Subway door gap anti-pinch system and detection method thereof

Abstract

The application provides a subway door gap anti-pinch system and a detection method thereof. The system comprises a first image acquisition module, a second image acquisition module and a first linear light source, which are arranged in a gap between a train door and a platform screen door. The first image acquisition module and the second image acquisition module are arranged on the inner side of the platform screen door and the train body at one end of a detected platform section respectively. The first linear light source is arranged on the inner side of the platform screen door at the other end of the detected platform section. The first image acquisition module and the second image acquisition module are used for acquiring light source images of the first linear light source in corresponding visual angles. A processor is used for acquiring the light source images of the first linear light source collected by the first image acquisition module and the second image acquisition module, and determining the contour size information of the linear light source in each light source image, so as to determine whether there is a foreign matter in the gap according to the contour size information. The application can improve the efficiency of foreign matter detection in the gap between the train door and the platform screen door and the accuracy of the detection result.

Description

Technical Field

[0001] This invention relates to the field of information processing technology, and in particular to a subway car door gap anti-pinch system and its detection method. Background Technology

[0002] With the continuous development of urban rail transit construction, more and more passengers are choosing to travel by subway, high-speed rail and other rail transit. However, in actual train operation, incidents of people being trapped in train doors or platform screen doors frequently occur, seriously affecting the personal safety of passengers.

[0003] To prevent the aforementioned accidents, existing technologies provide a traditional manual method for detecting foreign objects. This involves installing light strips at the end of the platform, with the train driver observing the light strips to determine if there are foreign objects between the train doors and the platform screen doors. However, this method not only increases the workload of the train driver but is also easily affected by the driver's mental state, leading to false positives and false negatives, resulting in low safety and reliability. Existing technologies also provide an infrared method for detecting foreign objects, using infrared laser beam detectors at both ends of the platform to detect foreign objects between the train doors and the platform screen doors. However, this method has limited detection range and blind spots, still posing safety hazards. Existing technologies also provide an image detection method, which involves installing two linear non-visible light sources diagonally inside the platform screen doors and installing two image acquisition devices, one directly above the other linear non-visible light source and the other directly below it, to improve the coverage of the detection range. However, this method still has blind spots and cannot achieve truly complete coverage of the gap area. Existing technology also provides an image detection method that uses a camera installed inside the platform screen door to detect the complete number of light strips in the gap between the train door and the platform screen door to determine whether there are foreign objects in the gap. However, this method also has a detection blind spot, and when the light strips are damaged, it will lead to false detection.

[0004] Therefore, how to achieve a safer and more reliable method for detecting foreign objects in the gap between train doors and platform screen doors during train operation has become a technical problem that the industry urgently needs to solve. Summary of the Invention

[0005] This invention provides a subway door gap anti-pinch system and its detection method, which enables a safer and more reliable method for detecting foreign objects in the gap between train doors and platform screen doors.

[0006] This invention provides a subway car door gap anti-pinch system, comprising:

[0007] An image acquisition module, a linear light source, and a processor; the image acquisition module includes a first image acquisition module and a second image acquisition module, and the linear light source includes a first linear light source;

[0008] The first image acquisition module, the second image acquisition module, and the first linear light source are all disposed in the gap between the train door and the platform screen door; the first image acquisition module and the second image acquisition module are respectively disposed on the inside of the platform screen door at one end of the inspected platform section and on the train body; the first linear light source is disposed on the inside of the platform screen door at the other end of the inspected platform section.

[0009] Both the first image acquisition module and the second image acquisition module are used to acquire the light source image of the first linear light source from the corresponding viewpoint;

[0010] The processor is used to acquire light source images of the first linear light source acquired by the first image acquisition module and the second image acquisition module, and to determine the external dimensions of the linear light source in each light source image, so as to determine whether there are foreign objects in the gap based on the external dimensions.

[0011] According to the subway door gap anti-pinch system provided by the present invention, the image acquisition module further includes a third image acquisition module and a fourth image acquisition module, and the linear light source further includes a second linear light source;

[0012] The third image acquisition module, the fourth image acquisition module, and the second linear light source are all disposed in the gap between the train door and the platform screen door. The third image acquisition module and the fourth image acquisition module are respectively disposed on the inside of the platform screen door at the other end of the inspected platform section and on the train body; the second linear light source is disposed on the inside of the platform screen door at one end of the inspected platform section.

[0013] Both the third image acquisition module and the fourth image acquisition module are used to acquire the light source image of the second linear light source from the corresponding viewpoint;

[0014] The processor is used to acquire light source images of the linear light source acquired by the first image acquisition module, the second image acquisition module, the third image acquisition module and the fourth image acquisition module respectively, and determine the external dimensions of the linear light source in each light source image, and determine whether there are foreign objects in the gap based on the external dimensions.

[0015] According to the present invention, a subway door gap anti-pinch system is provided, wherein the processor is specifically used for:

[0016] Extract the pixel contours of the linear light source in each of the light source images;

[0017] Construct the bounding rectangle of each pixel contour;

[0018] Based on the size information of the bounding rectangle of each pixel contour, the external size information of the linear light source in each light source image is obtained; the external size information includes the area of ​​the bounding rectangle and the aspect ratio of the bounding rectangle.

