LiDAR-based train door control method, device, and controller

Abstract

This application relates to the field of lidar detection technology and provides a lidar-based train door control method, device, and controller, including: before closing each train door, acquiring a point cloud collected by a detection device and an image collected by an image sensor for each platform screen door; if the point cloud is a point cloud of a preset shape and the image is a target image, then determining that there are no foreign objects in the gap between the platform screen door corresponding to the detection device and the train door; and controlling the train door to close. This application improves the accuracy of foreign object detection in subway gaps by using the acquired point cloud and image, thus ensuring train operation safety.

Description

Technical Field

[0001] This application belongs to the field of lidar detection technology, and in particular relates to a lidar-based train door control method, device and controller. Background Technology

[0002] In the development of rail transit, in order to improve the safety of driverless trains, it is necessary to conduct foreign object detection on the gap between the platform screen doors and the train doors in a timely manner to avoid situations where passengers or items get caught in the gap.

[0003] In existing technologies, cameras are typically installed above the platform screen doors of subway stations to capture images of the gap between the platform screen doors and the train doors. These images are then processed by backend monitoring equipment to determine if any foreign objects are present in the gap. However, due to the long distance and insufficient lighting conditions between subway doors and platforms, images captured by cameras can be significantly inaccurate when there is insufficient light or interference from other light sources. This results in low accuracy for the backend monitoring equipment in detecting foreign objects, impacting subway safety. Summary of the Invention

[0004] This application provides a train door control method, device, and controller based on lidar. By detecting foreign objects in the gaps between trains based on collected point clouds and images, the accuracy of detection is improved, ensuring the safety of train operation.

[0005] In a first aspect, embodiments of this application provide a train door control method based on lidar, applied to a controller of a subway detection system. The subway detection system further includes multiple detection devices and multiple image sensors. Each platform screen door of the subway is equipped with a detection device and an image sensor. The controller is connected to each of the detection devices and each of the image sensors. The detection range of each detection device covers at least the sliding door head of a train door and the platform screen door head adjacent to the sliding door head.

[0006] Before closing each of the train doors, for each of the platform screen doors, the point cloud collected by the detection device and the image collected by the image sensor are obtained;

[0007] If the point cloud is a point cloud of a preset shape and the image is a target image, then it is determined that there are no foreign objects in the gap between the platform screen door and the train door corresponding to the detection device. The point cloud of the preset shape is a straight point cloud, and the target image is a gap image collected when there are no foreign objects in the gap between the platform screen door and the train door.

[0008] Control the closing of the train doors.

[0009] It should be understood that the detection device in this application is a lidar, used to collect point clouds of the gap between the train doors and the platform screen doors.

[0010] In one possible implementation of the first aspect, after obtaining the point cloud acquired by the detection device and the image acquired by the image sensor, the method further includes:

[0011] If the point cloud is not a point cloud of the preset shape, and / or the image is not an image of the target image, then it is determined that there is a foreign object in the gap between the platform screen door and the train door corresponding to the detection device.

[0012] Control the opening of the train doors.

[0013] In one possible implementation of the first aspect, after determining that a foreign object exists in the gap between the platform screen door and the train door corresponding to the detection device, the method further includes:

[0014] The anomaly number is determined based on the number of the shielding door containing the foreign object;

[0015] An alarm message containing at least one of the abnormal numbers is sent to the alarm platform so that the alarm platform can indicate that there is a foreign object in the gap between the platform screen door and the train door corresponding to each of the abnormal numbers.

[0016] One possible implementation of the first aspect also includes:

[0017] For each of the shielding doors, a first point cloud and a second point cloud are obtained by the detection device within a preset time period, wherein the first point cloud contains multiple first point clouds and the second point cloud contains multiple second point clouds.

[0018] Based on the point cloud of the preset shape, at least one boarding time window and at least one alighting time window are selected from the first point cloud set and the second point cloud set.

[0019] The passenger flow of the carriage corresponding to the detection device is determined based on the number of boarding time windows and the number of alighting time windows included in the preset time period.

[0020] The first passenger flow within the preset time period is determined based on the passenger flow of multiple carriages.

[0021] One possible implementation of the first aspect also includes:

[0022] Anomaly point clouds are filtered out from the first point cloud and the second point cloud, wherein the anomaly

[0023] The point cloud is a point cloud that does not belong to the preset shape, and the abnormal point cloud contains two or more preset 0-width point clouds;

[0024] Accordingly, determining the passenger flow of the carriage corresponding to the detection device based on the number of boarding time windows and the number of alighting time windows included in the preset time period includes:

[0025] If the second point cloud of the previous time interval within the boarding time window is an abnormal point cloud, the number of people corresponding to the boarding time window is determined according to the number of the preset width point cloud contained in the second point cloud; 5 If the first point cloud of the previous time interval within the alighting time window is an abnormal point cloud, the number of people corresponding to the alighting time window is determined according to the number of the preset width point cloud contained in the first point cloud.

