Vehicle detection device and vehicle detection method

Abstract

To provide a vehicle detection device and a vehicle detection method capable of reducing time and trouble required for adjustment for installation by having a simple configuration regarding detection of the vehicle.SOLUTION: A vehicle detection device 1 includes: a camera 5 capable of imaging between two adjacent cars 21 of a train in a state of stopping at a platform and at least one car door 22 as bodies to be photographed in one angle and generating three-dimensional imaging data which is the imaging result; a train stop detection unit for detecting whether or not the train imaged by the camera 5 is stopped or not based on the generated three-dimensional data; a stop position detection unit for detecting the stopped position of the train photographed by the camera 5 based on the generated three-dimensional imaging data; and a door opening / closing detection unit for detecting opening / closing of car door 22 imaged by the three-dimensional imaging unit based on the generated three-dimensional imaging data.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present disclosure relates to a vehicle detection device and a vehicle detection method. [Background technology]

[0002] The platform door device installed on the platform has a door pocket section installed along the edge of the platform and a door section that enters and exits the door pocket section. If TASC control or ATO control is not implemented on the line on which trains operate, a stop detection sensor is installed on the platform to detect whether the train is stopped in its designated position when it enters the platform. In addition, a door opening / closing detection sensor that detects the opening and closing of the train doors is also installed on the platform so that the platform door doors can be opened and closed in accordance with the opening and closing timing of the train doors. Furthermore, a track presence detection sensor that detects whether a train is present on the platform is installed on the platform.

[0003] Patent Document 1 listed below discloses a technology for a train position determination device that captures an image of a linear shadow that appears in the gap between the train and the platform and determines the train position from the captured image.Patent Document 2 discloses a technology for a vehicle detection device that captures an image of an area including a track on which a vehicle runs, detects straight lines included in the captured image, and determines that the captured image does not include a vehicle if the captured image includes a straight line with an angle within a preset range.

[0004] Furthermore, Patent Document 3 discloses a technology for an automatic door closing device that captures an image of the entrance / exit gate of a train that is stopped opposite a platform door device, compares the captured real-time image with a reference image, and determines whether the entrance / exit gate door is open or closed.Patent Document 4 discloses a technology for a train door open / close detection device that captures a three-dimensional distance image using a distance image sensor that sets a range including the train floor near the entrance / exit gate as a distance measurement target range, and determines whether the train door is open or closed based on the captured three-dimensional distance image. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent Publication No. 2021-66379 [Patent Document 2] Japanese Patent Application Publication No. 2019-191763 [Patent Document 3] Japanese Patent Application Publication No. 2020-62907 [Patent Document 4] Japanese Patent Application Laid-Open No. 2013-100008 Summary of the Invention [Problem to be solved by the invention]

[0006] Conventionally, the stop detection sensor, door opening / closing detection sensor, and track presence detection sensor are provided separately, which has resulted in the problem of requiring time and money for installation and maintenance.

[0007] In addition, 3D distance images acquired by laser-based 3D distance sensors have difficulty distinguishing between the shape of train cars and doors and the surrounding environment, and recording the movement of cars and doors. Therefore, detection using 3D distance sensors makes it difficult to confirm the situation when a problem occurs or consider measures to resolve the problem. Furthermore, when 3D distance sensors detect platforms and cars, they are easily affected by external environments that change depending on the weather and time of day, which creates the problem of time-consuming test runs of 3D distance sensors and adjustments before installation to improve detection accuracy.

[0008] The present disclosure has been made in consideration of the above circumstances, and aims to provide a vehicle detection device and a vehicle detection method that can simplify the configuration related to vehicle detection and reduce the time and effort required for adjustments for installation. [Means for solving the problem]

[0009] In order to solve the above problems, the vehicle detection device and vehicle detection method of the present disclosure employ the following means. That is, the vehicle detection device of the present disclosure is equipped with a three-dimensional imaging unit that can capture images of the area between two adjacent vehicles of a train stopped on a platform and at least one vehicle door as a subject within a single angle of view, and generates three-dimensional imaging data that is the imaging result, a train stop detection unit that detects whether the train imaged by the three-dimensional imaging unit is stopped or not based on the generated three-dimensional imaging data, a stop position detection unit that detects the stop position of the train imaged by the three-dimensional imaging unit based on the generated three-dimensional imaging data, and a door opening / closing detection unit that detects the opening and closing of the vehicle door imaged by the three-dimensional imaging unit based on the generated three-dimensional imaging data.