[0019] According to the subway door gap anti-pinch system provided by the present invention, the processor is further configured to:

[0020] If each of the aforementioned external dimensions is determined to be within the corresponding preset threshold range, it is determined that there are no foreign objects in the gap, and a signal allowing the train to run is output.

[0021] or,

[0022] If any of the aforementioned dimensional information is determined to be outside the corresponding preset threshold range, a foreign object is identified within the gap, and a signal prohibiting train operation is output.

[0023] According to the subway door gap anti-pinch system provided by the present invention, the processor is further configured to:

[0024] Each of the light source images is blurred, and each blurred light source image is converted into a grayscale image.

[0025] For each grayscale image, image gradient calculation, binarization, and denoising are performed sequentially to obtain the pixel contour of the linear light source in each light source image.

[0026] The present invention also provides a detection method for a subway door gap anti-pinch system as described above, comprising:

[0027] The first image acquisition module acquires the light source image of the first linear light source from its corresponding viewpoint, and the second image acquisition module acquires the light source image of the first linear light source from its corresponding viewpoint.

[0028] The processor acquires the light source images of the first linear light source acquired by the first image acquisition module and the second image acquisition module, and the processor determines the external dimensions of the linear light source in each light source image, and determines whether there are foreign objects in the gap between the train door and the platform screen door based on the external dimensions.

[0029] According to a detection method provided by the present invention, after the first image acquisition module acquires a light source image of the first linear light source at its corresponding viewing angle, and the second image acquisition module acquires a light source image of the first linear light source at its corresponding viewing angle, the method further includes:

[0030] The third image acquisition module acquires the light source image of the second linear light source from its corresponding viewpoint, and the fourth image acquisition module acquires the light source image of the second linear light source from its corresponding viewpoint.

[0031] The processor acquires the light source images of the linear light source acquired by the first image acquisition module, the second image acquisition module, the third image acquisition module, and the fourth image acquisition module, and determines the external dimensions of the linear light source in each light source image, so as to determine whether there are foreign objects in the gap based on the external dimensions.

[0032] According to a detection method provided by the present invention, the processor determines the external dimensions of a linear light source in each of the light source images, including:

[0033] The processor extracts the pixel contours of linear light sources in each of the light source images;

[0034] The processor constructs the bounding rectangle of each pixel outline;

[0035] The processor obtains the outline size information of the linear light source in each light source image based on the size information of the bounding rectangle of each pixel outline; the outline size information includes the area of ​​the bounding rectangle and the aspect ratio of the bounding rectangle.

[0036] According to a detection method provided by the present invention, determining whether there are foreign objects in the gap between the train door and the platform screen door based on the external dimensional information includes:

[0037] If each of the aforementioned external dimensions is determined to be within the corresponding preset threshold range, it is determined that there are no foreign objects in the gap, and a signal allowing the train to run is output.

[0038] or,

[0039] If any of the aforementioned dimensional information is determined to be outside the corresponding preset threshold range, a foreign object is identified within the gap, and a signal prohibiting train operation is output.

[0040] According to a detection method provided by the present invention, the processor extracts the pixel contours of linear light sources in each of the light source images, including:

[0041] The processor performs blurring processing on each of the light source images and converts each of the blurred light source images into a grayscale image.

[0042] The processor sequentially performs image gradient calculation, binarization, and denoising on each grayscale image to obtain the pixel contour of the linear light source in each light source image.

[0043] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the detection method as described above.

[0044] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the detection method as described above.

[0045] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the detection method as described above.

[0046] The subway door gap anti-pinch system and its detection method provided by this invention, by placing a first image acquisition module, a second image acquisition module, and a first linear light source within the gap between the train door and the platform screen door, not only places the first image acquisition module inside the platform screen door at one end of the platform section, but also places the second image acquisition module on the train body at one end of the platform section being inspected, and places the first linear light source inside the platform screen door at the other end of the platform section being inspected. Compared with the existing solution of arranging image acquisition devices only on one side of the platform screen door, this can truly achieve a detection method with no blind spots and full coverage of the gap area formed by one side of the train door and one side of the platform screen door. Furthermore, by utilizing the first image acquisition module and the second image acquisition module... The block acquires the light source image of the first linear light source from the corresponding viewpoint. Based on the acquired light source images, the processor uses image processing technology to determine the external dimensions of the linear light source in each image. This ensures that even if some internal LEDs of the linear light source are damaged, it will not affect the detection of the overall external dimensions of the linear light source, resulting in reliable detection results. Furthermore, based on the external dimensions, it can jointly determine whether there are foreign objects in the gap. This achieves a larger detection range and a truly full-coverage detection method without manual intervention, greatly improving the detection efficiency and accuracy of foreign objects in the gap between train doors and platform screen doors, enhancing the safety and reliability of train operation, and enabling fully automatic SIL4 level safety anti-pinch detection. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0048] Figure 1This is one of the structural schematic diagrams of the subway door gap anti-pinch system provided by the present invention;

[0049] Figure 2 This is the second structural schematic diagram of the subway door gap anti-pinch system provided by the present invention;

[0050] Figure 3 This is the third structural schematic diagram of the subway door gap anti-pinch system provided by the present invention;

[0051] Figure 4 This is a flowchart illustrating the detection method of the subway door gap anti-pinch system provided by the present invention;

[0052] Figure 5 This is a schematic diagram of the physical structure of the electronic device provided by the present invention. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0054] In the description of the invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0055] The following is combined Figures 1-5 This invention describes the subway car door gap anti-pinch system and its detection method.

