[0034] Preferably, the pedestrian and vehicle detection switching control method includes an automatic switching mode. When the pedestrian and vehicle detection switching control method is automatic switching, the step of switching the current mode to pedestrian detection mode or vehicle detection mode includes the following sub-steps: The system compares the proportion of people and vehicles in the current captured image with a preset switching threshold, and also incorporates real-time signals from factory access control and gate systems for further analysis. If the proportion of human features in the current image is higher than the preset third switching threshold, and there is no vehicle passage signal at the access control / gate, then switch to human detection mode; If the proportion of vehicle features in the current image is higher than the preset third switching threshold, or if there is a vehicle passage signal at the access control / gate, then switch to vehicle detection mode.
[0035] It is understandable that in actual security applications in factories, the characteristics of human and vehicle movement vary greatly depending on the production time period and production process, and the rules for human and vehicle passage differ in different areas of the factory. Therefore, it is still somewhat unreasonable to switch the current detection mode solely based on the time period. Thus, combining the proportion of human and vehicle features in the image with the real-time passage signals of the factory's access control and gates can improve the accuracy of human and vehicle mode switching.
[0036] The human and vehicle detection switching control mode is set to automatic switching mode. The current mode is switched according to the above composite judgment conditions, which can adapt to the differences in human and vehicle flow caused by different working scenarios and production processes in the factory, thereby achieving more accurate detection of theft objects in the factory.
[0037] Preferably, in the sub-step of comparing the proportion of human and vehicle features in the currently captured image with a preset switching threshold: Regarding the proportion of human features, these human features are identified and statistically analyzed through human body contour features and gait features. Regarding the proportion of vehicle features, these features are identified and statistically analyzed through vehicle model features and license plate features, and verified by combining them with RFID vehicle identification signals from the factory area.
[0038] This identification method combines the factory's own security hardware system with video image feature recognition and RFID vehicle identification signals in the factory area, effectively avoiding identification errors caused by image obstruction or similar vehicle / human features, and improving the accuracy of the statistics on the proportion of human and vehicle features.
[0039] Preferably, before step 102, the following step is further included: The pedestrian and vehicle detection switching control mode can be set, including timed switching mode, automatic switching mode and default mode; When the human and vehicle detection switching control mode is set to the default mode, the human and vehicle detection switching function is turned off, and the same set of theft detection parameters is used by default for both human and vehicle.
[0040] Setting different human and vehicle detection switching control methods provides more flexible configuration for factory security applications. Different switching methods can be changed according to different production scenarios and security needs of the factory. For example, the finished product workshop with dense human operations can adopt the automatic switching method, while the material channel for 24-hour vehicle transportation in the factory can adopt the timed switching method.
[0041] Then proceed to step 103, where theft detection parameters corresponding to the current mode are read from theft detection parameters of each theft target detection area, and fused with the theft target type parameters of that area to obtain fused detection parameters.
[0042] Theft detection parameters include movement duration parameters, movement displacement threshold parameters, and target contour matching parameters. In the step of detecting stolen objects in the images captured by the camera in each theft target detection area, the fused detection parameters must be combined with the determination of whether authorized movement identifiers exist, such as factory work badges, vehicle authorized RFID, and electronic work order identifiers. If no authorized movement identifier is detected, unauthorized movement is then determined based on the parameters.
[0043] It is understandable that the longer the movement duration parameter, the longer the target needs to move within the detection area before a judgment is triggered; the larger the movement displacement threshold parameter, the greater the displacement the target needs to undergo within the detection area before a judgment is triggered; and the higher the target contour matching parameter, the stricter the matching requirement between the target contour and the theft target type parameter.
[0044] Next, in step 104, based on the fused detection parameters, it is determined whether an unauthorized movement detection event of the stolen object has occurred in the images captured by the cameras in each theft target detection area. It is important to note that the theft target detection area, which was defined and activated in step 101, is continuously detecting stolen objects. Whether an unauthorized movement detection event of the stolen object has occurred is determined based on the fusion of the read parameters and target type parameters, combined with the detection results of the authorized movement identifier.
