Rail transit abnormality analysis system false alarm elimination method and device, and medium

Abstract

The present application relates to a kind of track traffic anomaly analysis system false alarm elimination method, device and medium, comprising: in the detection area demarcated, image is subjected to foreground detection, obtain the moving target existing in image;Moving target is subjected to image illumination algorithm detection and linear programming algorithm detection, confirm whether moving target is interference;After removing interference, moving target is detected by target detection algorithm and is determined whether it is intruding foreign matter, such as intruding foreign matter is determined, then alarm is carried out.The present application can effectively assist disaster detection system to carry out accurate abnormal condition detection by analyzing real-time video stream along railway, based on image illumination and linear programming and combining the railway all-weather multi-class interference detection method of deep learning target detection, and identifies the real railway intruding foreign matter.

Description

Technical Field

[0001] This invention relates to a method, device, and medium for eliminating false alarms in a rail transit anomaly analysis system, and relates to the application of computer vision in rail transit disaster prevention scenarios. Background Technology

[0002] In modern rail transit systems, safety and reliability are paramount. With the application of computer vision technology in the rail transit field, it can be used for railway disaster prevention detection and early warning, effectively reducing labor costs and significantly improving efficiency and accuracy.

[0003] A normal and effective disaster prevention alarm system should trigger an alarm when intrusive objects, such as rocks, people, or mudslides, are detected in the video feed of the railway or its vicinity. However, in the complex and harsh environmental conditions along railway lines, detection systems often mistakenly identify moving objects in the video feed (such as flying insects, raindrops, snowflakes, time-lapse characters in the video feed, or trains appearing at night) as intrusive objects, leading to frequent false alarms. False alarms not only waste resources but may also threaten the reliability and security of the system.

[0004] Due to the influence of various types of interference in the complex environment along railway lines, there is currently a lack of effective interference elimination algorithms and mechanisms for various interferences that occur in and around railways in the rail transit field. Summary of the Invention

[0005] The present invention aims to at least solve one of the technical problems existing in the prior art. Therefore, in response to the above-mentioned problem, the object of the present invention is to provide a method, apparatus, and medium for eliminating false alarms in a rail transit anomaly analysis system that can effectively eliminate false alarms caused by abnormal interference.

[0006] In a first aspect, the present invention provides a method for eliminating false alarms in a rail transit anomaly analysis system, comprising:

[0007] Within the defined detection area, the image undergoes foreground detection to identify moving targets within the image;

[0008] The moving target is detected using image illumination algorithm and linear programming algorithm to confirm whether the moving target is a disturbance.

[0009] After removing interference, the moving target is detected by a target detection algorithm to determine whether it is an intrusive foreign object. If it is determined to be an intrusive foreign object, an alarm is issued.

[0010] Furthermore, within the defined detection area, the image undergoes foreground detection to obtain moving targets present in the image, including:

[0011] A data stream of continuous image frames is captured using video acquisition equipment along the railway line;

[0012] A detection area is defined around the railway line in each frame of the image;

[0013] Within the detection time period m, foreground algorithm detection is performed on each frame of the image within the defined detection area, and the coordinates of all detected moving targets are accumulated and stored.

[0014] Furthermore, the moving target is detected using image illumination algorithm and linear programming algorithm to confirm whether the moving target is a disturbance, including:

[0015] The acquired moving target is detected using an image illumination algorithm to determine whether it is the first interference object, which is a nighttime train.

[0016] The acquired moving targets are detected using a linear programming algorithm to determine if there is a second interfering object, which could be characters, rain, snow, or flying insects.

[0017] Furthermore, the acquired moving targets are subjected to image illumination algorithm detection to confirm whether it is a nighttime train, including:

[0018] When an image frame containing a moving target is detected, if the area of ​​the selected moving target occupies a proportion of the entire image that reaches a set value k, and the average brightness L of the entire image... avg Within range [L] min ,L max If a moving target is identified as a night train within a given frame, it is considered to have appeared once. If the cumulative number of valid night train appearances in consecutive image frames reaches n, then the moving target is considered to be a night train and should be excluded as the first interference.

[0019] Furthermore, the average brightness L of the entire image avg The calculation formula is:

[0020]

[0021] Among them, w i h i w represents the width and height of the detected moving target i, respectively. p h p B represents the width and height of the image frame, respectively; ij G ij R ij These represent the blue channel value, green channel value, and red channel value of each pixel in the image frame, respectively.

