Railway perimeter disaster protection method and system, processing equipment and storage medium

Abstract

The invention relates to a railway perimeter disaster protection method and system, a processing device and a storage medium, and the method is characterized in that the method comprises the steps: obtaining a video stream of continuous image frames along a railway; defining a detection defense area along the railway; within a preset detection time period, detecting coordinate points of all moving targets in the corresponding detection defense area in each frame of image of the video stream by adopting a foreground and background detection algorithm; a target detection method is adopted, target detection is carried out on all moving targets obtained through foreground and background detection, interferents are eliminated, a target detection result is output, and other recognized moving targets serve as invasion foreign matters to give an alarm; when the target detection method recognizes the invading foreign matter, existence detection, other foreign matter detection and driving safety detection are conducted on the invading foreign matter recognized according to the target detection result through the image-text large model, the target detection result is output or an alarm is given according to the detection result, and the method can be widely applied to the field of rail transit perimeter disaster protection.

Description

Technical Field

[0001] The present invention relates to the field of rail transit perimeter disaster protection, and in particular to a railway perimeter disaster protection method, system, processing equipment and storage medium. Background Art

[0002] In modern rail transit systems, safety and reliability are of vital importance. With the application of computer vision technology in the field of rail transit, railway disaster prevention detection and early warning can be carried out, effectively reducing labor costs and significantly improving utilization efficiency and accuracy. A normal and effective disaster prevention alarm system should sound an alarm when intrusive foreign objects such as stones, people, mudslides, etc. appear on the railway and its vicinity in the video screen.

[0003] However, under the complex and harsh environmental conditions along the railway, the detection system often misidentifies moving interference objects detected in the video (such as flying insects, raindrops, snowflakes, jumping time characters in the video, trains appearing at night, etc.) as intrusions and issues alarms, resulting in frequent false alarms. False alarms not only consume resources, but may also threaten the reliability and security of the system. Summary of the invention

[0004] In view of the above problems, the object of the present invention is to provide a railway perimeter disaster protection method, system, processing equipment and storage medium that can effectively identify various interference objects appearing on the railway and its vicinity in the video picture.

[0005] To achieve the above objectives, the present invention adopts the following technical solutions: In a first aspect, a method for protecting railway perimeter disasters is provided, comprising: Acquire a video stream of continuous image frames along the railway line; Designate detection and defense zones along the railway; In a pre-set detection time period, the foreground and background detection algorithm is used to detect the coordinate points of all moving targets in the corresponding detection zone in each frame of the video stream; Adopting the target detection method, all moving targets detected by the foreground background are detected, interference objects are eliminated, the target detection results are output, and other moving targets identified are alarmed as intrusion foreign objects; When the target detection method identifies an intruding foreign object, the large graphic model is used to perform existence detection, other foreign object detection and driving safety detection on the intruding foreign object identified by the target detection result, and output the target detection result or issue an alarm based on the detection result.

[0006] Furthermore, the video stream of the continuous image frames is acquired through encoding and decoding using a camera or other video acquisition equipment.

[0007] Furthermore, the method of detecting the coordinate points of all moving targets in each frame of the video stream by using a foreground-background detection algorithm within a preset detection time period also includes: The coordinate points of all detected moving targets are accumulated and stored.

[0008] Furthermore, when the target detection method identifies an intruding foreign object, the image-text model is used to perform existence detection, other foreign object detection and driving safety detection on the intruding foreign object identified by the target detection result, and the target detection result is output or an alarm is issued according to the detection result, including: When the target detection method identifies an intruding foreign object, an image of a preset size around the intruding foreign object is cut out from the frame image and input into the large image model; The large model of graphics and text performs existence detection based on the target detection results and reviews the intruding foreign objects. If there are intruding foreign objects, the review is completed and the target detection results are output; If no intruding foreign matter is detected, the large model of the graphic will detect other foreign matter. If no other foreign matter is found, the detection ends. If other foreign objects are detected, the large graphic model will conduct a driving safety check. If it is detected that driving safety is affected, an alarm will be issued; if it is detected that there is no impact on driving safety, the test will end.