[0045] The specific determination logic is as follows: when a target within the detection area meets any of the following conditions: the duration of movement exceeds the duration of movement parameter, the displacement reaches the displacement threshold parameter, or the matching degree between the target contour and the corresponding theft target type parameter reaches the target contour matching degree parameter, and no authorized movement identifier is detected, it is determined to be an unauthorized movement detection event with a theft target.
[0046] This process will then end.
[0047] Setting up factory theft detection into multiple theft target detection zones and configuring target type parameters can meet the differentiated theft detection needs of different areas of the factory. Simultaneously, each theft target detection zone supports the setting of two sets of theft detection parameters for people and vehicles, according to the specific detection scenario requirements. After parameter fusion, unauthorized movement determination is performed, enabling factory theft detection to achieve the lowest possible false alarm and false negative rates.
[0048] As a preferred embodiment of this implementation, the specific processing flow for switching between human and vehicle detection can be set according to the factory's security needs: the human and vehicle control mode can be selected as off (i.e., the human and vehicle detection switching control method is the default mode), timed mode, or automatic mode, depending on the factory's application requirements. When the human and vehicle control mode is off, the current mode is switched to off mode, and human and vehicle use the same set of parameters by default; when the human and vehicle control mode is timed mode, the current mode is switched to the corresponding human detection mode and vehicle detection mode based on whether the current time is within the personnel operation period or the vehicle transportation period; when the human and vehicle control mode is automatic mode, the proportion of human and vehicle features in the current captured image is compared with the preset switching threshold, and the real-time passage signals of the factory access control and gate are used for auxiliary judgment, and the current mode is switched to the corresponding human detection mode and vehicle detection mode. After setting the corresponding mode according to the above judgment, the corresponding parameters are read from the parameters of each theft target detection area and fused with the target type parameters to detect theft objects in the factory.
[0049] By optimizing the detection method for factory theft targets, the accuracy of factory theft detection can be effectively improved, and more flexible configuration of factory security applications can be provided. For situations where the factory monitoring area is large and the security needs of different areas vary significantly, the multi-area processing of theft detection allows the factory to set different parameters for different areas according to its own production scenario and security needs, which has practical application value.
[0050] The second embodiment of this application relates to a factory theft detection processing method. This factory theft detection processing method includes the factory theft detection method of the first embodiment. After determining whether an unauthorized movement detection event of a theft object has occurred in the images captured by cameras in each theft target detection area, the method further includes a step of performing corresponding theft detection processing when an unauthorized movement detection event of a theft object occurs.
[0051] Specific theft detection and processing include: On-site audible and visual alarms; Triggers an alarm upload from the factory security terminal, which in turn triggers the location tracking terminal for security personnel. Store H.264 video images, MPEG video images, or video clips of the theft process; Capture high-resolution close-up images of the target of theft and the moving subject.
[0052] Furthermore, it is understood that in other embodiments of this application, other theft detection processes may also be adopted, such as linking the factory access control / barrier locking system, triggering the factory broadcast system to issue warnings, etc., and are not limited to the above-mentioned processes.
[0053] The corresponding theft detection processing involves triggering an alarm upload from the factory security terminal, with the alarm information carrying the detection area information of the theft target, the theft target type parameters, and the real-time displacement information of unauthorized movement.
[0054] Sending the above detailed information with the alarm will help security personnel to pinpoint the location of the theft, identify the type of theft target and its movement trajectory as soon as possible, and improve the emergency response efficiency of factory security.
[0055] The concurrent processing of multiple theft detection methods in this embodiment can save static high-definition close-up images and dynamic video clips at the time of theft, providing strong evidence for subsequent theft investigations and liability determination, and effectively providing the best image source required for factory theft detection.
[0056] As a preferred embodiment of this implementation, the specific process for detecting factory theft objects based on the switching control of human and vehicle detection is as follows: First, the current mode is determined to be human detection mode, vehicle detection mode, or off mode based on the human and vehicle control parameters; then, based on the determination result, the parameters of multiple theft target detection areas are read and fused with the theft target type parameters of each area; then, based on the fused parameters and the changes in the image, combined with the detection results of authorized movement markers, it is determined whether an unauthorized movement detection event of theft objects has occurred; if such an event occurs, the corresponding theft detection processing is performed according to the pre-configured settings, and then the process ends.