[0056] Figure 1 This is one of the structural schematic diagrams of the subway door gap anti-pinch system provided by the present invention, such as... Figure 1 As shown, the system may include:

[0057] Image acquisition module, linear light source and processor 3;

[0058] The image acquisition module includes a first image acquisition module 11 and a second image acquisition module 12, and the linear light source includes a first linear light source 21;

[0059] The first image acquisition module 11, the second image acquisition module 12, and the first linear light source 21 are all located in the gap between the train door and the platform screen door; the first image acquisition module 11 and the second image acquisition module 12 are respectively located on the inside of the platform screen door at one end of the inspected platform section and on the train body; the first linear light source 21 is located on the inside of the platform screen door at the other end of the inspected platform section.

[0060] Both the first image acquisition module 11 and the second image acquisition module 12 are used to acquire the light source image of the first linear light source 21 from the corresponding viewpoint;

[0061] The processor 3 is used to acquire light source images of the first linear light source 21 acquired by the first image acquisition module and the second image acquisition module, and to determine the external dimensions of the linear light source in each light source image, so as to determine whether there are foreign objects in the gap based on the external dimensions.

[0062] Specifically, in the embodiments of the present invention, both the first image acquisition module and the second image acquisition module can be industrial cameras, including cameras. Here, the lens of the camera can be a telephoto lens. By utilizing its long focal length property, a long-distance detection function for foreign objects in the gap between the train door and the platform screen door can be realized, enabling the detection system to achieve a larger detection range.

[0063] In embodiments of the present invention, the linear light source includes a first linear light source, which can specifically be a light source device with a linear shape, such as a line or strip. This light source device can be an LED strip composed of multiple LED beads, and the light source can be a visible light source. Optionally, the light source can also be a non-visible light source, such as infrared light, which, compared to visible light sources, can avoid affecting the worker's vision during foreign object detection. Specifically, the linear light source can be arranged vertically, perpendicular to the platform plane, inside the shielding door at the other end of the inspected platform section, ensuring that the linear light source captured by the image acquisition module is rectangular in shape.

[0064] Figure 2 This is the second structural schematic diagram of the subway door gap anti-pinch system provided by the present invention, as shown below. Figure 2 As shown, this is a front view of the train's front end. The first image acquisition module 11, the second image acquisition module 12, and the first linear light source 21 are all located in the gap between the train door and the platform screen door. The first image acquisition module 11 is located inside the platform screen door at one end of the platform being inspected. The second image acquisition module 12 is located on the train body at one end of the platform being inspected. The first linear light source 21 is located inside the platform screen door at the other end of the platform being inspected.

[0065] In an embodiment of the present invention, by setting the first image acquisition module inside the platform door at one end of the inspected platform section, the shooting angle on one side plane of the platform door within the gap between the train door and the platform door can be covered. Furthermore, by setting the second image acquisition module on the train body at one end of the inspected platform section, the shooting angle on one side plane of the train door within the gap between the train door and the platform door can be covered. Thus, the gap area formed by the space between one side plane of the train door and one side plane of the platform door, i.e. the entire gap area between the train door and the platform door, can achieve a truly comprehensive detection method without blind spots, without any blind spots in the shooting angle.

[0066] In embodiments of the present invention, the number of first and second image acquisition modules can be adaptively increased according to the actual scenario to ensure that the first linear light source can be captured from different angles, further enhancing the coverage of the entire gap area between the train door and the platform screen door. Simultaneously, based on the mechanism of multiple first and second image acquisition modules, when some image acquisition modules malfunction and cannot function properly, the system can still perform foreign object detection through other normally functioning image acquisition modules, thereby improving the stability of the entire subway door gap anti-pinch system.

[0067] It should be noted that, in this embodiment of the invention, the specific location and shooting angle of the image acquisition module only need to satisfy the requirement that the image acquisition module can acquire a complete image of the first linear light source. Therefore, the present invention does not impose specific limitations on the specific location and shooting angle of the image acquisition module.

[0068] Furthermore, in an embodiment of the present invention, each image acquisition module establishes a communication connection with the processor, which can be located inside the train control platform. Both the first image acquisition module and the second image acquisition module acquire light source images of the first linear light source at the corresponding viewing angle, and send the light source images to the processor through the communication connection network for image processing and calculation.

[0069] The dimensional information of the linear light source described in this embodiment of the invention refers to the shape and related dimensions of the linear light source in the image obtained by image processing of the light source image. Since it is a linear light source, the displayed image generally exhibits a rectangular shape. Therefore, the dimensional information of the linear light source may include information such as the rectangular shape, the length of the long side, the length of the short side, the aspect ratio between the long and short sides, and the area of ​​the rectangle.