[0009] Furthermore, the image-text model performs existence detection based on the target detection result, and verifies the intruding foreign matter. If the intruding foreign matter exists, the verification is completed and the target detection result is output, including: The existence detection of the large graphic model asks the question "There is a () object at the () position, does it exist?" If the answer is yes, the review is completed, it is identified as a normal intrusion, and the target detection result is output; if the answer is no, it enters other foreign body detection.

[0010] Furthermore, if the detection shows that there is no intruding foreign body, the large model of the graphic and text performs other foreign body detection. If there is no other foreign body, the detection ends, including: The other foreign object detection of the large graphic model asks the question "Are there other foreign objects on the rails?" If the answer is yes, the vehicle safety detection will begin; if the answer is no, the detection ends.

[0011] Furthermore, if other foreign objects are detected, the large graphic model performs a driving safety test. If it is detected that driving safety is affected, an alarm is issued; if it is detected that driving safety is not affected, the test ends, including: The driving safety test of the large graphic model asks the question "Does it affect driving safety?" If the answer is yes, an alarm is issued; if the answer is no, the test ends.

[0012] In a second aspect, a railway perimeter disaster protection system is provided, comprising: A data acquisition module, used to acquire a video stream of continuous image frames along the railway; The area demarcation module is used to define detection and defense areas along the railway; The foreground and background detection module is used to detect the coordinate points of all moving targets in the detection zone corresponding to each frame of the video stream using the foreground and background detection algorithm within a pre-set detection time period; The target detection module is used to detect all moving targets detected by the foreground background using the target detection method, exclude interference objects, output the target detection results, and alarm other identified moving targets as intrusion foreign objects; The review module is used to use a large graphic model to perform existence detection, other foreign object detection and driving safety detection on the intruding foreign object identified by the target detection result when the target detection method identifies an intruding foreign object, and output the target detection result or issue an alarm based on the detection result.

[0013] According to a third aspect, a processing device is provided, comprising computer program instructions, wherein the computer program instructions, when executed by the processing device, are used to implement the steps corresponding to the above-mentioned railway perimeter disaster protection method.

[0014] In a fourth aspect, a computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions, when executed by a processor, are used to implement steps corresponding to the above-mentioned railway perimeter disaster protection method.

[0015] Since the present invention adopts the above technical scheme, it has the following advantages: the present invention combines the analysis of real-time video streams along the railway, based on foreground and background detection and deep learning target detection, and a railway perimeter disaster protection detection method for large model image detection. Even if it is an untrained object category and sample, by utilizing the characteristics of large model open detection, it can automatically identify unknown objects and exclude various categories of false abnormal alarms, and can effectively assist the disaster detection system to perform accurate abnormal situation detection and identify real railway intrusion foreign objects, so as to reduce the generation of false alarms, improve the accuracy and availability of system detection, and improve the safety of rail transit systems. In summary, the present invention can be widely used in the field of rail transit perimeter disaster protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Throughout the accompanying drawings, the same reference numerals are used to represent the same components. In the accompanying drawings: Figure 1 It is a schematic diagram of a method flow provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0018] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0019] Although the terms first, second, third, etc. can be used in the text to describe multiple elements, components, regions, layers and / or sections, these elements, components, regions, layers and / or sections should not be limited by these terms. These terms can only be used to distinguish an element, component, region, layer or section from another region, layer or section. Unless the context clearly indicates, terms such as "first", "second" and other numerical terms do not imply order or sequence when used in the text. Therefore, the first element, component, region, layer or section discussed below can be referred to as the second element, component, region, layer or section without departing from the teaching of the example embodiments.

