A method and device for preventing pinching based on a laser radar for a multi-car vehicle platform

Abstract

The application provides a kind of based on laser radar's multi-car vehicle platform anti-pinch method and device, for detecting the laser radar of being pinched between the person or foreign matter of car body and platform shielding door is installed at the position near the connection between car body and car body two sides, this method comprises: the point cloud obtained by laser radar is down-sampled, and the laser point cloud in the preset area is segmented;Again, the laser point cloud is twice secondary down-sampling to obtain first group of key points and second group of key points, and the plane equation of the plane where the platform shielding door is based on first group of key points and second group of key points respectively fitted with multiple plane equations of the plane where multiple car sides are;According to the plane equation obtained, the laser point cloud is executed fine segmentation, and the result of fine segmentation is clustered to detect the person or foreign matter;And estimate the attribute information of person or foreign matter, based on attribute information, execute anti-pinch alarm and control car door opening and closing.

Description

Technical Field

[0001] This invention relates to the field of lidar detection, and in particular to a method and device for preventing pinching of multi-carriage vehicle platforms based on lidar. Background Technology

[0002] Multi-car trains, such as intelligent rail transit (ART) vehicles, typically use three articulated rubber-tired virtual tracks and represent a new form of public transportation. Similar to subway vehicles, there is a gap between the platform screen doors and the train doors after the train enters the station. When there are many passengers entering and exiting the train, there is a possibility of people being trapped between the platform and the train.

[0003] Because of the gap between the platform screen doors and the vehicles, there is a lack of effective and stable methods in the existing technology for detecting foreign objects in the gaps, especially for multi-articulated vehicles. In addition, anti-pinch detection devices for multi-carriage vehicles are generally installed on the platform, which requires the establishment of a wireless communication link between the platform detection device and the entering vehicle. However, the transmission of wireless communication links is subject to time delays and is susceptible to interference.

[0004] To overcome the aforementioned deficiencies in existing technologies, there is an urgent need in this field for a method and device for preventing pinching of multi-carriage vehicles on platform based on lidar. This method involves installing lidar on the side of the multi-articulated vehicle body to effectively detect targets around the vehicle body. By segmenting the original point cloud, the point cloud of the vehicle body and the point cloud of the platform screen door are separated, and the presence of pedestrians or foreign objects between the two can be detected in real time. If any abnormality is detected, a timely warning is issued when the doors close, thereby reducing the occurrence of accidents. Summary of the Invention

[0005] The following provides a brief overview of one or more aspects to offer a basic understanding of them. This overview is not an exhaustive summary of all conceived aspects, nor is it intended to identify key or decisive elements of all aspects, nor to define the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form to prepare for the more detailed descriptions that follow.

[0006] To overcome the aforementioned deficiencies in existing technologies, this invention provides a multi-carriage vehicle platform anti-pinch method based on lidar. The lidar for detecting pedestrians or foreign objects trapped between the vehicle body and the platform screen door is installed on both sides of the vehicle body near the connection between carriages. The method includes: downsampling the point cloud acquired by the lidar to segment the lidar point cloud within a preset area; performing secondary downsampling on the lidar point cloud within the preset area to obtain a first set of key points; fitting the plane equation of the plane where the platform screen door is located based on the first set of key points; and further downsampling the preset area... The laser point cloud within the area is downsampled again to obtain a second set of key points. Based on this second set of key points, multiple plane equations of the planes on which the sides of the multiple carriages are located are fitted. Based on the plane equation of the plane on which the platform screen door is located and the multiple plane equations of the planes on which the sides of the multiple carriages are located, the laser point cloud within the preset area is finely segmented. The results of the fine segmentation are clustered to detect pedestrians or foreign objects sandwiched between the carriage and the platform screen door. The attribute information of the pedestrians or foreign objects sandwiched between the carriage and the platform screen door is estimated. Based on the attribute information, an anti-pinch alarm is executed and the opening and closing of the carriage doors are controlled.

[0007] In one embodiment, preferably, the preset area is a spatial region above the ground and below the vehicle roof. The downsampling of the point cloud acquired by the lidar and segmentation of the laser point cloud within the preset area includes: downsampling and denoising the original point cloud acquired by the lidar based on a three-dimensional voxel method; and removing the point cloud above the ground, curb, and above the vehicle position based on prior knowledge of the installation height of the lidar to obtain the laser point cloud within the preset area.