[0070] In this embodiment of the invention, the processor may be equipped with image processing capabilities, and the image acquisition module employs an industrial camera. After the processor acquires the light source images of the linear light source captured by each industrial camera, it can also perform image processing and calculations on each light source image to extract the external dimensions of the linear light source in each image. Through a multi-camera joint judgment mechanism, it can determine whether the external dimensions of the linear light source in the light source images captured by each industrial camera meet the requirements, thereby determining whether there are foreign objects in the gap between the train door and the platform screen door.

[0071] In an embodiment of the present invention, when the linear light source is a light strip composed of multiple LED beads, the processor can also calculate the number of bright spots of the linear light source in each light source image, i.e. the number of LED beads, to determine whether the linear light source is obstructed, and thus determine whether there are foreign objects in the gap between the train door and the platform screen door.

[0072] It should be noted that, in this embodiment of the invention, considering the integrity of the linear light source's shape is more reliable than detecting the number of LEDs in the linear light source. This is because, in actual system operation scenarios, it is inevitable that some LEDs in the linear light source will be damaged. In this case, calculating the number of bright spots in each light source image is no longer accurate, which can easily lead to system misjudgment and affect the system's detection results.

[0073] The method of determining the presence of foreign objects by directly extracting the shape and size information of linear light sources in the light source image can effectively avoid the situation where the system misjudges due to damage to the LED beads of the linear light source. It will not affect the normal operation of the entire subway door gap anti-pinch system, and the detection results are reliable and safer.

[0074] In embodiments of the present invention, if it is determined that there are no foreign objects in the gap between the train door and the platform screen door, the train door and the platform screen door can be controlled to close, thereby allowing the train to run safely. Conversely, if it is determined that there are foreign objects in the gap, both the train door and the platform screen door can be kept open until no foreign objects are detected in the gap, at which point the train door and the platform screen door can be controlled to close, and the train can begin operation. This effectively prevents incidents of passengers being trapped by the train door or platform screen door, ensuring passenger safety.

[0075] In this embodiment of the invention, by using a processor to automatically read the images of each light source and process them using algorithms, the train driver is not required to look at the light strips, which reduces the train driver's workload and reduces unreliability caused by human error or omissions. Furthermore, it can be applied to driverless lines. The entire subway door gap anti-pinch system only requires a few image acquisition modules, linear light sources, and a computer, resulting in low hardware costs and no additional labor costs.

[0076] The subway door gap anti-pinch system provided in this embodiment of the invention, by placing a first image acquisition module, a second image acquisition module, and a first linear light source within the gap between the train door and the platform screen door, not only places the first image acquisition module inside the platform screen door at one end of the platform section, but also places the second image acquisition module on the train body at one end of the platform section being inspected, and places the first linear light source inside the platform screen door at the other end of the platform section being inspected. Compared to existing solutions that only arrange image acquisition devices on one side of the platform screen door, this truly achieves a detection method with no blind spots and full coverage of the gap area formed by one side of the train door and one side of the platform screen door. Furthermore, by utilizing the first and second image acquisition modules... The processor collects images of the first linear light source from the corresponding viewing angle. Based on the acquired images, it uses image processing technology to determine the external dimensions of the linear light source in each image. This ensures that even if some internal LEDs of the linear light source are damaged, it will not affect the detection of the overall external dimensions of the linear light source, resulting in reliable detection results. Furthermore, based on the external dimensions, it can jointly determine whether there are foreign objects in the gap. This achieves a larger detection range and a truly full-coverage detection method without manual intervention, greatly improving the detection efficiency and accuracy of foreign objects in the gap between train doors and platform screen doors, enhancing the safety and reliability of train operation, and enabling fully automated SIL4 level safety anti-pinch detection.

[0077] Figure 3 This is the third structural schematic diagram of the subway door gap anti-pinch system provided by the present invention, as shown below. Figure 3 As shown, the system may include:

[0078] The image acquisition module may also include a third image acquisition module 13 and a fourth image acquisition module 14, and the linear light source may also include a second linear light source 22;

[0079] The third image acquisition module 13, the fourth image acquisition module 14, and the second linear light source 22 are all located in the gap between the train door and the platform screen door; the third image acquisition module 13 and the fourth image acquisition module 14 are respectively located on the inside of the platform screen door at the other end of the inspected platform section and on the train body; the second linear light source 22 is located on the inside of the platform screen door at one end of the inspected platform section.

[0080] Both the third and fourth image acquisition modules are used to acquire the light source image of the second linear light source from the corresponding viewpoint;

[0081] The processor is used to acquire the light source images of the linear light source acquired by the first image acquisition module 11, the second image acquisition module 12, the third image acquisition module 13 and the fourth image acquisition module 14 respectively, and determine the external dimensions of the linear light source in each light source image. Based on the external dimensions, it determines whether there are foreign objects in the gap between the train door and the platform screen door.

[0082] Specifically, in embodiments of the present invention, the third image acquisition module, the fourth image acquisition module, and the second linear light source can all be disposed within the gap between the train door and the platform screen door. The second linear light source is disposed inside the platform screen door at one end of the inspected platform section, and the third image acquisition module is disposed inside the platform screen door at the other end of the inspected platform section. The fourth image acquisition module is disposed on the train body at the other end of the inspected platform section. In this way, the system can also capture images of the light source of the opposite second linear light source within the gap from different perspectives at the other end of the inspected platform section. This can prevent missed detections caused by the fixed perspective of the image acquisition module at one end of the inspected platform section, further enhance the coverage of the entire gap area between the train door and the platform screen door, strengthen the coverage of all blind spots within the gap, and thus further improve the detection accuracy of the subway door gap anti-pinch system.