[0010] The vehicle detection method of the present disclosure includes the steps of: a three-dimensional imaging unit capable of capturing an image of the space between two adjacent vehicles of a train stopped on a platform and at least one vehicle door within a single angle of view, generating three-dimensional imaging data as the imaging results; a train stop detection unit detecting whether the train imaged by the three-dimensional imaging unit is stopped based on the generated three-dimensional imaging data; a stop position detection unit detecting the stop position of the train imaged by the three-dimensional imaging unit based on the generated three-dimensional imaging data; and a door opening / closing detection unit detecting whether the vehicle door imaged by the three-dimensional imaging unit is open or closed based on the generated three-dimensional imaging data. [Effects of the Invention]

[0011] According to the present disclosure, the configuration related to vehicle detection can be simplified, and the time and effort required for adjustments for installation can be reduced. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a schematic diagram showing a platform and a stopped train, showing the camera positions. [Figure 2]FIG. 1 is a schematic diagram showing a platform and a train, with the train viewed from the side. [Figure 3] FIG. 1 is a schematic diagram showing a platform and a train, the train viewed from the front. [Figure 4] FIG. 2 is an enlarged partial plan view showing the platform and a stopped train. [Figure 5] FIG. 1 is a block diagram illustrating a vehicle detection device according to an embodiment of the present disclosure. [Figure 6] FIG. 2 is a diagram showing an image captured by a camera and coordinate axes. [Figure 7] FIG. 2 is a block diagram illustrating an image processing unit of the vehicle detection device according to an embodiment of the present disclosure. [Figure 8] 10A and 10B are diagrams illustrating an image captured by a camera and a vehicle stop detection process. [Figure 9] 10A and 10B are diagrams illustrating an image captured by a camera and a stop position detection process. [Figure 10] 10A and 10B are diagrams illustrating an image captured by a camera and a door open / close detection process. [Figure 11] 10 is a diagram showing an image captured by a camera and a process for detecting whether a train is on the track, showing a state in which a train has not yet entered the platform. FIG. [Figure 12] 10A and 10B are diagrams showing an image captured by a camera and a process for detecting a train being on the track, showing a state in which a train has entered the platform. [Figure 13] 4 is a flowchart illustrating an operation of the vehicle detection device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0013] A vehicle detection device 1 according to an embodiment of the present disclosure will be described with reference to the drawings. 1 to 3, the vehicle detection device 1 detects the stopping status of the train 20, the stopping position of the train 20, the opening and closing of the vehicle doors 22, and the presence of the train 20 by using a camera 5 to capture images of the train 20. Information based on each detection result by the vehicle detection device 1 is transmitted to a control device 13 (see FIG. 5) of the platform screen door device 10 and is used to control the opening and closing of the platform screen door device 10.

[0014] As shown in Fig. 4, the platform screen door device 10 includes a main body 11 installed on the platform 15 and a door portion 12 that moves relative to the main body portion 11. When the train 20 approaches the platform 15, the door portion 12 of the platform screen door device 10 is closed, thereby preventing people, luggage, etc. from falling from the platform 15. When the train 20 arrives at the platform 15, the vehicle doors 22 of the train 20 and the door portion 12 of the platform screen door device 10 open, allowing passengers to get on and off.

[0015] 5, the vehicle detection device 1 includes a detection unit 2, a control unit 3, a storage unit 4, etc. The detection unit 2 also includes a camera 5, an image processing unit 6, etc.

[0016] In the detection unit 2, the camera 5 captures an image of a subject to generate image data, processes the generated image data, and, based on the processing results, detects the stopping state of the train 20, the stopping position of the train 20, the opening and closing of the car doors 22, and the location of the train 20. As shown in FIG. 6, in the image captured by the camera 5, the direction in which the platform 15 extends, i.e., a direction substantially parallel to the traveling direction of the train 20, is defined as the X axis, and the direction perpendicular to the X axis and substantially parallel to the height direction of the train 20 is defined as the Y axis. Furthermore, the direction perpendicular to the X axis and Y axis, and substantially parallel to the width direction of the car 21, i.e., a direction from the car doors 22 toward the interior of the car 21, is defined as the Z axis.