[0008] In one embodiment, preferably, the secondary downsampling of the laser point cloud in the preset area to obtain the first set of key points includes: obtaining the laser point cloud in the preset area within a vertical distance of 10 to 40 cm from the lidar to perform secondary downsampling; the fitting of the plane equation of the plane where the platform screen door is located based on the first set of key points includes: performing plane fitting on the first set of key points using RANSAC or least squares method to obtain the plane equation of the plane where the platform screen door is located.

[0009] In one embodiment, preferably, the process of performing a second downsampling on the laser point cloud within the preset area to obtain a second set of key points includes: selecting laser point clouds within multiple azimuth angle ranges within the preset area based on the installation position of the lidar on the vehicle body to perform a second downsampling to obtain the second set of key points, where each azimuth angle range corresponds to one side of the vehicle body.

[0010] In one embodiment, preferably, the fine segmentation of the laser point cloud in the preset area based on the plane equation of the plane where the platform screen door is located and the multiple plane equations of the planes where the multiple carriage sides are located includes: determining and filtering out the platform screen door itself and the laser point cloud located on the side of the platform screen door away from the carriage based on the distance of the laser point cloud to the plane where the platform screen door is located; and determining and filtering out the laser point cloud of the carriage based on the distance of the laser point cloud to the planes where the multiple carriage sides are located, so as to retain the laser point cloud between the carriage and the platform screen door in the preset area.

[0011] In one embodiment, preferably, the attribute information of the pedestrian or foreign object includes shape, position, and moving speed; the execution of the anti-pinch alarm and control of the opening and closing of the carriage door based on the attribute information includes: calculating the passage time of the pedestrian or foreign object through the platform screen door and the carriage door based on the moving speed of the pedestrian or foreign object; in response to the current opening of the carriage door, determining whether the passage time is greater than the remaining time for the carriage door to remain open, and if so, executing the anti-pinch alarm and delaying the closing of the carriage door.

[0012] In one embodiment, preferably, the method of performing anti-pinch alarm and controlling the opening and closing of the carriage door based on the attribute information further includes: in response to the carriage door starting to perform a closing operation, detecting whether there is a pedestrian or foreign object between the carriage and the platform screen door; if so, performing the anti-pinch alarm, stopping the carriage door from closing and restoring it to the open state.

[0013] In one embodiment, preferably, the method of executing the anti-pinch alarm and controlling the opening and closing of the carriage door based on the attribute information further includes: in response to the fact that both the carriage door and the platform screen door are closed and the vehicle has not yet started to leave, detecting whether there is a pedestrian or foreign object between the carriage and the platform screen door; if so, executing the anti-pinch alarm, prohibiting the vehicle from starting, and keeping the carriage door and the platform screen door in the closed state.

[0014] Another aspect of the present invention provides a multi-carriage vehicle platform anti-pinch device based on lidar, wherein the lidar for detecting pedestrians or foreign objects trapped between the vehicle body and the platform screen door is installed on both sides of the vehicle body near the connection between the carriages. The multi-carriage vehicle platform anti-pinch device includes: a memory; and a processor coupled to the memory, the processor being configured to perform the steps of any of the above-described lidar-based multi-carriage vehicle platform anti-pinch methods.

[0015] The present invention also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-mentioned LiDAR-based multi-car platform anti-pinch methods. Attached Figure Description

[0016] The above-described features and advantages of the present invention will be better understood after reading the following detailed description of embodiments of the present disclosure in conjunction with the accompanying drawings. In the drawings, components are not necessarily drawn to scale, and components having similar related characteristics or features may have the same or similar reference numerals.

[0017] Figure 1 This is a schematic diagram illustrating the installation position of a lidar in a multi-compartment vehicle according to an embodiment of the present invention;

[0018] Figure 2 This is a schematic flowchart illustrating a method for preventing pinching of multi-carriage vehicles at a platform based on lidar, according to one aspect of the present invention.

[0019] Figure 3 This is a schematic diagram illustrating the principle of pedestrian or foreign object detection in a multi-carriage vehicle platform anti-pinch method based on lidar according to an embodiment of the present invention; and

[0020] Figure 4 This is a schematic diagram of the structure of a multi-carriage vehicle platform anti-pinch device based on lidar, according to another aspect of the present invention.