[0022] Furthermore, the acquired moving targets are subjected to linear programming algorithm detection to confirm the presence of characters, rain / snow, or flying insects, including:

[0023] The presence of characters is determined by detecting the edge point coordinates of moving target point pairs: select the edge point coordinates in the four directions of up, down, left, and right of all moving target points and obtain their horizontal and vertical differences. If the horizontal and vertical differences are both less than the threshold q, then the characters are judged as the second interference and removed.

[0024] The cumulative coordinates of moving targets are fitted using a linear programming algorithm to obtain the loss function W. When the loss function is greater than the threshold e, the moving targets accumulated in each frame are considered to have no regularity and are identified as flying insects, rain, or snow as secondary interference and excluded.

[0025] Furthermore, the moving target after removing interference is detected by a target detection algorithm to determine whether it is an intrusive foreign object. If it is determined to be an intrusive foreign object, an alarm is issued, including:

[0026] Within the detection time period m, if the detected moving target still exists after the image illumination algorithm and linear programming algorithm have successively eliminated interference, the target detection algorithm will continue to be applied to the moving target. If the target detection algorithm detects a train, it will be eliminated as interference. Otherwise, if other moving targets are still identified by the target detection algorithm, this moving target will be alarmed as an intrusive foreign object.

[0027] Secondly, the present invention also provides a false alarm elimination device for a rail transit anomaly analysis system, comprising:

[0028] The moving target acquisition unit is configured to perform foreground detection on the image within a defined detection area to acquire the moving targets present in the image;

[0029] The interference detection unit is configured to perform image illumination algorithm detection and linear programming algorithm detection on the moving target to confirm whether the moving target is an interference.

[0030] The intrusion foreign object detection unit is configured to detect whether a moving target after removing interference is an intrusion foreign object through a target detection algorithm, and to issue an alarm if it is determined to be an intrusion foreign object.

[0031] Thirdly, the present invention also provides an electronic device, characterized in that it comprises: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for performing any of the methods.

[0032] Fourthly, the present invention also provides a computer-readable storage medium for storing one or more programs, said one or more programs including instructions that, when executed by a computing device, cause the computing device to perform any of the methods.

[0033] Because the present invention adopts the above technical solution, it has the following characteristics:

[0034] 1. This invention analyzes real-time video streams along railway lines and proposes an all-weather, multi-category interference detection method based on image illumination and linear programming combined with deep learning object detection. Even with object categories and samples that have not undergone extensive training, image illumination and linear programming can automatically identify and eliminate various types of false alarms by fully utilizing the traditional spatial and motion characteristics of the objects themselves. This can effectively assist disaster detection systems in accurately detecting abnormal situations and identifying genuine railway intrusions.

[0035] 2. In order to effectively identify various interference objects appearing in and around the railway in the video footage, this invention utilizes image analysis and pattern recognition technology to automatically identify and eliminate multiple types of false alarms, thereby reducing false alarms, improving the accuracy and availability of system detection, and ultimately enhancing the safety of the rail transit system.

[0036] In summary, this invention can be widely applied to the automatic identification and elimination of various types of false alarms in rail transit. Attached Figure Description

[0037] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts. In the drawings:

[0038] Figure 1 This is a flowchart of the anomaly analysis and detection process according to an embodiment of the present invention.

[0039] Figure 2 This is a schematic diagram of the electronic device structure of the present invention. Detailed Implementation

[0040] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0041] Although terms such as first, second, third, etc., may be used in this document to describe multiple elements, components, regions, layers, and / or segments, these elements, components, regions, layers, and / or segments should not be limited by these terms. These terms may be used only to distinguish one element, component, region, layer, or segment from another. Unless the context clearly indicates otherwise, terms such as "first," "second," and other numerical terms used herein do not imply order or sequence. Therefore, the first element, component, region, layer, or segment discussed below may be referred to as the second element, component, region, layer, or segment without departing from the teachings of the exemplary embodiments.

[0042] For ease of description, spatial relative terms may be used in the text to describe the relationship of one element or feature relative to another element or feature as shown in the figure. These relative terms include, for example, "inside," "outside," "middle," "outer," "below," "above," etc. Such spatial relative terms are intended to include different orientations of the device in use or operation, other than those depicted in the figure.