[0017] Camera 5 is a digital camera capable of capturing moving images, and is a stereo camera equipped with two image sensors to capture stereo images. Camera 5 generates three-dimensional image data as the imaging results. Because camera 5 is a stereo camera, the position coordinates of the object imaged by camera 5 can be calculated by image processing. Camera 5 transmits the generated three-dimensional image data to image processing unit 6. Camera 5 is an example of a three-dimensional imaging unit.

[0018] The camera 5 is installed, for example, on the platform 15, and captures an image within one angle of view of the space between two adjacent cars 21 of the train 20 stopped on the platform 15 and at least one car door 22 as subjects. The captured image is an image in which the two cars 21, the space between the cars 21, and the car door 22 can be seen.

[0019] 1, for example, three cameras 5 are installed on one track of platform 15. When three cameras 5 are installed, it is desirable to install them at positions corresponding to the front, rear, and middle cars 21 of the multiple cars 21 of train 20, respectively. This makes it possible to compare detection results based on each piece of image data, thereby improving the detection accuracy of vehicle detection device 1.

[0020] The image processing unit 6 acquires from the camera 5 the three-dimensional imaging data generated by the camera 5. Based on the acquired three-dimensional imaging data, the image processing unit 6 detects the stopping status of the train 20, the stopping position of the train 20, the open / closed status of the car doors 22, and the location of the train 20 on the track. The detection unit 2 is connected to the control unit 3, and the image processing unit 6 transmits the detection results, that is, information on the stopping status of the train 20, information on the stopping position, information on the open / closed status of the car doors 22, and information on the location of the train 20 on the track, to the control unit 3. The image processing unit 6 also transmits the three-dimensional imaging data to the storage unit 4.

[0021] The control unit 3 receives information on the stopping status of the train 20, information on the stopping position, information on the opening and closing of the car doors 22, and information on the location of the train 20 from the image processing unit 6. The control unit 3 generates an opening / closing instruction signal for instructing the opening and closing of the door unit 12 of the platform screen door device 10, based on the information on the stopping status of the train 20, information on the stopping position, information on the opening and closing of the car doors 22, and information on the location of the train 20. The control unit 3 transmits the generated opening / closing instruction signal to the control device 13 of the platform screen door device 10.

[0022] The storage unit 4 is an auxiliary storage device, such as a NAS (Network Attached Storage) connected to a plurality of vehicle detection devices 1 via a LAN. The storage unit 4 records and stores the 3D imaging data received from the image processing unit 6. The 3D imaging data recorded in the storage unit 4 can be reproduced by an external computer, such as a monitoring device 14 (see FIG. 5) that is a computer for monitoring stations. The storage unit 4 is an example of a second storage unit.

[0023] The storage unit 4 records the generated three-dimensional imaging data. Since the generated three-dimensional imaging data is recorded in the storage unit 4, it is possible to replay and check the situation before and after the train 20 stops at the platform 15, the opening and closing of the car doors 22, and the situation before and after the train 20 departs from the platform 15 when a problem occurs.

[0024] The image processing unit 6 of the detection unit 2, the control unit 3, and the control device 13 are computers that are executed by programs.

[0025] The control device 13 of the platform screen door device 10 generates a door drive signal for driving the door section 12 of the platform screen door device 10 based on the opening / closing instruction signal received from the control unit 3. The generated door drive signal is sent to the drive motor of the platform screen door device 10, and the door section 12 is driven by the operation of the drive motor.

[0026] <Image processing unit> 7, the image processing unit 6 includes a train stop detection unit 31, a stop position detection unit 32, a door open / close detection unit 33, a vehicle on track detection unit 34, and a memory unit 35. The train stop detection unit 31, the stop position detection unit 32, the door open / close detection unit 33, and the vehicle on track detection unit 34 will be described below.

[0027] <Train stop detection section> The train stop detection unit 31 detects, based on the three-dimensional imaging data generated by the camera 5, whether or not the train 20 captured by the camera 5 is stopped.

[0028] For example, the train stop detection unit 31 has a speed calculation unit 41 and a stop detection unit 42. The speed calculation unit 41 calculates the speed of the train 20 stopping at the platform 15 based on the three-dimensional image data generated by the camera 5. The stop detection unit 42 detects whether the train 20 is stopped or not based on the calculated speed.