[0020] Under the complex and harsh environmental conditions along the railway, the detection system often misidentifies moving interference objects detected in the video (such as flying insects, raindrops, snowflakes, jumping time characters in the video, trains appearing at night, etc.) as intrusive foreign objects and issues alarms, resulting in frequent false alarms. False alarms not only consume resources, but may also pose a threat to the reliability and security of the system. Therefore, affected by the various types of interference objects in the complex environment along the railway, there is currently a lack of effective interference object exclusion algorithms and mechanisms for various interference objects that appear on railways and their vicinity in the field of rail transit. The present embodiment provides a method for protecting the perimeter of a railway from disasters, including: acquiring a video stream of continuous image frames along the railway; defining a detection zone along the railway; within a pre-set detection time period, using a foreground and background detection algorithm to detect the coordinate points of all moving targets in the corresponding detection zone in each frame of the video stream; using a target detection method to perform target detection on all moving targets obtained by the foreground and background detection, exclude interference, output target detection results, and alarm other identified moving targets as intrusive foreign objects; when the target detection method identifies an intrusive foreign object, using a large graphic model to perform existence detection, other foreign object detection, and driving safety detection on the intrusive foreign object identified by the target detection result, and output the target detection result or alarm according to the detection result. The present invention proposes an all-weather multi-category interference object detection method along the railway based on foreground and background detection and target detection, combined with a graphic and text large model thinking chain. Even for untrained object categories and samples, by fully mobilizing the open detection capabilities of the large model, it is possible to automatically identify and eliminate various categories of false abnormal alarms, effectively assist the disaster detection system in accurate abnormal situation detection, identify real railway intrusion foreign objects, reduce the generation of false alarms, and improve the accuracy and availability of system detection.

[0021] Example 1 like Figure 1 As shown, this embodiment provides a railway perimeter disaster protection method, comprising the following steps: 1) Use cameras or other video acquisition devices along the railway to obtain a video stream of continuous image frames through encoding and decoding.

[0022] 2) Designate detection and defense zones along the railway line.

[0023] 3) Within a pre-set detection time period m, the foreground and background detection algorithm is used to detect the coordinate points of all moving targets in the corresponding detection zone in each frame of the video stream, and the coordinate points of all detected moving targets are accumulated and stored.

[0024] 4) Within the detection time period m, the target detection method is used to perform target detection on all moving targets detected by the foreground background, eliminate interference, output the target detection results, and warn other identified moving targets such as pedestrians, stones, mudslides, etc. as intrusive foreign objects.

[0025] 5) When the target detection method identifies an intruding foreign object, the image and text model is used to perform existence detection, other foreign object detection and driving safety detection on the intruding foreign object identified by the target detection result, and output the target detection result or issue an alarm based on the detection result, specifically: 5.1) When the target detection method identifies an intruding foreign object, a 336*336 image around the intruding foreign object is cut out from the frame image and input into the large graphic model so that the specified operation can be performed according to the input prompt word.

[0026] 5.2) The large graphic model performs existence detection based on the target detection results and verifies the intruding foreign objects. If there are intruding foreign objects, the verification is completed and the target detection results are output; if there are no intruding foreign objects, it goes to step 5.3).

[0027] Specifically, the existence detection of the large graphic model asks the question "There is a () object at the () position, does it exist?" If the answer is yes, the review is completed, it is identified as a normal intrusion, and the target detection result is output; if the answer is no, it goes to step 5.3), where the existence detection includes detecting normal intrusions as well as intrusions such as people, stones, and mudslides.

[0028] 5.3) The large model of images and texts performs other foreign body detection based on the results of the existence detection. If other foreign bodies are detected, it proceeds to step 5.4); if no other foreign bodies are present, the detection ends.

[0029] Specifically, the other foreign object detection of the large graphic model asks the question "Are there other foreign objects on the rails, such as gravel, animals or mosquitoes?" If the answer is yes, then go to step 5.4); if the answer is no, then the detection ends, that is, the result of the target detection is a misjudgment, and there is actually no invading foreign object, so there is no need to alarm.

[0030] 5.4) The large graphic model performs a driving safety test based on the results of other foreign object detections. If it is detected that driving safety is affected, an alarm is issued; if it is detected that driving safety is not affected, the test ends.