[0057] Compared to commonly used motion detection processing methods applied to factory theft detection, the improvements of this application are mainly reflected in: The factory theft detection can be set to multiple theft target detection areas. The theft detection parameters for each area can be set separately. Each area can be selected by index and the parameters such as the area drawing duration, movement displacement threshold, and target contour matching degree can be set. At the same time, the corresponding theft target type parameters can be configured for each area. Meanwhile, multi-dimensional theft detection parameters are added, and a comprehensive judgment is made by combining the duration of movement, the movement displacement threshold, and the target contour matching degree. At the same time, the detection link of authorized movement marks is added to avoid judging normal factory work and compliant vehicle transportation as theft, thereby improving detection accuracy. Furthermore, the parameters for each area in the factory theft detection system (movement duration, movement displacement threshold, target contour matching parameters) are set according to both human and vehicle detection modes. This caters to different security scenarios in factories, supporting the setting of two sets of parameters for both human and vehicle detection to minimize false alarms and missed alarms. Human and vehicle control offers three modes for factory users to choose from: default, automatic switching, and timed switching. The default setting uses the same set of parameters for both human and vehicle detection. Switching between the two sets of parameters can be timed by setting a time period, or automatically controlled by combining the proportion of human and vehicle features on the screen with real-time signals from factory access control and gates.
[0058] All implementation methods of this application can be implemented in software, hardware, firmware, etc. Regardless of whether this application is implemented in software, hardware, or firmware, the instruction code can be stored in any type of computer-accessible memory (e.g., permanent or modifiable, volatile or non-volatile, solid-state or non-solid-state, fixed or replaceable media, etc.). Similarly, the memory can be, for example, Programmable Array Logic (PAL), Random Access Memory (RAM), Programmable Read Only Memory (PROM), Read-Only Memory (ROM), Electrically Erasable Programmable ROM (EEPROM), magnetic disk, optical disk, Digital Versatile Disc (DVD), etc. To facilitate better implementation of the factory theft detection method of this application embodiment, this application embodiment also provides a factory theft detection device, wherein the meaning of the terms is the same as that in the factory theft detection system described above, and specific implementation details can be found in the description of the system embodiment.
[0059] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a factory theft detection device provided in an embodiment of this application. Specifically, the factory theft detection device may include a configuration module 201, a switching module 202, a reading module 203, and a judgment module 204, as follows: The configuration module 201 is used to pre-set at least two theft target detection areas within the range captured by the factory camera, and to configure corresponding theft target type parameters for each theft target detection area; The switching module 202 is used to switch the current mode to human detection mode or vehicle detection mode according to the preset human and vehicle detection switching control mode and the corresponding switching threshold. In each mode, the theft detection parameters of each theft target detection area are set separately. The reading module 203 is used to read the theft detection parameters corresponding to the current mode from the theft detection parameters of each theft target detection area, and fuse them with the theft target type parameters of the area to obtain fused detection parameters; The judgment module 204 is used to determine, based on the fused detection parameters, whether an unauthorized movement detection event of the theft object has occurred in the images captured by the cameras in each theft target detection area. This application provides a factory theft detection device. A configuration module 201 pre-sets at least two theft target detection areas within the field of view of a factory camera, and configures corresponding theft target type parameters for each detection area. A switching module 202 switches the current mode to either a human detection mode or a vehicle detection mode based on a pre-set human / vehicle detection switching control method and corresponding switching threshold. In each mode, the theft detection parameters for each detection area are set individually. A reading module 203 reads the theft detection parameters corresponding to the current mode from the theft detection parameters of each detection area and fuses them with the theft target type parameters of that area to obtain fused detection parameters. Finally, a judgment module 204 determines the fused detection parameters based on the fused parameters. The fused detection parameters are used to determine whether unauthorized movement of the stolen object has occurred in the images captured by the cameras in each theft target detection area. In the factory theft object detection scheme provided in this application, the theft detection parameters for multiple areas are set separately. Each area is selected by index for drawing the area and setting parameters such as movement duration, movement displacement threshold, and target contour matching degree. At the same time, corresponding theft target type parameters are configured for each area. In addition, multi-dimensional theft detection parameters are added, and a comprehensive judgment is made by combining movement duration, movement displacement threshold, and target contour matching degree. An authorized movement identification detection step is also added to avoid judging normal factory operations and compliant vehicle transportation as theft, thereby improving detection accuracy. Furthermore, embodiments of this application also provide an electronic device, such as... Figure 3 As shown, it illustrates a structural schematic diagram of the electronic device involved in the embodiments of this application, specifically: The electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more processor-readable storage media, a power supply 303, and an input unit 304. Those skilled in the art will understand that... Figure 3 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: Processor 301 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in memory 302, and by calling data stored in memory 302, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. Optionally, processor 301 may include one or more processing cores; preferably, processor 301 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless factory theft detection. It is understood that the modem processor may not be integrated into processor 301.