[0021] For clarity, a brief explanation of the reference numerals in the accompanying drawings is provided below:

[0022] 101 LiDAR

[0023] 102 hinged plate

[0024] Carriage 103

[0025] 301 LiDAR

[0026] 302 Pedestrian Foreign Object

[0027] Side view of carriage 303

[0028] Platform screen door plan of Station 304

[0029] Carriage 305 Detailed Implementation

[0030] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Although the description of the present invention will be presented in conjunction with preferred embodiments, this does not mean that the features of the invention are limited to these embodiments. On the contrary, the purpose of describing the invention in conjunction with embodiments is to cover other options or modifications that may be derived based on the claims of the present invention. To provide a thorough understanding of the invention, many specific details will be included in the following description. The invention may also be implemented without using these details. Furthermore, to avoid confusion or obscuring the focus of the invention, some specific details will be omitted in the description.

[0031] In the description of this 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 based on the specific circumstances.

[0032] Furthermore, the terms "upper," "lower," "left," "right," "top," "bottom," "horizontal," and "vertical" used in the following description should be understood as the orientations shown in the relevant paragraphs and accompanying drawings. These relative terms are for illustrative purposes only and do not imply that the described apparatus must be manufactured or operated in a specific orientation, and therefore should not be construed as limiting the invention.

[0033] It is understood that although terms such as "first," "second," and "third" may be used herein to describe various components, regions, layers, and / or parts, these components, regions, layers, and / or parts should not be limited by these terms, and these terms are only used to distinguish different components, regions, layers, and / or parts. Therefore, the first components, regions, layers, and / or parts discussed below may be referred to as second components, regions, layers, and / or parts without departing from some embodiments of the present invention.

[0034] To overcome the aforementioned deficiencies in the existing technology, this invention provides a method and device for preventing pinching of multi-carriage vehicles at platform stations based on lidar. The lidar is installed on the side of the multi-articulated vehicle body to effectively detect targets around the vehicle body. By segmenting the original point cloud, the point cloud of the vehicle body and the point cloud of the platform screen door are separated, and the presence of pedestrians or foreign objects between the two is detected in real time. Once an abnormality is detected, a timely warning is issued when the doors close, thereby reducing the occurrence of accidents.

[0035] In the multi-carriage vehicle platform anti-pinch method and device based on lidar provided by this invention, the lidar used to detect pedestrians or foreign objects trapped between the vehicle body and the platform screen door is installed on both sides of the vehicle body near the connection between the carriages. This can be referenced in conjunction with other relevant documents. Figure 1 .

[0036] Figure 1 This is a schematic diagram illustrating the installation position of a lidar in a multi-compartment vehicle according to an embodiment of the present invention.

[0037] In this embodiment, the multiple carriages 103 in a multi-carriage vehicle are connected by articulated plates 102, making it a multi-articulated vehicle. Because the different carriages in a multi-articulated vehicle may have different postures, in this case, the sensors in one carriage cannot cover all areas of the vehicle's sides, creating blind spots.

[0038] To ensure blind-spot-free lateral coverage of the vehicle, in this embodiment of the three-compartment articulated vehicle, the lidar 101 is positioned on the sides of the first and third compartments 103 near the articulation plate 102, extending slightly outwards to a height approximately equal to the height of the rearview mirror. The lidar 101 can be a mechanically rotating radar with a horizontal field of view of 360°. This arrangement effectively covers the entire area around the vehicle, ensuring virtually no blind spots even during sharp turns on the vehicle's outer sides.

[0039] It should be noted that the multi-articulated vehicle described here is merely an example to better illustrate the installation position of the lidar in the method provided by this invention, and is not intended to limit the scope of protection of this invention. In fact, for other types of multi-carriage vehicles, the lidar can be installed on both sides of the vehicle body at the transition between multiple carriages, thereby providing better coverage of the gaps between carriages and meeting the detection requirements.

[0040] Figure 2 This is a schematic flowchart illustrating a method for preventing pinching of multi-carriage vehicles at a platform based on lidar, according to one aspect of the present invention.