[0026] The number of passengers boarding is determined based on the number of passengers in each boarding time window within the preset time period, and the number of passengers alighting is determined based on the number of passengers in each alighting time window within the preset time period.

[0027] 0. The passenger flow of the carriage corresponding to the detection device is determined based on the number of passengers boarding and disembarking within a preset time period.

[0028] In one possible implementation of the first aspect, the preset time period is a train stopping time period, and after determining the first passenger flow within the preset time period based on the passenger flow of multiple carriages, the method further includes:

[0029] 5. Obtain the first passenger flow corresponding to each of the train stopping time periods;

[0030] The number of passengers inside the train is determined by the sum of the first passenger flow corresponding to multiple train stopping time periods.

[0031] If the number of passengers is greater than or equal to the first preset number, an early warning message will be sent to the alarm platform so that train staff can manage passenger flow based on the early warning message.

[0032] In one possible implementation of the first aspect, determining the first passenger flow within the preset time period based on passenger flow in multiple carriages further includes:

[0033] If the first passenger flow is greater than or equal to the second preset number within the preset time period, then the set of door images collected by the image sensor within the preset time period is obtained, wherein the set of door images includes at least one door image when the train is open.

[0034] For each of the aforementioned detection devices, each of the vehicle door images in the set of vehicle door images collected by the detection device is detected according to a preset target detection model to obtain the second passenger flow.

[0035] The number of passengers in the train during the preset time period is determined based on the first passenger flow and the second passenger flow.

[0036] Secondly, embodiments of this application provide a train door control device based on lidar, comprising:

[0037] 5. Acquisition module, used to acquire detection equipment for each platform screen door before each train door closes.

[0038] Point clouds collected by the device and images collected by the image sensor;

[0039] The determination module is used to determine that if the point cloud is a point cloud of a preset shape and the image is a target image, then there are no foreign objects in the gap between the platform screen door and the train door corresponding to the detection device.

[0040] Wherein, the point cloud of the preset shape is a straight point cloud, and the target image is a gap image collected when there are no foreign objects in the gap between the platform screen door and the train door;

[0041] The control module is used to control the closing of the train doors.

[0042] Thirdly, embodiments of this application provide a controller, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor performs the...

[0043] The computer program implements the laser radar-based train door control method as described in any of the first aspects.

[0044] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, perform the train door control method based on lidar as described in any of the first aspects.

[0045] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.

[0046] The beneficial effects of this application embodiment compared with the prior art are as follows: before closing each train door, for each platform screen door, a point cloud collected by the detection device and an image collected by the image sensor are obtained; if the point cloud is a point cloud of a preset shape and the image is the target image, it is determined that there are no foreign objects in the gap between the platform screen door corresponding to the detection device and the train door; and the train door is controlled to close. This application improves the accuracy of foreign object detection in subway gaps by collecting point clouds and images, thus ensuring the safety of train operation. Attached Figure Description

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

[0048] Figure 1 This is a schematic diagram of the structure of the subway detection system provided in the embodiments of this application. Figure 1 ;

[0049] Figure 2 This is a schematic diagram of the structure of the subway detection system provided in the embodiments of this application. Figure 2 ;

[0050] Figure 3 This is a schematic diagram of the installation of the detection device provided in the embodiments of this application;

[0051] Figure 4 This is a flowchart illustrating the train door control method based on lidar provided in the embodiments of this application. Figure 1 ;

[0052] Figure 5 This is a flowchart illustrating the train door control method based on lidar provided in the embodiments of this application. Figure 2 ;

[0053] Figure 6 This is a flowchart illustrating the train door control method based on lidar provided in the embodiments of this application. Figure 3 ;

[0054] Figure 7 This is a schematic diagram of the scanning angle of the lidar provided in the embodiments of this application;

[0055] Figure 8 This is a flowchart illustrating the train door control method based on lidar provided in the embodiments of this application. Figure 4 ;

[0056] Figure 9This is a flowchart illustrating the train door control method based on lidar provided in the embodiments of this application. Figure 5 ;

[0057] Figure 10 This is a flowchart illustrating the train door control method based on lidar provided in the embodiments of this application. Figure 6 ;

[0058] Figure 11 This is a structural block diagram of a train door control device based on lidar provided in an embodiment of this application;

[0059] Figure 12 This is a schematic diagram of the controller provided in the embodiments of this application. Detailed Implementation

[0060] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0061] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0062] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0063] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0064] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0065] References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized.

[0066] See Figure 1 This is a schematic diagram of the structure of the subway detection system provided in the embodiments of this application. Figure 1 .like Figure 1 As shown, the subway detection system includes a controller 101, multiple detection devices 102, and multiple image sensors 103. Each detection device 102 and each image sensor 103 is connected to the controller 101. Specifically, the detection device 102 is a multi-line lidar used to collect point clouds of the detection space. Specifically, the image sensor is a camera used to capture images of the train door locations. Each image sensor is sequentially connected to a communication network via a network cable, transmitting the collected images to the controller through the network. Specifically, the detection device 102 is connected to the controller 101 via a bus. For example, the bus is an RS485 bus, a CAN bus, or a PROFIBUS bus.