[0083] In an embodiment of the present invention, in addition to acquiring the light source images of the first linear light source acquired by the first image acquisition module and the second image acquisition module, the processor will also acquire the light source images of the first linear light source acquired by the third image acquisition module and the fourth image acquisition module. After extracting the shape and size information of the linear light source in each light source image, the processor will use a multi-camera joint judgment mechanism to determine whether the shape and size information of the linear light source in the light source images acquired by each image acquisition module meets the requirements, thereby determining whether there are foreign objects in the gap between the train door and the platform screen door.

[0084] It should be noted that, similarly, the number of third and fourth image acquisition modules can be adaptively increased according to the actual scenario, ensuring that the second linear light source can be captured from different angles at the other end of the inspected platform section, further enhancing the coverage of the entire gap area between the train door and the platform screen door. Furthermore, based on the configuration mechanism of multiple third and fourth image acquisition modules, when some image acquisition modules malfunction and cannot function properly, the system can still perform foreign object detection through other normally functioning image acquisition modules, thereby further improving the stability of the entire subway door gap anti-pinch system.

[0085] The system of this invention, by setting an image acquisition module at one end of the inspected platform section and a linear light source at the opposite end, can simultaneously detect foreign objects in the gap between the train door and the platform door from the other end of the inspected platform section. This can further enhance the detection coverage of the entire gap area between the train door and the platform door, strengthen the coverage of all blind spots in the gap, and further improve the detection accuracy of the subway door gap anti-pinch system.

[0086] Based on the above embodiments, as an optional embodiment, the processor is specifically used for:

[0087] Extract the pixel contours of linear light sources from each light source image;

[0088] Construct the bounding rectangle of the outline of each pixel;

[0089] Based on the size information of the bounding rectangle of each pixel contour, the external size information of the linear light source in each light source image is obtained; the external size information includes the area of ​​the bounding rectangle and the aspect ratio of the bounding rectangle.

[0090] Specifically, in an embodiment of the present invention, after the processor acquires the light source images of the linear light source acquired by each image acquisition module, it can use image processing technology to determine the external dimensions of the linear light source in each light source image.

[0091] Specifically, the processor first extracts the pixel contours of linear light sources in each light source image. If no pixel contours are extracted, it means no linear light source was detected, and the algorithm returns an error. If the number of pixel contours is greater than one, the algorithm also returns an error, indicating that there may be other light sources within the gaps.

[0092] Optionally, the processor specifically extracts the pixel contours of linear light sources in each light source image, including:

[0093] The images of each light source are blurred, and each blurred image of the light source is converted into a grayscale image.

[0094] For each grayscale image, perform image gradient calculation, binarization, and denoising processing sequentially to obtain the pixel contour of the linear light source in each light source image.

[0095] Specifically, in embodiments of the present invention, the processor performs Gaussian blurring or other blurring processing on the images of each light source to reduce noise in the image and reduce the level of detail.

[0096] Furthermore, each blurred light source image is converted into a grayscale image. Since identifying linear light sources, such as LED strips, only brightness needs to be identified, and color is not required, the blurred light source images can be converted into grayscale images to prepare for subsequent judgment.

[0097] Then, operators such as Sobel can be used to calculate the image gradient for each grayscale image to find the vertical portion in the image. Since the light strip is a vertical strip shape, the pixel region of the light strip can be found through image gradient calculation.

[0098] Next, the light source images after gradient calculation are binarized. Since the light strips are relatively bright, they will still be retained after binarization, while areas with insufficient brightness will be directly turned into black areas.

[0099] Finally, a series of morphological operations are performed to remove remaining noise. For example, a dilation-erosion operation can be performed first in the x-axis of the image pixel coordinates to remove horizontal holes, and then an erosion-dilation operation can be performed in the y-axis to remove vertical noise. After this step, only the pixels of the light strip will remain in the light source image, thus allowing the pixel contours of the linear light source in each light source image to be obtained.

[0100] The system of this invention takes into account the actual process of linear light sources, such as the illumination pattern of light strips, and performs image processing on the images of each light source to ensure that the pixel contours of the linear light sources in each light source image are accurately and effectively extracted, providing effective data support for subsequent foreign object detection and judgment.

[0101] Furthermore, the processor constructs the bounding rectangle for each pixel's outline. At this point, it determines whether the rectangle's height is greater than three times its width, i.e., whether the bounding rectangle of the pixel's outline is a long and narrow rectangle. If not, it indicates that the pixel's outline is not a linear light source, and the algorithm returns an exception.

[0102] If so, the external dimensions of the linear light source in each light source image can be obtained based on the size information of the bounding rectangle of each pixel contour. The external dimensions can include the area and aspect ratio of the bounding rectangle. For example, to detect the area and aspect ratio of the bounding rectangle in the external dimensions of the linear light source in a certain light source image, the area and aspect ratio of the bounding rectangle are compared with the pre-stored preset area and aspect ratio of the bounding rectangle corresponding to the light source image to determine whether the detected area and aspect ratio of the bounding rectangle meet the requirements.