[0043] To compensate for and improve the false alarm elimination technology of rail transit anomaly analysis systems, this invention provides a method, device, and medium for eliminating false alarms in rail transit anomaly analysis systems. Based on image illumination and linear programming, combined with deep learning object detection, this method provides an all-weather, multi-category interference detection method along railway lines. Within a defined detection area, the image first undergoes foreground detection to check for moving targets. Multiple frames are accumulated over a detection period. If moving targets are found, they are sequentially fed into an image illumination algorithm, a linear programming algorithm, and a target detection algorithm to eliminate interference, thereby identifying normal intrusions along the railway line. Therefore, this invention proposes an all-weather, multi-category interference detection method along railway lines based on image illumination and linear programming combined with deep learning object detection. Even with object categories and samples that have not undergone extensive training, by fully utilizing the traditional spatial and motion characteristics of the objects themselves, it can automatically identify and eliminate multiple categories of false anomaly alarms. This effectively assists disaster detection systems in accurately detecting anomalies, identifying genuine railway intrusions, reducing false alarms, and improving the accuracy and usability of the system.

[0044] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the invention and to fully convey the scope of the invention to those skilled in the art.

[0045] Example 1: As Figure 1 As shown in this embodiment, the method for eliminating false alarms in a rail transit anomaly analysis system includes:

[0046] S1. Within the defined detection area, the acquired image undergoes foreground detection to determine whether a moving target exists in the image.

[0047] In this embodiment, the above process includes:

[0048] S11. A data stream of continuous image frames is captured along the railway line using cameras or other video acquisition devices. The continuous image frames can be obtained through encoding and decoding.

[0049] S12, and delineate the detection zone around the railway line in each frame of image.

[0050] In this embodiment, the detection zone can be defined by manually drawing multiple points from the start point to the end point using code before each video segment is detected. These points are then automatically connected to form a polygonal image detection area, such as a rectangular detection area. The detection zone can be defined as needed, but is not limited to this example.

[0051] S13. Within a detection time period m, perform foreground algorithm detection on each frame of the data stream and accumulate and store the coordinates of all detected moving targets.

[0052] S2. Perform image illumination algorithm detection on the acquired moving target to confirm whether it is a nighttime train.

[0053] In this embodiment, within an image frame where a moving target is detected, if the area of ​​the selected moving target occupies a proportion of the entire image that reaches k, as shown in Equation (1)1, and the average brightness L of the entire image... avg Within range [L] min ,L max Within a given frame, as shown in equation (2), a valid night train is considered to have appeared once. When the cumulative number of valid night train appearances in consecutive image frames reaches n, the moving target is considered to be a night train and should be excluded as interference. The brightness range of the night train lights can be obtained through statistical testing.

[0054]

[0055]

[0056] Among them, w i h i w represents the width and height of the detected moving target i, respectively. p h p B represents the width and height of the image frame, respectively; ij G ij R ij These represent the blue channel value, green channel value, and red channel value of each pixel in the image frame, respectively.

[0057] S3. Perform linear programming algorithm detection on the acquired moving targets to confirm the presence of characters and interference.

[0058] In this embodiment, the acquired moving target is detected using a linear programming algorithm to confirm the presence of characters and interference, including:

[0059] S31. Determine the presence of characters by detecting the edge point coordinates of moving target point pairs.

[0060] In this embodiment, the video recorded by the camera typically contains character information such as the date and time in positions such as the lower right corner of the screen, and these characters change frequently. To avoid false alarms caused by the algorithm misidentifying the date and time characters as moving targets when no other moving targets are detected in the frame, it is necessary to effectively remove these characters to reduce resource consumption and improve the running speed of the hardware and algorithm.

[0061] This embodiment selects the coordinates of edge points in the four directions (up, down, left, and right) of all moving target points and obtains their horizontal and vertical differences. If both the horizontal and vertical differences are less than a threshold q, it is determined that the information is character information and needs to be removed.

[0062] x right -x left <q (3)

[0063] y top -y bottom <q (4)

[0064] Where, x right x left These are the x-coordinates of the rightmost and leftmost points among all moving target points; y-coordinates of the leftmost points. top y bottom These are the y-coordinates of the uppermost and lowermost points among all moving target points.

[0065] S32. The cumulative coordinates of the moving target are fitted and calculated using a linear programming algorithm to eliminate interference from flying insects, rain, snow, and other objects.