[0041] Please refer to Figure 2 The multi-car platform anti-pinch method 200 based on lidar provided by the present invention may include:

[0042] Step 201: Downsample the point cloud acquired by the lidar to segment the lidar point cloud within the preset area.

[0043] In one embodiment, the preset area is a spatial region above the ground and below the vehicle roof. The step of downsampling the point cloud acquired by the lidar and segmenting the lidar point cloud within the preset area may include: downsampling and denoising the original point cloud acquired by the lidar based on a three-dimensional voxel method, thereby reducing the computational load of subsequent segmentation.

[0044] Based on prior knowledge of the lidar's installation height, point clouds from the ground, curbs, and areas above the vehicle's position are removed to obtain the lidar point cloud within the preset area. Using this prior knowledge to make a preliminary estimate of the platform screen door's location can improve the accuracy of foreign object detection between the train car and the platform screen door, and reduce the probability of false alarms.

[0045] Please continue to refer to this. Figure 2 The multi-car platform anti-pinch method 200 based on lidar provided by the present invention may further include:

[0046] Step 202: Perform secondary downsampling on the laser point cloud in the preset area to obtain the first set of key points, and fit the plane equation of the plane where the platform screen door is located based on the first set of key points.

[0047] In one embodiment, the secondary downsampling of the laser point cloud within the preset area to obtain the first set of key points may include: acquiring the laser point cloud within the preset area that is 10 to 40 cm vertically away from the lidar to perform secondary downsampling. It is readily understood that the distance between the carriage and the platform screen door is assumed to be between 10 and 40 cm, thus initially dividing the point cloud positions, reducing computational load and improving detection accuracy.

[0048] The process of fitting the plane equation of the platform screen door based on the first set of key points may include: performing plane fitting on the first set of key points using RANSAC or least squares method to obtain the plane equation of the platform screen door.

[0049] It should be noted that the specific plane fitting method is not intended to limit the scope of protection of this invention. Any related plane fitting methods applicable to this invention can be applied to the multi-carriage vehicle platform anti-pinch method based on lidar provided by this invention, and should be included within the scope of protection of this invention.

[0050] Please continue to refer to this. Figure 2 The multi-car platform anti-pinch method 200 based on lidar provided by the present invention may further include:

[0051] Step 203: Perform a second downsampling on the laser point cloud in the preset area to obtain a second set of key points, and fit multiple plane equations of the planes on the sides of the carriages based on the second set of key points.

[0052] In one embodiment, the process of performing a second downsampling on the laser point cloud within the preset area to obtain a second set of key points may include: selecting laser point clouds within multiple azimuth angle ranges in the preset area based on the installation position of the lidar on the vehicle body to perform a second downsampling to obtain the second set of key points, where each azimuth angle range corresponds to one side of the vehicle body.

[0053] It's easy to understand that, in order to effectively detect foreign objects between the car and the platform screen doors after a multi-articulated vehicle has stopped at the platform, it's also necessary to determine the attitude of each car. The car's attitude can be provided by the vehicle control system or estimated by LiDAR; here, selecting the LiDAR azimuth range takes into account the different car attitudes. Since different cars have different attitudes, by selecting multiple azimuth ranges, multiple different three-dimensional plane equations corresponding to multiple cars can be obtained.

[0054] Please continue to refer to this. Figure 2 The multi-car platform anti-pinch method 200 based on lidar provided by the present invention may further include:

[0055] Step 204: Perform fine segmentation of the laser point cloud in the preset area based on the plane equation of the plane where the platform screen door is located and the multiple plane equations of the planes where the multiple carriage sides are located. Perform clustering processing on the fine segmentation results to detect the pedestrian or foreign object sandwiched between the carriage and the platform screen door.

[0056] You can refer to the following: Figure 3 , Figure 3 This is a schematic diagram illustrating the principle of pedestrian or foreign object detection in a multi-car platform anti-pinch method based on lidar according to an embodiment of the present invention.

[0057] like Figure 3 As shown, in this embodiment, the installation positions of the lidar 301 and the carriage 305 are... Figure 1 The same applies. A pedestrian object 302 is sandwiched between the side plane 303 of the carriage and the platform screen door plane 304. Detecting this object requires precise spatial segmentation of the laser point cloud acquired by the lidar 301 to improve detection accuracy.