[0103] Finally, through a multi-camera joint judgment mechanism, the processor determines whether there are foreign objects in the gap between the train door and the platform screen door based on the shape and size information of the linear light source in each light source image. This enables foreign object detection from various angles in the gap between the train door and the platform screen door, improving the detection accuracy of the subway door gap anti-pinch system.

[0104] The system of this invention combines the geometric features of linear light sources in captured images and extracts the pixel contours of linear light sources in each light source image through image processing. It calculates the external dimensions of the linear light sources in each light source image. It has the characteristics of strong anti-interference ability, high accuracy, clear target positioning, and low noise results, which is beneficial to improving the detection accuracy of the subway door gap anti-pinch system.

[0105] Based on the above embodiments, as an optional embodiment, the processor is further configured to:

[0106] If the dimensions of the linear light source in each light source image are determined to be within the corresponding preset threshold range, and it is determined that there are no foreign objects in the gap, a signal allowing the train to run is output.

[0107] or,

[0108] If any external dimension information is determined to be inconsistent with the corresponding preset threshold range, a foreign object is identified in the gap, and a signal prohibiting train operation is output.

[0109] It is understandable that, since each image acquisition module detects the linear light source from a different angle, the external dimensions of the linear light source obtained from images taken at different angles will vary slightly. Each image acquisition module, at its fixed angle, will capture a light source image corresponding to a threshold range for the external dimensions of the linear light source. In the embodiments of this invention, as long as it is determined that the external dimensions of the linear light source in the light source images captured by each image acquisition module all conform to their corresponding threshold range, it can be concluded that each image acquisition module can normally detect the linear light source, and the linear light source is not obstructed at different angles. Therefore, it can be determined that there are no foreign objects or passengers in the gap between the train door and the platform screen door.

[0110] It should be noted that the normal detection of a linear light source described in the embodiments of the present invention refers to the image acquisition module being able to capture a complete luminous image of the linear light source.

[0111] Specifically, the preset threshold range in this embodiment of the invention refers to a pre-set threshold range, which is the threshold range within which each image acquisition module can normally detect the shape and size information of the linear light source in the image corresponding to the linear light source at its fixed viewing angle.

[0112] In one specific embodiment, the image acquisition module uses an industrial camera, and the linear light source is a light strip composed of LEDs. The light strip is captured by industrial cameras at both ends of the inspected station section. The light source image of the light strip acquired by each industrial camera is transmitted to a processor in a computer for data processing. Computer vision algorithms are used to process each light source image to detect the presence of the light strip and whether the shape and dimensions of the light strip meet the requirements, such as whether the shape is rectangular and whether the shape area and aspect ratio meet the corresponding preset threshold range.

[0113] In this embodiment, if the area and aspect ratio of the circumscribed rectangle of the light strip in each light source image meet the corresponding preset threshold range, it can be assumed that each industrial camera can detect the light strip normally, and it can be determined that there are no passengers or other foreign objects in the gap between the train door and the platform screen door, and a start signal that allows the train to run can be output.

[0114] In this embodiment, for any linear light source in the light source image, if no light strip is detected, or only part of the light strip is detected, and its shape area and aspect ratio are not within the corresponding preset threshold range, it is assumed that there is a passenger or other foreign object obstructing the gap between the train door and the platform screen door. In this case, the train is not allowed to start.

[0115] The method of this invention employs a multi-camera joint judgment mechanism to perform image detection on linear light source images acquired from different viewing angles, based on comprehensive coverage of the blind spots within the gap. When it is ensured that the linear light source within the gap can be detected normally from each viewing angle, it is determined that there are no foreign objects in the gap, which greatly improves the detection accuracy of the subway door gap anti-pinch system and can achieve SIL4 level safety anti-pinch detection.

[0116] The detection method of the subway door gap anti-pinch system provided by the present invention is described below. The detection method described below can be referred to in correspondence with the subway door gap anti-pinch system described above.

[0117] Figure 4 This is a flowchart illustrating the detection method for the subway door gap anti-pinch system provided by the present invention, as shown below. Figure 4 As shown, this method can be applied to the aforementioned subway door gap anti-pinch system, and the method may include:

[0118] Step 410: The first image acquisition module acquires the light source image of the first linear light source at its corresponding viewpoint, and the second image acquisition module acquires the light source image of the first linear light source at its corresponding viewpoint.

[0119] Step 420: The processor acquires the light source images of the first linear light source acquired by the first image acquisition module and the second image acquisition module, and the processor determines the external dimensions of the linear light source in each light source image, and determines whether there are foreign objects in the gap between the train door and the platform screen door based on the external dimensions.

[0120] The detection method described in this embodiment can be used to perform the above-mentioned detection method embodiment for the subway door gap anti-pinch system. Its principle and technical effect are similar, and will not be repeated here.