[0031] Specifically, the driving safety detection of the large graphic model asks the question "Does it affect driving safety?" If the answer is yes, an alarm is issued; if the answer is no, the detection ends.

[0032] The present invention is based on the foreground detection algorithm and the target detection method, and combines the image-text model thinking chain. In the designated detection zone, the image first undergoes foreground detection to detect whether there is a moving target. In a detection period, multiple frames of images are accumulated. If there is a moving target, it is passed to the target detection algorithm to eliminate interference, and then identify normal intrusions along the railway, such as pedestrians, stones, mudslides, etc.

[0033] Example 2 This embodiment provides a railway perimeter disaster protection system, including: The data acquisition module is used to acquire a video stream of continuous image frames along the railway.

[0034] The area demarcation module is used to define detection and defense zones around the railway line.

[0035] The foreground and background detection module is used to detect the coordinate points of all moving targets in the corresponding detection zone in each frame image of the video stream using the foreground and background detection algorithm within a pre-set detection time period.

[0036] The target detection module is used to use the target detection method to perform target detection on all moving targets detected by the foreground background, eliminate interference, output the target detection results, and alarm other identified moving targets as intrusion foreign objects.

[0037] The review module is used to use a large graphic model to perform existence detection, other foreign object detection and driving safety detection on the intruding foreign object identified by the target detection result when the target detection method identifies an intruding foreign object, and output the target detection result or issue an alarm based on the detection result.

[0038] The system provided in this embodiment is used to execute the above-mentioned method embodiments. Please refer to the above-mentioned embodiments for specific processes and detailed contents, which will not be repeated here.

[0039] Example 3 This embodiment provides a processing device corresponding to the railway perimeter disaster protection method provided in Embodiment 1. The processing device can be applicable to a client processing device, such as a mobile phone, a laptop computer, a tablet computer, a desktop computer, etc., to execute the method of Embodiment 1.

[0040] The processing device includes a processor, a memory, a communication interface and a bus, and the processor, the memory and the communication interface are connected through the bus to complete mutual communication. The memory stores a computer program that can be run on the processing device, and the processing device executes the railway perimeter disaster protection method provided in this embodiment 1 when running the computer program.

[0041] In some implementations, the memory may be a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage.

[0042] In some other implementations, the processor may be a central processing unit (CPU), a digital signal processor (DSP), or other general-purpose processors of various types, which are not limited herein.

[0043] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0044] Those skilled in the art will understand that the structure of the above-mentioned computing device is only a partial structure related to the solution of the present invention, and does not constitute a limitation on the computing device to which the solution of the present invention is applied. The specific computing device may include more or fewer components, or combine certain components, or have a different arrangement of components.

[0045] Example 4 This embodiment provides a computer program product corresponding to the railway perimeter disaster protection method provided in Example 1. The computer program product may include a computer-readable storage medium on which computer-readable program instructions for executing the railway perimeter disaster protection method described in Example 1 are loaded.

[0046] Computer readable storage media can be tangible devices that hold and store instructions used by instruction execution devices. Computer readable storage media can be, for example, but not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any combination thereof.

[0047] The above embodiment provides a computer-readable storage medium, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0048] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0049] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0050] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0051] The above embodiments are only used to illustrate the present invention, wherein the structure, connection mode and manufacturing process of each component may be changed. Any equivalent transformations and improvements based on the technical solution of the present invention should not be excluded from the protection scope of the present invention.

Claims

1. A railway perimeter disaster protection method, characterized in that: include: Acquire a video stream of continuous image frames along the railway line; Designate detection and defense zones along the railway; In a pre-set detection time period, the foreground and background detection algorithm is used to detect the coordinate points of all moving targets in the corresponding detection zone in each frame of the video stream; Adopting the target detection method, all moving targets detected by the foreground background are detected, interference objects are eliminated, the target detection results are output, and other moving targets identified are alarmed as intrusion foreign objects; When the target detection method identifies an intruding foreign object, the large graphic model is used to perform existence detection, other foreign object detection and driving safety detection on the intruding foreign object identified by the target detection result, and output the target detection result or issue an alarm based on the detection result.