[0067] See Figure 2 This is a schematic diagram of the structure of the subway detection system provided in the embodiments of this application. Figure 2 For example, the subway detection system also includes a power supply device 104. Specifically, the power supply device is connected to each detection device 102 and each image sensor 103 respectively, for supplying power to each detection device 102 and each image sensor 103. Specifically, the power supply device 104 outputs a safe voltage, and the power supply method is local centralized power supply. Specifically, the power supply device 104 is a switching power supply, capable of outputting a voltage of 24V, 36V, or 48V, wherein the power supply cables are all halogen-free, low-smoke, flame-retardant wires.

[0068] For example, the subway detection system also includes an alarm platform 105 for displaying the detection results of the subway detection system and timely alerting passengers to the presence of foreign objects in the gaps between trains.

[0069] See Figure 3 This is a schematic diagram of the installation of the detection device provided in the embodiments of this application. Figure 3As shown in the embodiment of this application, the detection device is a detection equipment. N detection devices are installed on the train, numbered 1, 2, 3…N, where N is a positive integer greater than 1. Each detection device is installed within the gap between each platform screen door and the train door. Specifically, the number of detection devices is the same as the number of train doors. Each detection device is installed below the inner top beam of the platform screen door and fixed using expansion bolts and a dedicated bracket. The detection range of the detection device installed on each platform screen door head covers at least the area of ​​the current train door head sliding door and the adjacent two platform screen door heads on either side.

[0070] Figure 4 This is a flowchart illustrating the train door control method based on lidar provided in the embodiments of this application. Figure 1 As an example and not a limitation, the execution subject of this embodiment is... Figure 1 The controller in this embodiment is not particularly limited here.

[0071] S401: Before closing each train door, obtain point cloud data collected by the detection device and image data collected by the image sensor for each platform screen door.

[0072] In this embodiment, the subway detection system completes system initialization after power-on. After the train arrives at the station and stops, and after the train doors close at the scheduled closing time, before the subway platform screen doors close, each detection device is controlled to scan the gap between the current platform screen door and the corresponding train door, and the image sensor is controlled to capture an image of the gap between the current platform screen door and the corresponding train door.

[0073] S402: If the point cloud is a point cloud of a preset shape and the image is the target image, then it is determined that there are no foreign objects in the gap between the platform screen door and the train door corresponding to the detection device. The point cloud of the preset shape is a straight point cloud, and the target image is the gap image collected when there are no foreign objects in the gap between the platform screen door and the train door.

[0074] In this embodiment, before the platform screen door closes, the lidar continuously emits detection signals into the corresponding train gap space and determines the measured point cloud based on the echo signals reflected back from the train gap space. The point cloud collected by the detection device is processed. If the point cloud is a point cloud of a preset shape (i.e., a straight-line point cloud) and the image is determined to be the target image, it is determined that there are no foreign objects in the gap between the platform screen door and the train door corresponding to the detection device. Specifically, the target image is the gap image collected when there are no foreign objects in the gap between the platform screen door and the train door.

[0075] It should be noted that the image sensor captures an image of the gap between the platform screen door and the train door. The target image is the image captured by the image sensor when there are no foreign objects in the gap between the platform screen door and the train door. Specifically, the image recognition model detects the captured image of the gap between the platform screen door and the train door to confirm whether there are any human head features in the captured image. If no head features are detected in the image, it is determined that no human head features were detected in the image of the gap between the platform screen door and the train door corresponding to the detection device, that is, the captured image is the target image, and it can be confirmed that there are no foreign objects in the gap between the platform screen door and the train door corresponding to the detection device. It should be noted that the training process of the image recognition model is existing technology and will not be described in detail here.

[0076] S403: Control the closing of train doors.

[0077] In this embodiment of the application, when it is confirmed from the point cloud and image that there are no foreign objects in the gap between the trains, the doors of each train are controlled to close in a timely manner according to the closing time set by the train.

[0078] In one possible implementation, if the point cloud is not a point cloud of a preset shape, and / or the image is not an image of the target image, then it is determined that there is a foreign object in the gap between the platform screen door and the train door corresponding to the detection device. To avoid affecting passenger safety due to forced door closure, the train door containing the foreign object is opened in a timely manner.

[0079] The train door control method based on lidar provided in this application utilizes a detection device installed in the gap between each platform screen door and the train door to collect point clouds of the gap and an image sensor to collect images of the gap. If the point cloud is a straight point cloud and the image is determined to be a target image, it is determined that there are no foreign objects in the gap, and the train door is opened or closed in a timely manner. This application improves the accuracy of foreign object detection in the gap by using the collected point clouds and images, thus ensuring the safety of train operation.