[0058] In essence, the purpose of point cloud segmentation is to precisely separate the ground point cloud, the carriage point cloud, and the platform screen door point cloud, leaving only the point cloud in the three-dimensional space between the carriage and the platform screen door. In one embodiment, the fine segmentation of the laser point cloud within a preset area based on the plane equation of the plane where the platform screen door is located and the multiple plane equations of the planes where the sides of the multiple carriages are located may include: determining and filtering out the platform screen door itself and the laser point cloud located on the side of the platform screen door away from the carriage based on the distance of the laser point cloud to the plane where the platform screen door is located; and determining and filtering out the laser point cloud of the carriage based on the distance of the laser point cloud to the planes where the sides of the multiple carriages are located, so as to retain the laser point cloud between the carriage and the platform screen door within the preset area.

[0059] For example, after obtaining the three-dimensional planar equation of the platform screen doors, the laser point cloud above the ground and below the roof is precisely segmented. Point clouds whose distance from the three-dimensional plane is less than a threshold are considered platform screen door point clouds and are filtered out. At the same time, point clouds on the side of the three-dimensional plane of the screen doors away from the carriages are also filtered out. A similar method is used to filter out laser point clouds for the planar equations of multiple carriage sides, ultimately retaining only the point clouds above the ground, below the roof, and between the carriages and the screen doors.

[0060] After performing fine segmentation, the point cloud between the carriage and the platform screen door is clustered. The specific clustering method can include, for example, Euclidean clustering or clustering based on point cloud density. This invention does not limit the choice of specific point cloud clustering method. Clustering methods that can achieve similar effects can be applied to the multi-carriage vehicle platform anti-pinch method based on lidar provided by this invention.

[0061] Please return to Figure 2 The multi-car platform anti-pinch method 200 based on lidar provided by the present invention may further include:

[0062] Step 205: Estimate the attribute information of the pedestrian or foreign object stuck between the train car and the platform screen door, and execute the anti-pinch alarm and control the opening and closing of the car door based on the attribute information.

[0063] In one embodiment, the attribute information of the pedestrian or object may include shape, location, and speed. The shape, location, and speed of the pedestrian or object can be estimated by estimating the shape, location, and speed of the clustered point cloud. For example, the shape can be used to roughly determine whether it is a pedestrian or an object, as well as the general shape of the pedestrian or the size of the object, thus allowing for a preliminary identification of its type.

[0064] It is easy to understand that since it is reasonable for foreign objects to exist between the platform screen doors and the carriages during passenger boarding and alighting, the detection of foreign objects between the carriages and the platform screen doors does not immediately trigger an alarm. Instead, it is necessary to make a comprehensive judgment based on the timing of the vehicle's door opening and closing and the behavior of the foreign object.

[0065] Therefore, in one embodiment, the execution of the anti-pinch alarm and control of the opening and closing of the carriage door based on the attribute information may include: calculating the passage time of the pedestrian or foreign object through the platform screen door and the carriage door based on the moving speed of the pedestrian or foreign object; in response to the current opening of the carriage door, determining whether the passage time is greater than the remaining time for the carriage door to remain open, and if so, executing the anti-pinch alarm and delaying the closing of the carriage door.

[0066] The method of performing anti-pinch alarm and controlling the opening and closing of the carriage door based on the attribute information may also include: in response to the carriage door starting to perform a closing operation, detecting whether there is a pedestrian or foreign object between the carriage and the platform screen door; if so, executing the anti-pinch alarm, stopping the carriage door from closing and restoring it to the open state.

[0067] In one embodiment, the method of performing the anti-pinch alarm and controlling the opening and closing of the carriage door based on the attribute information may further include: in response to the fact that both the carriage door and the platform screen door are closed and the vehicle has not yet started to leave, detecting whether there is a pedestrian or foreign object between the carriage and the platform screen door; if so, performing the anti-pinch alarm, prohibiting the vehicle from starting, and keeping the carriage door and the platform screen door in the closed state.

[0068] Keeping the carriage door and the platform screen door closed can prevent secondary injuries, while continuously sounding an alarm to request the driver and platform management personnel to handle the situation, thereby minimizing the probability of an accident.