[0066] In this embodiment, the video recorded along the railway line sometimes contains interfering objects such as flying insects, raindrops, and snowflakes. These interfering objects may appear randomly and disorderly in various positions of the frame, and are relatively small in size. The accumulated target points (x) of each frame are then... i ,y i The loss function W for linear programming is obtained through formulas (5)-(7). This loss function is used to measure the fitting quality of the linear regression model. The smaller the value, the better the model fits the data, the more regular it is, and the more likely it is to be an intrusive foreign object along the railway line. When the loss function is greater than the threshold e, it is considered that the moving targets accumulated in each frame of the image are irregular and may be interference objects such as flying insects, rain, snow, etc., which can be excluded.

[0067]

[0068]

[0069]

[0070] Among them, a box and b box These are the slope and intercept of the straight line fitted based on the cumulative target points in each frame, respectively, where y is y i The average value is n, where n is the cumulative number of moving targets in each frame.

[0071] S4. The moving target, excluding interference, is detected by the target detection algorithm to determine whether it is an intrusive foreign object. If it is determined to be an intrusive foreign object, an alarm is issued.

[0072] In this embodiment, within the detection time period m, if a detected moving target still exists after sequentially passing the image illumination algorithm and linear programming algorithm to eliminate interference, the target detection algorithm continues to be applied to the existing moving targets. If the target detection algorithm detects a train, it is excluded as interference; otherwise, if other moving targets, such as pedestrians, rocks, or mudslides, are still identified by the target detection algorithm, an alarm is triggered as if they were intrusive foreign objects.

[0073] Example 2: Following the method for eliminating false alarms in a rail transit anomaly analysis system provided in Example 1, this example provides a device for eliminating false alarms in a rail transit anomaly analysis system. The device provided in this example can implement the method for eliminating false alarms in a rail transit anomaly analysis system as described in Example 1. This device can be implemented through software, hardware, or a combination of both. For ease of description, this example is described by dividing the system into various functional units. Of course, in implementation, the functions of each unit can be implemented in one or more software and / or hardware components. For example, the device may include integrated or separate functional modules or units to execute the corresponding steps in the methods of Example 1. Since the device in this example is basically similar to the method example, the description process of this example is relatively simple. For relevant details, please refer to the description in Example 1. The example of the device for eliminating false alarms in a rail transit anomaly analysis system provided by this invention is merely illustrative.

[0074] Specifically, this embodiment also provides a false alarm cancellation device for a rail transit anomaly analysis system, comprising:

[0075] The moving target acquisition unit is configured to perform foreground detection on the image within a defined detection area to acquire the moving targets present in the image;

[0076] The interference detection unit is configured to perform image illumination algorithm detection and linear programming algorithm detection on the moving target to confirm whether the moving target is an interference.

[0077] The intrusion foreign object detection unit is configured to detect whether a moving target after removing interference is an intrusion foreign object through a target detection algorithm, and to issue an alarm if it is determined to be an intrusion foreign object.

[0078] Example 3: This example provides an electronic device corresponding to the false alarm elimination method of the rail transit anomaly analysis system provided in Example 1. The electronic device can be an electronic device for the client, such as a mobile phone, laptop, tablet computer, desktop computer, etc., to execute the method of Example 1.

[0079] like Figure 2As shown, the electronic device includes a processor, memory, communication interface, and bus. The processor, memory, and communication interface are connected via the bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. The memory stores a computer program that can run on the processor. When the processor runs the computer program, it executes the method of Embodiment 1. The implementation principle and technical effects are similar to those of Embodiment 1, and will not be repeated here. Those skilled in the art will understand that... Figure 2 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computing device on which the present application is applied. The specific computing device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0080] In a preferred embodiment, the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), and optical discs.

[0081] In a preferred embodiment, the processor can be any type of general-purpose processor such as a central processing unit (CPU) or a digital signal processor (DSP), and is not limited thereto.

[0082] Example 4: This example provides a computer program product. The computer program product may include a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by the computer, the computer can execute the method provided in Example 1 above. Its implementation principle and technical effects are similar to those in Example 1, and will not be repeated here.

[0083] In a preferred embodiment, the computer-readable storage medium may be a tangible device for holding and storing instructions used by an instruction execution device, such as, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. The computer-readable storage medium stores computer program instructions that cause a computer to perform the method provided in Embodiment 1 above.