[0080] Figure 5 This is a flowchart illustrating the train door control method based on lidar provided in the embodiments of this application. Figure 2 .exist Figure 4 Based on the implementation examples, such as Figure 5 As shown, the handling procedure for foreign objects present in the gaps between trains in this application is as follows:

[0081] S501: Determine the anomaly number based on the number of the shielding door containing the foreign object.

[0082] For example, the detection device for acquiring the target image is identified, and the door number corresponding to the detection device is used as the anomaly number indicating the presence of foreign objects. It should be noted that when it is determined that at least one train gap contains a foreign object, the anomaly number needs to be determined based on the number of the platform screen door containing the foreign object. Each train gap corresponding to an anomaly number should then be further inspected to confirm the presence of the foreign object.

[0083] S502: Send an alarm message containing at least one abnormality number to the alarm platform so that the alarm platform can indicate that there is a foreign object in the gap between the platform screen door and the train door corresponding to each abnormality number.

[0084] For example, the controller sends alarm information containing all anomaly numbers to the alarm platform of the subway detection system. The alarm platform displays a prompt message, reminding management personnel that there are foreign objects in the gaps between trains corresponding to each anomaly number, and further inspection must be carried out in a timely manner.

[0085] The train door control method based on lidar provided in this application sends an alarm message containing an anomaly number to the alarm platform after determining that there is a foreign object in the gap of the subway, so as to remind the station staff to deal with the abnormal situation in a timely manner and ensure the safety of passengers and the safe operation of the train.

[0086] Figure 6 This is a flowchart illustrating the train door control method based on lidar provided in the embodiments of this application. Figure 3 As an example and not a limitation, the execution subject of this embodiment is... Figure 1 The controller in this embodiment is not particularly limited here.

[0087] S601: For each platform screen door, within a preset time period, obtain the first point cloud and the second point cloud collected by the detection device, wherein the first point cloud contains multiple first point clouds and the second point cloud contains multiple second point clouds.

[0088] Figure 7 This is a schematic diagram of the scanning angle of the lidar provided in an embodiment of this application. For example... Figure 7 As shown in the embodiments of this application, each detection device includes multiple light-emitting devices, and each light-emitting device can emit a laser beam at a set angle. Figure 7As shown, the current detection device can emit laser beams at four angles: a first laser beam 701, a second laser beam 702, a third laser beam 703, and a fourth laser beam 704. For example, the first laser beam 701 is emitted at an angle of 77 degrees clockwise along the horizontal plane, the second laser beam 702 at an angle of 87 degrees clockwise along the horizontal plane, the third laser beam 703 at an angle of 97 degrees clockwise along the horizontal plane, and the fourth laser beam 704 at an angle of 107 degrees clockwise along the horizontal plane. It should be understood that each laser beam performs a 360-degree rotational scan within a plane according to the set emission angle.

[0089] In the embodiments of this application, from Figure 7 The four laser beams selected are a first-angle laser beam and a second-angle laser beam. The first-angle laser beam is closer to the train platform screen door, while the second-angle laser beam, relative to the first-angle laser beam, is closer to the train carriage.

[0090] In some possible real-time scenarios, the laser beam at the first angle can be set to 701, while the laser beam at the second angle can be set to 702, 703, or 704.

[0091] In some possible real-time scenarios, the laser beam at the first angle can be set to 701 or 702, while the laser beam at the second angle can be set to 703 or 704.

[0092] In some possible real-time scenarios, the laser beam at the first angle can be set to 701, 702 or 703, while the laser beam at the second angle can be set to 704.

[0093] In this embodiment of the invention, for example, the preset time period is the time during which the train opens its doors at the subway station. Specifically, within a single time period during which the doors are open, a detection device emits a laser beam at a first angle according to a preset frequency to obtain a first point cloud, and the detection device emits a laser beam at a second angle according to a preset frequency to obtain a second point cloud. For example, the first point cloud contains multiple first point clouds, and the second point cloud contains multiple second point clouds. It should be understood that each first point cloud is the point cloud corresponding to the train door captured after a 360-degree scan of a plane by a laser beam at the first angle, and each second point cloud is the point cloud corresponding to the train door captured after a 360-degree scan of a plane by a laser beam at the second angle.

[0094] S602: Based on the point cloud of the preset shape, at least one boarding time window and at least one alighting time window are selected from the first point cloud set and the second point cloud set.

[0095] In this embodiment, the size of the time window is determined based on the sampling frequency of the detection device. For example, when the sampling frequency of the detection device is 15Hz, the size of the time window can be set to 8 seconds.