[0060] The memory 302 can be used to store software programs and modules. The process 301 executes various functional applications and factory theft detection methods by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 302 may also include a memory controller to provide the process 301 with access to the memory 302.
[0061] The electronic device also includes a power supply 303 that supplies power to various components. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 303 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.
[0062] The electronic device may also include an input unit 304, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
[0063] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in the embodiments of this application, the processing 301 in the electronic device loads the executable files corresponding to the processes of one or more applications into the memory 302 according to the following instructions, and the processing 301 runs the applications stored in the memory 302 to realize various functions, as follows: At least two theft target detection areas are pre-defined within the field of view of the factory cameras, and corresponding theft target type parameters are configured for each theft target detection area. Based on the pre-defined human and vehicle detection switching control method and corresponding switching threshold, the current mode is switched to either human detection mode or vehicle detection mode. In each mode, the theft detection parameters for each theft target detection area are set independently. The theft detection parameters corresponding to the current mode are read from the theft detection parameters of each theft target detection area and fused with the theft target type parameters of that area to obtain fused detection parameters. Based on the fused detection parameters, it is determined whether an unauthorized movement detection event of the stolen object has occurred in the images captured by the cameras in each theft target detection area.
[0064] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.
[0065] In this embodiment, the theft detection parameters for multiple regions are set separately. Each region is selected by index for drawing and setting parameters such as movement duration, movement displacement threshold, and target contour matching degree. At the same time, corresponding theft target type parameters are configured for each region. In addition, multi-dimensional theft detection parameters are added, and a comprehensive judgment is made by combining movement duration, movement displacement threshold, and target contour matching degree. An authorized movement identifier detection step is also added to avoid judging normal factory work and compliant vehicle transportation as theft, thereby improving detection accuracy.
[0066] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a processor-readable storage medium and loaded and executed by a processor.
[0067] Therefore, embodiments of this application provide a storage medium storing a plurality of instructions that can be loaded by a processor to execute steps in any of the factory theft detection methods provided in embodiments of this application. For example, the instructions can execute the following steps: At least two theft target detection areas are pre-defined within the field of view of the factory cameras, and corresponding theft target type parameters are configured for each theft target detection area. Based on the pre-defined human and vehicle detection switching control method and corresponding switching threshold, the current mode is switched to either human detection mode or vehicle detection mode. In each mode, the theft detection parameters for each theft target detection area are set independently. The theft detection parameters corresponding to the current mode are read from the theft detection parameters of each theft target detection area and fused with the theft target type parameters of that area to obtain fused detection parameters. Based on the fused detection parameters, it is determined whether an unauthorized movement detection event of the stolen object has occurred in the images captured by the cameras in each theft target detection area.
[0068] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.
[0069] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.
[0070] Since the instructions stored in the storage medium can execute the steps in any of the factory theft detection methods provided in the embodiments of this application, the beneficial effects that any of the factory theft detection methods provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.
[0071] The foregoing has provided a detailed description of a factory theft detection method, apparatus, electronic device, and storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A method for detecting objects stolen from factories, characterized in that, include: At least two theft target detection areas are pre-defined within the range captured by the factory camera, and corresponding theft target type parameters are configured for each theft target detection area; Based on the preset human and vehicle detection switching control method and the corresponding switching threshold, the current mode is switched to human detection mode or vehicle detection mode. In each mode, the theft detection parameters of each theft target detection area are set separately. Read the theft detection parameters corresponding to the current mode from the theft detection parameters of each theft target detection area, and fuse them with the theft target type parameters of that area to obtain the fused detection parameters; Based on the fused detection parameters, determine whether the images captured by the cameras in each theft target detection area have shown an unauthorized movement detection event of the theft target.