[0121] The detection method for the subway door gap anti-pinch system provided in this invention involves placing a first image acquisition module, a second image acquisition module, and a first linear light source within the gap between the train door and the platform screen door. This method not only places the first image acquisition module inside the platform screen door at one end of the platform section being inspected, but also places the second image acquisition module on the train body at one end of the platform section being inspected, and places the first linear light source inside the platform screen door at the other end of the platform section being inspected. Compared to existing solutions that only place image acquisition devices on one side of the platform screen door, this method truly achieves a comprehensive detection method with no blind spots in the gap area formed by the plane of the train door and the plane of the platform screen door. Furthermore, by utilizing the first image acquisition module and the second image acquisition module... The module acquires images of the first linear light source from the corresponding viewpoint. Based on the acquired images, the processor uses image processing technology to determine the external dimensions of the linear light source in each image. This ensures that even if some internal LEDs of the linear light source are damaged, it will not affect the detection of the overall external dimensions of the linear light source, resulting in reliable detection results. Furthermore, based on the external dimensions, the system can jointly determine whether there are foreign objects in the gap. This achieves a larger detection range and a truly full-coverage detection method without the need for manual intervention, greatly improving the detection efficiency and accuracy of foreign objects in the gap between train doors and platform screen doors. This enhances the safety and reliability of train operation and enables fully automated SIL4 level safety anti-pinch detection.

[0122] Based on the above embodiments, as an optional embodiment, after the first image acquisition module acquires the light source image of the first linear light source at its corresponding viewing angle, and the second image acquisition module acquires the light source image of the first linear light source at its corresponding viewing angle, the method further includes:

[0123] The third image acquisition module acquires the light source image of the second linear light source from its corresponding viewpoint, and the fourth image acquisition module acquires the light source image of the second linear light source from its corresponding viewpoint.

[0124] The processor acquires the light source images of the linear light source acquired by the first image acquisition module, the second image acquisition module, the third image acquisition module, and the fourth image acquisition module, and determines the external dimensions of the linear light source in each light source image, so as to determine whether there are foreign objects in the gap based on the external dimensions.

[0125] Based on the above embodiments, as an optional embodiment, the processor determines the external dimensions of the linear light source in each light source image, including:

[0126] The processor extracts the pixel contours of linear light sources in each light source image;

[0127] The processor constructs the bounding rectangle of each pixel's outline;

[0128] The processor obtains the outline size information of the linear light source in each light source image based on the size information of the bounding rectangle of each pixel outline; the outline size information includes the area of ​​the bounding rectangle and the aspect ratio of the bounding rectangle.

[0129] Based on the above embodiments, as an optional embodiment, the processor extracts the pixel contours of linear light sources in each light source image, including:

[0130] The processor blurs the images of each light source and converts each blurred image into a grayscale image.

[0131] The processor sequentially performs image gradient calculation, binarization, and denoising on each grayscale image to obtain the pixel contour of the linear light source in each light source image.

[0132] Based on the above embodiments, as an optional embodiment, determining whether there are foreign objects in the gap between the train door and the platform screen door according to various external dimensional information includes:

[0133] If each external dimension information is determined to be within the corresponding preset threshold range, and it is determined that there are no foreign objects in the gap, a signal is output that allows the train to run.

[0134] or,

[0135] If any external dimension information is determined to be inconsistent with the corresponding preset threshold range, a foreign object is identified in the gap, and a signal prohibiting train operation is output.

[0136] Figure 5 This is a schematic diagram of the physical structure of the electronic device provided by the present invention, such as... Figure 5As shown, the electronic device may include a processor 510, a communication interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call logical instructions in the memory 530 to execute the detection methods provided by the above methods. The method includes: the first image acquisition module acquiring a light source image of the first linear light source from its corresponding viewing angle, and the second image acquisition module acquiring a light source image of the first linear light source from its corresponding viewing angle; the processor acquiring the light source images of the first linear light source acquired by the first image acquisition module and the second image acquisition module, and the processor determining the external dimensions of the linear light source in each light source image, and determining whether there are foreign objects in the gap between the train door and the platform screen door based on the external dimensions.

[0137] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, 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 the present invention. 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), magnetic disks, or optical disks.

[0138] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the detection methods provided by the above methods. The method includes: a first image acquisition module acquiring a light source image of the first linear light source at its corresponding viewing angle, and a second image acquisition module acquiring a light source image of the first linear light source at its corresponding viewing angle; the processor acquiring the light source images of the first linear light source acquired by the first image acquisition module and the second image acquisition module, and the processor determining the external dimensions of the linear light source in each light source image, and determining whether there are foreign objects in the gap between the train door and the platform screen door based on the external dimensions.

[0139] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the detection method provided by the above methods. The method includes: a first image acquisition module acquiring a light source image of the first linear light source at its corresponding viewing angle, and a second image acquisition module acquiring a light source image of the first linear light source at its corresponding viewing angle; the processor acquiring the light source images of the first linear light source acquired by the first image acquisition module and the second image acquisition module, and the processor determining the external dimensions of the linear light source in each light source image, and determining whether there is a foreign object in the gap between the train door and the platform screen door based on each external dimensions.