[0096] Furthermore, a first point cloud set and its idle point clouds are determined based on a preset shape point cloud. For example, the preset shape point cloud is a straight-line point cloud. It should be noted that when the vehicle door is open and no passengers are boarding or alighting, the first point cloud collected by a laser beam at a first angle scanning 360 degrees along a plane is a straight line, and the second point cloud collected by a laser beam at a second angle scanning 360 degrees along a plane is also a straight line. It should be understood that when the point cloud shape is a straight-line point cloud, it can be determined that there are no passengers at the detection position corresponding to the current point cloud.

[0097] For example, the process of selecting at least one disembarkation time window is as follows: when the first point cloud of the previous time interval within the time window is an idle point cloud and the second point cloud is not an idle point cloud, and the first point cloud of the next time interval within the time window is not an idle point cloud and the second point cloud is an idle point cloud, the time window is used as the disembarkation time window. Figure 7 As shown, if the first point cloud is collected by laser beam 701 and the second point cloud is collected by laser beam 704, when the point cloud collected by laser beam 701 is an idle point cloud while the point cloud collected by laser beam 704 is not an idle point cloud in the previous time interval, it means that there is a passenger below laser beam 704; when the next time interval is reached, the point cloud collected by laser beam 701 is not an idle point cloud while the point cloud collected by laser beam 704 is an idle point cloud, it means that there is a passenger below laser beam 701, that is, the passenger has moved from below laser beam 704 to below laser beam 701, and the passenger is getting off the bus at this time. This time window is taken as the getting off time window.

[0098] For example, the process of selecting at least one boarding time window is as follows: when the first point cloud of the previous time interval within the time window is not an idle point cloud and the second point cloud is an idle point cloud, and the first point cloud of the next time interval within the time window is an idle point cloud and the second point cloud is not an idle point cloud, the time window is used as the boarding time window. Figure 7 As shown, if the first point cloud is collected by laser beam 701 and the second point cloud is collected by laser beam 704, when the point cloud collected by laser beam 701 is not an idle point cloud and the point cloud collected by laser beam 704 is an idle point cloud in the previous time interval, it means that there is a passenger below laser beam 701; when the next time interval, the point cloud collected by laser beam 701 is an idle point cloud and the point cloud collected by laser beam 704 is not an idle point cloud, it means that there is a passenger below laser beam 704, that is, the passenger has moved from below laser beam 701 to below laser beam 704, and the passenger is boarding the vehicle at this time. The time window at this time is taken as the boarding time window.

[0099] S603: Determine the passenger flow of the carriage corresponding to the detection device based on the number of boarding time windows and the number of alighting time windows included in the preset time period.

[0100] In this embodiment of the invention, after determining the number of boarding time windows and the number of alighting time windows, the number of boarding passengers is determined based on the number of boarding time windows, and the number of alighting passengers is determined based on the number of alighting time windows. Then, the passenger flow of the carriage within a preset time period is obtained based on the number of boarding passengers and the number of alighting passengers. Specifically, the total number of boarding passengers or the total number of alighting passengers is calculated as the passenger flow based on the number of boarding passengers and the number of alighting passengers.

[0101] In this embodiment of the application, the first point cluster and the second point cluster collected by the detection device installed at a train door during the train's stopping time can determine the passenger flow in the current carriage after the train door opens.

[0102] S604: Determine the first passenger flow within a preset time period based on the passenger flow of multiple carriages.

[0103] For example, after obtaining the passenger flow of each carriage during the train's stopping time, the passenger flow of the entire train can be calculated, thereby obtaining the passenger flow of the current train during a train stopping time.

[0104] The train door control method based on lidar provided in this application obtains a first point cloud and a second point cloud collected by a detection device of a subway detection system. Based on a preset shape point cloud, at least one boarding time window and at least one alighting time window are selected from the first and second point clouds. The passenger flow of the corresponding carriage is determined based on the number of boarding and alighting time windows within a preset time period. Finally, based on the passenger flow of multiple carriages, a first passenger flow within the preset time period is determined. This application achieves the purpose of determining the passenger flow within a train carriage by processing the point cloud collected by the detection device.

[0105] Figure 8 This is a flowchart illustrating the train door control method based on lidar provided in the embodiments of this application. Figure 4 .like Figure 8 As shown in the embodiments of this application, the train door control method based on lidar is as follows:

[0106] S801: For each platform screen door, within a preset time period, obtain the first point cloud and the second point cloud collected by the detection device, wherein the first point cloud contains multiple first point clouds and the second point cloud contains multiple second point clouds.

[0107] In the embodiments of this application, the method and effects implemented by S801 are the same as those of... Figure 6 S601 is the same in the embodiment, and will not be repeated here.

[0108] S802: Filter out abnormal point clouds from the first point cloud set and the second point cloud set. Abnormal point clouds are point clouds that do not belong to the preset shape and contain two or more point clouds with preset widths.

[0109] For example, to avoid multiple people boarding or alighting from the vehicle side by side, according to Figure 6 The passenger flow calculated in the example may have some omissions. Based on the point cloud characteristics when multiple people board or alight side by side, the corresponding abnormal point clouds are filtered out from the first point cloud set and the second point cloud set. Furthermore, the passenger flow is adjusted based on the abnormal point clouds.