2. A railway perimeter disaster protection method as claimed in claim 1, characterized in that: The video stream of the continuous image frames is acquired through encoding and decoding using a camera or other video acquisition equipment.

3. A railway perimeter disaster protection method as claimed in claim 1, characterized in that: The method of detecting the coordinate points of all moving targets in each frame of the video stream by using a foreground-background detection algorithm within a preset detection time period also includes: The coordinate points of all detected moving targets are accumulated and stored.

4. A railway perimeter disaster protection method as claimed in claim 1, characterized in that: When the target detection method identifies an intruding foreign object, the image-text model is used to perform existence detection, other foreign object detection and driving safety detection on the intruding foreign object identified by the target detection result, and the target detection result is output or an alarm is issued according to the detection result, including: When the target detection method identifies an intruding foreign object, an image of a preset size around the intruding foreign object is cut out from the frame image and input into the large image model; The large model of graphics and text performs existence detection based on the target detection results and reviews the intruding foreign objects. If there are intruding foreign objects, the review is completed and the target detection results are output; If no intruding foreign matter is detected, the large model of the graphic will detect other foreign matter. If no other foreign matter is found, the detection ends. If other foreign objects are detected, the large graphic model will conduct a driving safety check. If it is detected that driving safety is affected, an alarm will be issued; if it is detected that there is no impact on driving safety, the test will end.

5. A railway perimeter disaster protection method as claimed in claim 4, characterized in that: The image and text model performs existence detection based on the target detection result and reviews the intruding foreign objects. If there are intruding foreign objects, the review is completed and the target detection result is output, including: The existence detection of the large model of graphics and text asks the question "There is a () object at the () position, does it exist?" If the answer is yes, the review is completed, it is identified as a normal intrusion, and the target detection result is output; if the answer is no, it enters other foreign body detection.

6. A railway perimeter disaster protection method as claimed in claim 4, characterized in that: If the detection shows that there is no intruding foreign body, the large model of the graphic will detect other foreign bodies. If there is no other foreign body, the detection ends, including: The other foreign object detection of the large graphic model asks the question "Are there other foreign objects on the rails?" If the answer is yes, the vehicle safety detection will begin; if the answer is no, the detection ends.

7. A railway perimeter disaster protection method as claimed in claim 4, characterized in that: If other foreign objects are detected, the large model will perform a driving safety test. If it is detected that driving safety is affected, an alarm will be issued; if it is detected that driving safety is not affected, the test ends, including: The driving safety test of the large graphic model asks the question "Does it affect driving safety?" If the answer is yes, an alarm is issued; if the answer is no, the test ends.

8. A railway perimeter disaster protection system, characterized in that: include: A data acquisition module, used to acquire a video stream of continuous image frames along the railway; The area demarcation module is used to define detection and defense areas along the railway; The foreground and background detection module is used to detect the coordinate points of all moving targets in the detection zone corresponding to each frame of the video stream using the foreground and background detection algorithm within a pre-set detection time period; The target detection module is used to detect all moving targets detected by the foreground background using the target detection method, exclude interference objects, output the target detection results, and alarm other identified moving targets as intrusion foreign objects; The review module is used to use a large graphic model to perform existence detection, other foreign object detection and driving safety detection on the intruding foreign object identified by the target detection result when the target detection method identifies an intruding foreign object, and output the target detection result or issue an alarm based on the detection result.

9. A processing device, characterized in that: It includes computer program instructions, wherein when the computer program instructions are executed by a processing device, they are used to implement the steps corresponding to the railway perimeter disaster protection method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, wherein the computer program instructions, when executed by a processor, are used to implement steps corresponding to the railway perimeter disaster protection method according to any one of claims 1 to 7.

Images