[0140] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0141] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0142] 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 subway car door gap anti-pinch system, characterized in that, include: An image acquisition module, a linear light source, and a processor; the image acquisition module includes a first image acquisition module and a second image acquisition module, and the linear light source includes a first linear light source; The first image acquisition module, the second image acquisition module, and the first linear light source are all disposed in the gap between the train door and the platform screen door; the first image acquisition module and the second image acquisition module are respectively disposed on the inside of the platform screen door at one end of the inspected platform section and on the train body; the first linear light source is disposed on the inside of the platform screen door at the other end of the inspected platform section in a vertical direction perpendicular to the platform ground plane. Both the first image acquisition module and the second image acquisition module are used to acquire the light source image of the first linear light source from the corresponding viewpoint; The processor is used to acquire the light source images of the first linear light source acquired by the first image acquisition module and the second image acquisition module, and to determine the external dimensions of the linear light source in each light source image, so as to determine whether there are foreign objects in the gap based on the external dimensions. The processor is specifically used for: Extract the pixel contours of the linear light source in each of the light source images; Construct the bounding rectangle of each pixel contour; Based on the size information of the bounding rectangle of each pixel contour, the external size information of the linear light source in each light source image is obtained; the external size information includes the area of ​​the bounding rectangle and the aspect ratio of the bounding rectangle.

2. The subway door gap anti-pinch system according to claim 1, characterized in that, The image acquisition module further includes a third image acquisition module and a fourth image acquisition module, and the linear light source further includes a second linear light source; The third image acquisition module, the fourth image acquisition module, and the second linear light source are all disposed in the gap between the train door and the platform screen door. The third image acquisition module and the fourth image acquisition module are respectively disposed on the inside of the platform screen door at the other end of the inspected platform section and on the train body; the second linear light source is disposed on the inside of the platform screen door at one end of the inspected platform section. Both the third image acquisition module and the fourth image acquisition module are used to acquire the light source image of the second linear light source from the corresponding viewpoint; The processor is used to acquire light source images of the linear light source acquired by the first image acquisition module, the second image acquisition module, the third image acquisition module and the fourth image acquisition module respectively, and determine the external dimensions of the linear light source in each light source image, so as to determine whether there are foreign objects in the gap based on the external dimensions.

3. The subway door gap anti-pinch system according to any one of claims 1 or 2, characterized in that, The processor is further specifically used for: If each of the aforementioned external dimensions is determined to be within the corresponding preset threshold range, it is determined that there are no foreign objects in the gap, and a signal allowing the train to run is output. or, If any of the aforementioned dimensional information is determined to be outside the corresponding preset threshold range, a foreign object is identified within the gap, and a signal prohibiting train operation is output.

4. The subway door gap anti-pinch system according to claim 1, characterized in that, The processor is further specifically used for: Each of the light source images is blurred, and each blurred light source image is converted into a grayscale image. For each grayscale image, image gradient calculation, binarization, and denoising are performed sequentially to obtain the pixel contour of the linear light source in each light source image.

5. A detection method for the anti-pinch system for subway car door gaps as described in any one of claims 1-4, characterized in that, include: The first image acquisition module acquires the light source image of the first linear light source from its corresponding viewpoint, and the second image acquisition module acquires the light source image of the first linear light source from its corresponding viewpoint. The first image acquisition module and the second image acquisition module are respectively installed inside the platform screen door at one end of the inspected platform section and on the train body. The first linear light source is installed in a vertical direction perpendicular to the platform ground plane inside the platform screen door at the other end of the inspected platform section. The processor acquires the light source images of the first linear light source acquired by the first image acquisition module and the second image acquisition module, and the processor determines the external dimensions of the linear light source in each light source image, and determines whether there are foreign objects in the gap between the train door and the platform screen door based on the external dimensions. The processor determines the external dimensions of the linear light source in each of the light source images, including: The processor extracts the pixel contours of linear light sources in each of the light source images; The processor constructs the bounding rectangle of each pixel outline; The processor obtains the outline size information of the linear light source in each light source image based on the size information of the bounding rectangle of each pixel outline; the outline size information includes the area of ​​the bounding rectangle and the aspect ratio of the bounding rectangle.

6. The detection method according to claim 5, characterized in that, After the first image acquisition module acquires the light source image of the first linear light source at its corresponding viewpoint, and the second image acquisition module acquires the light source image of the first linear light source at its corresponding viewpoint, the method further includes: The third image acquisition module acquires the light source image of the second linear light source from its corresponding viewpoint, and the fourth image acquisition module acquires the light source image of the second linear light source from its corresponding viewpoint. The processor acquires the light source images of the linear light source acquired by the first image acquisition module, the second image acquisition module, the third image acquisition module, and the fourth image acquisition module, and determines the external dimensions of the linear light source in each light source image, so as to determine whether there are foreign objects in the gap based on the external dimensions.

7. The detection method according to any one of claims 5 or 6, characterized in that, The step of determining whether there are foreign objects in the gap between the train door and the platform screen door based on the aforementioned external dimensions includes: If each of the aforementioned external dimensions is determined to be within the corresponding preset threshold range, it is determined that there are no foreign objects in the gap, and a signal allowing the train to run is output. Alternatively, if any of the aforementioned dimensional information is determined to be outside the corresponding preset threshold range, a foreign object is identified within the gap, and a signal prohibiting train operation is output.

8. The detection method according to claim 5, characterized in that, The processor extracts the pixel contours of linear light sources in each of the light source images, including: The processor performs blurring processing on each of the light source images and converts each of the blurred light source images into a grayscale image. The processor sequentially performs image gradient calculation, binarization, and denoising on each grayscale image to obtain the pixel contour of the linear light source in each light source image.

Images