[0110] For example, the point cloud corresponding to a passenger in the point cloud collected when a passenger passes through the laser beam is used as a point cloud of a preset width. Specifically, for the first point cloud set and the second point cloud set, point clouds containing two or more preset widths are selected as abnormal point clouds that have missed passengers.

[0111] S803: Select at least one boarding time window and at least one alighting time window from the first point cloud set and the second point cloud set according to the point cloud of the preset shape.

[0112] In the embodiments of this application, the method and effects implemented by S803 are the same as those of S803. Figure 6 S603 is the same as in the embodiment, and will not be repeated here.

[0113] S804: If the second point cloud of the previous time interval within the boarding time window is an abnormal point cloud, then the number of people corresponding to the boarding time window is determined based on the number of point clouds with a preset width contained in the second point cloud; if the first point cloud of the previous time interval within the alighting time window is an abnormal point cloud, then the number of people corresponding to the alighting time window is determined based on the number of point clouds with a preset width contained in the first point cloud.

[0114] In this embodiment, after determining the boarding time window, the number of passengers boarding in the current boarding time window is updated according to the number of point clouds with a preset width contained in the second point cloud. Specifically, when the number of point clouds with a preset width contained in the second point cloud is 3, the number of passengers boarding in the current boarding time window is 3. It should be understood that the process of adjusting the number of passengers corresponding to the alighting time window is the same as the process of adjusting the number of passengers corresponding to the boarding time window, and will not be described again here.

[0115] S805: Determine the number of passengers boarding based on the number of passengers in each boarding time window within a preset time period, and determine the number of passengers alighting based on the number of passengers alighting based on the number of passengers in each alighting time window within a preset time period.

[0116] In this embodiment of the application, after determining the number of people corresponding to each boarding time window and the number of people corresponding to each alighting time window, the number of people boarding and alighting within a preset time period can be determined.

[0117] S806: Determine the passenger flow of the corresponding carriage based on the number of passengers boarding and alighting within a preset time period.

[0118] In the embodiments of this application, the method and effects implemented by S806 are the same as those of S806. Figure 6 S603 is the same as in the embodiment, and will not be repeated here.

[0119] The train door control method based on lidar provided in this application further adjusts the calculated passenger flow based on the abnormal point clouds contained in the first point cloud and the second point cloud, which may have missed multiple passengers boarding or alighting at the same time, thereby improving the accuracy of the results.

[0120] Figure 9 This is a flowchart illustrating the train door control method based on lidar provided in the embodiments of this application. Figure 5 .like Figure 9 As shown in the embodiments of this application, the train door control method based on lidar is as follows:

[0121] S901: Obtain the first passenger flow corresponding to each train stopping time period.

[0122] In embodiments of the present invention, it can be based on Figure 6 The method provided in the embodiment obtains the first passenger flow corresponding to each train stopping time period, which will not be described in detail here.

[0123] S902: Determine the number of passengers inside the train based on the sum of the first passenger flow corresponding to multiple train stopping time periods.

[0124] In this embodiment of the application, after the train departs, according to Figure 6 The method in this embodiment calculates the first passenger flow during a stop time period after each train enters the station, and determines the number of passengers in all carriages of the current train by calculating the sum of the first passenger flows corresponding to multiple train stop time periods.

[0125] S903: If the number of passengers is greater than or equal to the first preset number, an early warning message will be sent to the alarm platform so that train staff can manage passenger flow based on the early warning message.

[0126] In this embodiment of the application, when the calculated number of passengers in the train is greater than the first preset number, it indicates that there are too many passengers and there is a risk of overcrowding. At this time, the warning information is sent to the alarm platform so that the train staff can control the passenger flow based on the warning information, control the passengers about to enter the station in a timely manner, reduce the number of passengers entering the station, and avoid overcrowding.

[0127] The train door control method based on lidar provided in this application, after determining the total number of passengers in the train carriage, promptly sends early warning information to the alarm platform if there is a risk of overcrowding. This enables train staff to manage passenger flow based on the early warning information, thereby ensuring passenger safety.

[0128] Figure 10 This is a flowchart illustrating the train door control method based on lidar provided in the embodiments of this application. Figure 6 .like Figure 10 As shown in the embodiments of this application, the train door control method based on lidar is as follows:

[0129] S1001: If the first passenger flow is greater than or equal to the second preset number within a preset time period, then obtain the set of door images collected by the image sensor within the preset time period, wherein the set of door images includes at least one door image when the train is open.

[0130] In this embodiment of the application, when the number of passengers in the train is greater than or equal to the second preset number within a short period of time, it indicates that the current number of passengers is large, and the following approach is adopted. Figure 4 The passenger flow calculated in the example may need to be adjusted further due to adhesion of the collected point cloud.