[0069] The multi-car platform anti-pinch method based on lidar provided by this invention can effectively reduce the risk of people or foreign objects being pinched during the closing process of multi-articulated vehicles on the platform. It uses on-board sensors for detection and can be directly linked with the vehicle control system. Compared with the existing anti-pinch methods, it can reduce the interference of station ground wireless communication.

[0070] Although the methods described above are illustrated and depicted as a series of actions for the sake of simplicity, it should be understood and appreciated that these methods are not limited by the order of the actions, as some actions may occur in a different order and / or concurrently with other actions from the illustrations and descriptions herein or not illustrated and described herein but which may be understood by those skilled in the art, according to one or more embodiments.

[0071] Figure 4 This is a schematic diagram of the structure of a multi-carriage vehicle platform anti-pinch device based on lidar, according to another aspect of the present invention.

[0072] According to another aspect of the present invention, an embodiment of a multi-car platform anti-pinch device 400 based on lidar is also provided herein.

[0073] like Figure 4 As shown, the multi-car platform anti-pinch device 400 based on lidar provided in this embodiment may include a memory 401 and a processor 402 coupled to the memory 401. The processor 402 may be configured to implement the steps of any of the above-described lidar-based multi-car platform anti-pinch methods.

[0074] According to another aspect of the invention, an embodiment of a computer storage medium is also provided herein.

[0075] The computer storage medium contains a computer program. When executed by a processor, this computer program can implement the steps of any of the aforementioned lidar-based anti-pinch methods for multi-carriage vehicle platforms.

[0076] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps are described above in a generalized manner in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in different ways for each specific application, but such implementation decisions should not be construed as departing from the scope of the invention.

[0077] The processors described herein can be implemented using electronic hardware, computer software, or any combination thereof. Whether such processors are implemented as hardware or software will depend on the specific application and the overall design constraints imposed on the system. As an example, the processors, any portion thereof, or any combination thereof presented in this disclosure can be implemented using microprocessors, microcontrollers, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gated logic, discrete hardware circuitry, and other suitable processing components configured to perform the various functions described throughout this disclosure. The functionality of the processors, any portion thereof, or any combination thereof presented in this disclosure can be implemented using software executed by a microprocessor, microcontroller, DSP, or other suitable platform.

[0078] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of both. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor such that the processor can read and write information to / from the storage medium. In an alternative, the storage medium may be integrated into the processor. The processor and storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and storage medium may reside as discrete components in the user terminal.

[0079] In one or more exemplary embodiments, the described functionality may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functionality may be stored or transmitted as one or more instructions or code on or through a computer-readable medium. A computer-readable medium includes both computer storage media and communication media, encompassing any medium that facilitates the transfer of a computer program from one location to another. A storage medium may be any available medium accessible to a computer. By way of example and not limitation, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and is accessible to a computer. Any connection is also legitimately referred to as a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of a medium. As used in this article, disk and disc include compact discs (CDs), laser discs, optical discs, digital multi-purpose discs (DVDs), floppy disks, and Blu-ray discs. Disks typically reproduce data magnetically, while discs reproduce data optically using lasers. Combinations of these should also be included within the scope of computer-readable media.

[0080] The prior description of this disclosure is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to this disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not intended to be limited to the examples and designs described herein, but should be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for preventing pinching of multi-carriage vehicles at a platform based on lidar, wherein the lidar for detecting pedestrians or foreign objects pinched between the vehicle body and the platform screen doors is installed on both sides of the vehicle body near the connection between the carriages, and the method includes: The point cloud acquired by the lidar is downsampled to segment the lidar point cloud within a preset area; The laser point cloud in the preset area is downsampled a second time to obtain the first set of key points, and the plane equation of the plane where the platform screen door is located is fitted based on the first set of key points. The laser point cloud within the preset area is downsampled again to obtain a second set of key points, and multiple plane equations of the planes on which the sides of the carriages are located are fitted based on the second set of key points. Based on the plane equations of the plane where the platform screen doors are located and the plane equations of the planes where the sides of the multiple carriages are located, fine segmentation is performed on the laser point cloud within the preset area. The results of this fine segmentation are then clustered to detect pedestrians or foreign objects sandwiched between the carriage and the platform screen doors. Estimate the attribute information of the pedestrian or foreign object trapped between the train car and the platform screen door, and execute the anti-pinch alarm and control the opening and closing of the car door based on the attribute information.