[0084] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In the description of this specification, the terms "a preferred embodiment," "furthermore," "specifically," "in this embodiment," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments in this specification. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0085] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0086] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0087] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for eliminating false alarms in a rail transit anomaly analysis system, characterized in that, include: Within the defined detection area, the image undergoes foreground detection to identify moving targets within the image; The moving target is detected using image illumination algorithm and linear programming algorithm to confirm whether the moving target is a disturbance. After removing interference, the moving target is detected by a target detection algorithm to determine whether it is an intrusive foreign object. If it is determined to be an intrusive foreign object, an alarm is triggered. The moving target is detected using image illumination algorithm and linear programming algorithm to confirm whether it is a disturbance. This includes: detecting the acquired moving target using image illumination algorithm to confirm whether it is a first disturbance, which is a night train; and detecting the acquired moving target using linear programming algorithm to confirm whether there is a second disturbance, which is characters, rain or snow, or flying insects. The acquired moving targets are detected using an image illumination algorithm to determine if it is a nighttime train. This includes: when an image frame with a moving target is detected, if the area of ​​the selected moving target occupies a proportion of the entire image that reaches a set value... k And the average brightness of the entire image L avg Within range [ L min , L max Within a given frame, one valid night train is considered to have occurred. The number of valid night train occurrences accumulated across consecutive image frames reaches a certain threshold. n If the target is a night train, it should be excluded as the first disturbance. The acquired moving targets are detected using a linear programming algorithm to confirm the presence of characters, rain / snow, or flying insects. This includes: determining the presence of characters by detecting the edge point coordinates of moving target point pairs; selecting the edge point coordinates in the four directions (up, down, left, and right) of all moving target points and obtaining their horizontal and vertical differences; if both the horizontal and vertical differences are less than a threshold... q If the character is identified as a second interference, it is removed. The cumulative coordinates of the moving target are then fitted using a linear programming algorithm to calculate the loss function of the linear programming algorithm. W When the loss function is greater than the threshold e If the accumulated moving targets in each frame are not regular, then flying insects and rain / snow are identified as secondary interference objects and excluded.

2. The method for eliminating false alarms in a rail transit anomaly analysis system according to claim 1, characterized in that, Within the defined detection area, the image undergoes foreground detection to identify moving targets present in the image, including: A data stream of continuous image frames is captured using video acquisition equipment along the railway line; A detection area is defined around the railway line in each frame of the image; During the detection period m Within the defined detection area, foreground detection algorithms are used to detect each frame of the image, and the coordinates of all detected moving targets are accumulated and stored.

3. The method for eliminating false alarms in a rail transit anomaly analysis system according to claim 1, characterized in that, Average brightness of the entire image L avg The calculation formula is: ； Among them, w i h i These represent the detected moving targets. i Width and height, w p h p B represents the width and height of the image frame, respectively; ij G ij R ij These represent the blue channel value, green channel value, and red channel value of each pixel in the image frame, respectively.

4. The method for eliminating false alarms in a rail transit anomaly analysis system according to claim 1, characterized in that, After removing interference, the moving target is detected by a target detection algorithm to determine whether it is an intrusive foreign object. If it is determined to be an intrusive foreign object, an alarm is triggered, including: During the detection period m If the detected moving target still exists after the image illumination algorithm and linear programming algorithm have successively eliminated interference, the target detection algorithm will continue to be applied to the moving target. If the target detection algorithm detects a train, it will be eliminated as interference. Otherwise, if other moving targets are still identified by the target detection algorithm, this moving target will be alarmed as an intrusive foreign object.

5. A false alarm elimination device for a rail transit anomaly analysis system for implementing the false alarm elimination method of any one of claims 1 to 4, characterized in that, include: The moving target acquisition unit is configured to perform foreground detection on the image within a defined detection area to acquire the moving targets present in the image; The interference detection unit is configured to perform image illumination algorithm detection and linear programming algorithm detection on the moving target to confirm whether the moving target is an interference. The intrusion foreign object detection unit is configured to detect whether a moving target after removing interference is an intrusion foreign object through a target detection algorithm, and to issue an alarm if it is determined to be an intrusion foreign object.

6. An electronic device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the methods described in claims 1 to 4.

7. A computer-readable storage medium for storing one or more programs, characterized in that, The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any of the methods described in claims 1 to 4.

Images