[0131] For example, if the first passenger flow is greater than or equal to the second preset number within a preset time period, then the set of door images collected by the image sensor within the preset time period is obtained.

[0132] S1002: For each detection device, detect each door image in the door image set collected by the detection device according to the preset target detection model to obtain the second passenger flow.

[0133] In this embodiment, a preset target detection model is used to detect each door image in the image set to obtain the second passenger flow. For example, the preset target detection model is a model trained based on labeled images of the train doors when they are open. For example, the target detection model is the YOLOv7 model. It should be noted that the trained preset target detection model is already implemented in the prior art and will not be described further here.

[0134] S1003: Determine the number of passengers in the train within a preset time period based on the first passenger flow and the second passenger flow.

[0135] In this embodiment of the application, for example, the number of passengers inside the train within a preset time period is adjusted according to a preset weighting coefficient and a first passenger flow and a second passenger flow. Specifically, the preset weighting coefficient includes a first preset weighting coefficient and a second preset weighting coefficient. A first product of the first preset weighting coefficient and the first passenger flow, and a second product of the second preset weighting coefficient and the second passenger flow are obtained, and the sum of the first product and the second product is used as the adjusted number of passengers.

[0136] The train door control method based on lidar provided in this application improves the accuracy of passenger count calculation by adjusting the number of passengers using collected images when there are many passengers in the train.

[0137] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0138] Corresponding to the train passenger flow determination method in the above embodiment, Figure 11 This is a structural block diagram of a train door control device based on lidar provided in the embodiments of this application. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0139] Reference Figure 11 The train door control device based on lidar includes: an acquisition module 1101, a determination module 1102, and a control module 1103.

[0140] The module 1101 is used to obtain point clouds collected by the detection device and images collected by the image sensor for each platform screen door before each train door is closed.

[0141] The determination module 1102 is used to determine that there are no foreign objects in the gap between the platform screen door and the train door corresponding to the detection device if the point cloud is a point cloud of a preset shape and the image is a target image. The preset shape point cloud is a straight point cloud and the target image is a gap image collected when there are no foreign objects in the gap between the platform screen door and the train door.

[0142] The control module 1103 is used to control the closing of the train doors.

[0143] It should be noted that the information interaction and execution process between the above modules / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0144] in addition, Figure 11 The train door control device based on lidar shown can be a software unit, a hardware unit, or a combination of software and hardware built into existing terminal equipment. It can also be integrated into the terminal equipment as an independent component, or exist as a standalone terminal equipment.

[0145] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0146] Figure 12 This is a schematic diagram of the controller provided in an embodiment of this application. The controller 120 provided in this embodiment includes: at least one processor 121 ( Figure 12 (Only one is shown in the image), memory 122, and computer program 123 stored in memory 122 and executable on at least one processor 121, wherein processor 121 executes computer program 123 to implement the steps performed by the controller in any of the above embodiments of the LiDAR-based train door control method.

[0147] The processor 121 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0148] In some embodiments, memory 122 may be an internal storage unit of controller 120, such as a hard disk or RAM of controller 120. In other embodiments, memory 122 may be an external storage device of controller 120, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on controller 120. Furthermore, controller 120 may include both internal storage units and external storage devices. Memory 122 is used to store operating systems, applications, boot loaders, data, and other programs, such as program code for computer programs. Memory 122 may also be used to temporarily store data that has been output or will be output.

[0149] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement the steps executed by the controller in any of the above embodiments of the train door control method based on lidar.

[0150] This application provides a computer program product that, when run on a terminal device, enables the terminal device to execute the steps performed by the controller in any of the above-described embodiments of the LiDAR-based train door control method. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-described embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above-described method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to the device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, such as a USB flash drive, a portable hard drive, a magnetic disk, or an optical disk. In some jurisdictions, computer-readable media may not be electrical carrier signals or telecommunication signals, according to legislation and patent practice.

[0151] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0152] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented using electronic hardware, or a combination of computer software and electronic hardware. 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, i.e., they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0153] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application 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. Such 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 this application, and should all be included within the protection scope of this application.

Claims

1. A train door control method based on lidar, characterized in that, A controller is applied to a subway detection system, which also includes multiple detection devices and multiple image sensors. Each platform screen door of the subway is equipped with one detection device and one image sensor. The controller is connected to each of the detection devices and each of the image sensors. The detection range of each detection device covers at least the sliding door head of a train door and the platform screen door head adjacent to the sliding door head. Before closing each of the train doors, for each of the platform screen doors, the point cloud collected by the detection device and the image collected by the image sensor are obtained; If the point cloud is a point cloud of a preset shape and the image is a target image, then it is determined that there are no foreign objects in the gap between the platform screen door and the train door corresponding to the detection device. The point cloud of the preset shape is a straight point cloud, and the target image is a gap image collected when there are no foreign objects in the gap between the platform screen door and the train door. Control the closing of the train doors; The method further includes: For each of the shielding doors, a first point cloud and a second point cloud are obtained by the detection device within a preset time period, wherein the first point cloud contains multiple first point clouds and the second point cloud contains multiple second point clouds. Based on the point cloud of the preset shape, at least one boarding time window and at least one alighting time window are selected from the first point cloud set and the second point cloud set. The passenger flow of the carriage corresponding to the detection device is determined based on the number of boarding time windows and the number of alighting time windows included in the preset time period. The first passenger flow within the preset time period is determined based on the passenger flow of multiple carriages.