2. The method for preventing multi-carriage vehicle platform pinching as described in claim 1, characterized in that, The preset area is the spatial region above the ground and below the vehicle roof. The step of downsampling the point cloud acquired by the lidar to segment the lidar point cloud within the preset area includes: The original point cloud acquired by the lidar is downsampled and denoised using a three-dimensional voxel method; and Based on prior knowledge of the installation height of the lidar, point clouds on the ground, curbs, and above the vehicle position are removed to obtain the lidar point cloud within the preset area.

3. The method for preventing multi-carriage vehicle platform pinching as described in claim 2, characterized in that, The step of performing secondary downsampling on the laser point cloud within the preset area to obtain the first set of key points includes: Acquire laser point clouds within the preset area that are 10 to 40 cm vertically away from the lidar to perform secondary downsampling; The fitting of the plane equation of the plane where the platform screen door is located based on the first set of key points includes: The first set of key points is fitted with RANSAC or least squares method to obtain the plane equation of the plane where the platform screen door is located.

4. The method for preventing multi-carriage vehicle platform pinching as described in claim 2, characterized in that, The step of performing a second downsampling on the laser point cloud within the preset area to obtain a second set of key points includes: Based on the installation position of the lidar on the vehicle body, a second downsampling is performed on the laser point cloud within a multiple azimuth angle range in the preset area to obtain the second set of key points, with one azimuth angle range corresponding to one side of the vehicle body.

5. The method for preventing multi-carriage vehicle platform pinching as described in claim 1, characterized in that, The step of performing fine segmentation of the laser point cloud within the preset area based on the plane equation of the plane where the platform screen door is located and the multiple plane equations of the planes where the multiple carriage sides are located includes: Based on the distance from the laser point cloud to the plane where the platform screen door is located, determine and filter out the platform screen door itself and the laser point cloud located on the side of the platform screen door away from the carriage; and Based on the distance from the laser point cloud to the plane where the sides of the multiple carriages are located, the laser point cloud of the carriages is determined and filtered out, so as to retain the laser point cloud between the carriages and the platform screen doors in the preset area.

6. The method for preventing multi-carriage vehicle platform pinching as described in claim 1, characterized in that, The attribute information of the pedestrian or object includes shape, location, and speed of movement; The step of executing the anti-pinch alarm and controlling the opening and closing of the carriage door based on the attribute information includes: The passage time of the pedestrian or object through the platform screen doors and carriage doors is calculated based on the moving speed of the pedestrian or object. In response to the current opening of the carriage door, it is determined whether the passage time is greater than the remaining time for the carriage door to remain open. If so, the anti-pinch alarm is executed and the closing of the carriage door is delayed.

7. The method for preventing multi-carriage vehicle platform pinching as described in claim 6, characterized in that, The step of executing the anti-pinch alarm and controlling the opening and closing of the carriage door based on the attribute information also includes: In response to the start of the closing operation of the carriage door, the system detects whether there is a pedestrian or foreign object between the carriage and the platform screen door. If so, the anti-pinch alarm is activated, the carriage door stops closing and returns to the open state.

8. The method for preventing multi-carriage vehicle platform pinching as described in claim 6, characterized in that, The step of executing the anti-pinch alarm and controlling the opening and closing of the carriage door based on the attribute information also includes: In response to the fact that both the carriage door and the platform screen door are closed and the vehicle has not yet started to leave, the system detects whether there is a pedestrian or foreign object between the carriage and the platform screen door. If so, the system executes the anti-pinch alarm, prohibits the vehicle from starting, and keeps the carriage door and the platform screen door closed.

9. A multi-carriage vehicle platform anti-pinch device based on lidar, wherein the lidar for detecting pedestrians or foreign objects trapped between the vehicle body and the platform screen doors is installed on both sides of the vehicle body near the connection between carriages, the multi-carriage vehicle platform anti-pinch device comprising: Memory; as well as A processor coupled to the memory, the processor being configured to perform the steps of any one of the lidar-based anti-pinch methods for multi-carriage vehicle platforms according to claims 1 to 8.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of any one of the lidar-based anti-pinch methods for multi-carriage vehicle platforms as described in claims 1 to 8.

Images