2. The factory theft detection method according to claim 1, characterized in that, The theft detection parameters include movement duration parameters, movement displacement threshold parameters, and target contour matching degree parameters. In the step of determining whether an unauthorized movement detection event of a theft object has occurred in the images captured by the camera in each theft target detection area, if the target in the detection area meets any of the following conditions: the movement duration exceeds the movement duration parameter, the movement displacement reaches the movement displacement threshold parameter, or the matching degree between the target contour and the corresponding theft target type parameter reaches the target contour matching degree parameter, and no authorized movement identifier is detected, then it is determined that there is an unauthorized movement detection event of a theft object.
3. The factory theft detection method according to claim 1, characterized in that, The human and vehicle detection switching control method includes a timed switching method; When the human and vehicle detection switching control mode is a timed switching mode, the step of switching the current mode to human detection mode or vehicle detection mode includes the following sub-steps: Compare the current time with the preset switching threshold. If the current time reaches the preset first switching threshold, then switch to human detection mode; If the current time reaches the preset second switching threshold, then switch to vehicle detection mode.
4. The factory theft detection method according to claim 3, characterized in that, The vehicle and pedestrian detection switching control method includes an automatic switching mode; When the human and vehicle detection switching control mode is automatic switching mode, the step of switching the current mode to human detection mode or vehicle detection mode includes the following sub-steps: The system compares the proportion of people and vehicles in the current captured image with a preset switching threshold, and also incorporates real-time signals from factory access control and gate systems for further analysis. If the proportion of human features in the current image is higher than the preset third switching threshold, and there is no vehicle passage signal at the access control / gate, then switch to human detection mode; If the proportion of vehicle features in the current image is higher than the preset third switching threshold, or if there is a vehicle passage signal at the access control / gate, then switch to vehicle detection mode.
5. The factory theft detection method according to claim 4, characterized in that, Before the step of switching the current mode to human detection mode or vehicle detection mode according to the preset human and vehicle detection switching control method and the corresponding switching threshold, the following steps are also included: The pedestrian and vehicle detection switching control mode is set, which includes the timed switching mode, the automatic switching mode, and the default mode; When the human and vehicle detection switching control mode is in the default mode, the human and vehicle detection switching function is turned off, and the same set of theft detection parameters is used by default for both human and vehicle.
6. The factory theft detection method according to claim 4, characterized in that, In the sub-step of comparing the proportion of human and vehicle features in the currently captured image with a preset switching threshold, Regarding the proportion of human features, these human features are identified and statistically analyzed through human body contour features and gait features. Regarding the proportion of vehicle features, these features are identified and statistically analyzed through vehicle model features and license plate features, and verified by combining them with RFID vehicle identification signals from the factory area.
7. The factory theft detection and processing method according to any one of claims 1 to 6, characterized in that, After determining whether an unauthorized movement detection event of the theft target has occurred in the images captured by the cameras in each theft target detection area based on the fused detection parameters, the method further includes: The steps for handling theft detection in cases of unauthorized movement of stolen objects.
8. A factory theft detection device, characterized in that, include: The configuration module is used to pre-set at least two theft target detection areas within the range captured by the factory camera, and to configure corresponding theft target type parameters for each theft target detection area; The switching module is used to switch the current mode to either human detection mode or vehicle detection mode according to the preset human and vehicle detection switching control mode and the corresponding switching threshold. In each mode, the theft detection parameters of each theft target detection area are set separately. The reading module is used to read the theft detection parameters corresponding to the current mode from the theft detection parameters of each theft target detection area, and fuse them with the theft target type parameters of the area to obtain the fused detection parameters; The judgment module is used to determine, based on the fused detection parameters, whether the images captured by the cameras in each theft target detection area have shown an unauthorized movement detection event of the theft object.
9. An electronic device, characterized in that, include: A memory, a processor, and a processor program stored in the memory and executable on the processor, wherein the processor executes the program as steps of the factory theft detection method as described in any one of claims 1 to 7.
10. A storage medium, characterized in that, The computer processing program is stored and can be loaded by a processor to execute the factory theft detection method as described in any one of claims 1 to 7.