2. The train door control method based on lidar as described in claim 1, characterized in that, After obtaining the point cloud acquired by the detection device and the image acquired by the image sensor, the method further includes: If the point cloud is not a point cloud of the preset shape, and / or the image is not an image of the target image, then it is determined that there is a foreign object in the gap between the platform screen door and the train door corresponding to the detection device. Control the opening of the train doors.

3. The train door control method based on lidar as described in claim 1, characterized in that, After determining that a foreign object exists in the gap between the platform screen door and the train door corresponding to the detection device, the method further includes: The anomaly number is determined based on the number of the shielding door containing the foreign object; An alarm message containing at least one of the aforementioned anomaly numbers is sent to the alarm platform, so that the alarm platform can indicate that there is a foreign object in the gap between the platform screen door and the train door corresponding to each of the aforementioned anomaly numbers.

4. The train door control method based on lidar as described in claim 1, characterized in that, Also includes: Abnormal point clouds are filtered out from the first point cloud set and the second point cloud set, wherein the abnormal point cloud is a point cloud that does not belong to the preset shape, and the abnormal point cloud contains two or more point clouds with preset widths. Accordingly, determining the passenger flow of the carriage corresponding to the detection device based on the number of boarding time windows and the number of alighting time windows included in the preset time period includes: If the second point cloud of the previous time interval within the boarding time window is an abnormal point cloud, the number of people corresponding to the boarding time window is determined based on the number of point clouds with the preset width contained in the second point cloud; if the first point cloud of the previous time interval within the alighting time window is an abnormal point cloud, the number of people corresponding to the alighting time window is determined based on the number of point clouds with the preset width contained in the first point cloud. The number of passengers boarding is determined based on the number of passengers in each boarding time window within the preset time period, and the number of passengers alighting is determined based on the number of passengers in each alighting time window within the preset time period. The passenger flow of the carriage corresponding to the detection device is determined based on the number of passengers boarding and alighting within a preset time period.

5. The train door control method based on lidar as described in claim 1, characterized in that, The preset time period is the train stopping time period. After determining the first passenger flow within the preset time period based on the passenger flow of multiple carriages, the method further includes: Obtain the first passenger flow corresponding to each of the train stopping time periods; The number of passengers inside the train is determined by the sum of the first passenger flow corresponding to multiple train stopping time periods. If the number of passengers is greater than or equal to the first preset number, an early warning message will be sent to the alarm platform so that train staff can manage passenger flow based on the early warning message.

6. The train door control method based on lidar as described in claim 1, characterized in that, After determining the first passenger flow within the preset time period based on the passenger flow of multiple carriages, the method further includes: If the first passenger flow is greater than or equal to the second preset number within the preset time period, then the set of door images collected by the image sensor within the preset time period is obtained, wherein the set of door images includes at least one door image when the train is open. For each of the aforementioned detection devices, each of the vehicle door images in the set of vehicle door images collected by the detection device is detected according to a preset target detection model to obtain the second passenger flow. The number of passengers in the train during the preset time period is determined based on the first passenger flow and the second passenger flow.

7. A train door control device based on lidar, characterized in that, include: The module is used to acquire point clouds collected by the detection device and images collected by the image sensor for each platform screen door before each train door is closed. The determination module is used to determine that if the point cloud is a point cloud of a preset shape and the image is a target image, there is no foreign object in the gap between the platform screen door and the train door corresponding to the detection device. The point cloud of the preset shape is a straight point cloud, and the target image is a gap image collected when there is no foreign object in the gap between the platform screen door and the train door. The control module is used to control the closing of the train doors; The device is also used for: For each of the shielding doors, a first point cloud and a second point cloud are obtained by the detection device within a preset time period, wherein the first point cloud contains multiple first point clouds and the second point cloud contains multiple second point clouds. Based on the point cloud of the preset shape, at least one boarding time window and at least one alighting time window are selected from the first point cloud set and the second point cloud set. The passenger flow of the carriage corresponding to the detection device is determined based on the number of boarding time windows and the number of alighting time windows included in the preset time period. The first passenger flow within the preset time period is determined based on the passenger flow of multiple carriages.

8. A controller, characterized in that, The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the LiDAR-based train door control method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, it performs the train door control method based on lidar as described in any one of claims 1 to 6.

Images