[0029] First, as shown in FIG. 8, the speed calculation unit 41 sets a horizontal line L1 on the image acquired from the camera 5 and reads the luminance values ​​of pixels on the line L1. The speed calculation unit 41 compares luminance waveforms generated from the relationship between the positions of pixels on the line L1 and the luminance values ​​of each pixel between multiple images to calculate the amount of movement of the luminance waveforms (movement distance per unit time), and calculates the speed of the train 20 based on the calculated amount of movement. When the speed of the train 20 is fast, correlation of the luminance waveforms may not be obtained between multiple images, but when the speed of the train 20 is slow, correlation of the luminance waveforms can be obtained between multiple images. Since it is sufficient for the train stop detection unit 31 to detect the stop of the train 20, it calculates the speed of the train 20 using the above-mentioned method that obtains correlation when the speed of the train 20 is slow.

[0030] By setting two parallel horizontal lines L1, the velocity calculation unit 41 can reduce the influence of disturbances and improve the accuracy of velocity calculation, unlike when a single line L1 is set. By adopting the higher velocity value from the two velocities calculated based on the two lines L1, it is possible to determine with certainty whether the vehicle is stopped. Furthermore, by using the distribution of brightness values ​​on the line L1 in the image acquired from the camera 5, processing time can be reduced, unlike when velocity is calculated using the distribution of brightness values ​​on a surface.

[0031] The stop detection unit 42 determines that the train 20 is stopped when the speed calculated by the speed calculation unit 41 is 0. On the other hand, when the speed calculated by the speed calculation unit 41 exceeds 0, the stop detection unit 42 determines that the train 20 is not stopped but is moving.

[0032] The information that the train 20 has stopped, detected by the train stop detection unit 31, is used to determine whether or not to start detecting the stop position, and whether or not the platform screen door device 10 can be opened or closed.

[0033] <Stop position detection unit> The stop position detection unit 32 detects the stop position of the train 20 captured by the camera 5 based on the three-dimensional image data generated by the camera 5.

[0034] For example, the stop position detection unit 32 includes a vehicle end face extraction unit 51 and an end face position detection unit 52 . As shown in FIG. 9, the vehicle end surface extraction unit 51 extracts one of the mutually facing end surfaces 21a of two adjacent vehicles 21 based on the generated 3D image data. Specifically, the vehicle end surface extraction unit 51 first calculates the normal vector of the object in the image from the 3D image data. Then, the vehicle end surface extraction unit 51 extracts a surface having a normal vector parallel to an axis (X-axis) that is approximately parallel to the direction of travel of the train 20. In FIG. 9, an example of an extracted surface having a normal vector parallel to the X-axis is shown by a gray area. The vehicle end surface extraction unit 51 sets an end surface detection range S1 within the image acquired from the camera 5 and extracts a surface within that range having a normal vector parallel to the X-axis.

[0035] When the vehicle end face extraction unit 51 extracts a surface having a normal vector parallel to the X-axis within the preset end face detection range S1, the vehicle end face extraction unit 51 determines that surface to be the end face 21a of the vehicle 21. By setting the end face detection range S1, the vehicle end face extraction unit 51 extracts the end face 21a only within a range where it is predicted in advance that the end face 21a will be detected. Therefore, unlike when extracting a surface having a normal vector parallel to the X-axis from the entire screen, it is possible to prevent the extraction of a surface different from the end face 21a of the vehicle 21, thereby improving the accuracy of extracting the end face 21a.

[0036] The end face position detection unit 52 calculates the average value of the X coordinates of the planes determined to be the end face 21a of the vehicle 21 and having normal vectors parallel to the X axis. The calculated average value of the X coordinates indicates the position of the end face 21a of the vehicle 21 in the image. The end face position detection unit 52 pre-sets a reference position P1 within the angle of view of the 3D imaging data. The end face position detection unit 52 calculates the distance from the reference position P1 to the end face 21a based on the average value of the X coordinates of the planes having normal vectors parallel to the X axis and the reference position P1. The end face position detection unit 52 detects the actual stopping position of the train 20 relative to the fixed position by comparing the distance from the reference position P1 to the end face 21a when the train 20 stops at the fixed position.

[0037] The stop position detected by the stop position detection unit 32 is used to determine whether the door section 12 of the platform screen door device 10 can be opened or closed, and to adjust the opening position of the door section 12 of the platform screen door device 10 when the opening position is variable.

[0038] <Door open / close detector> The door open / close detector 33 detects whether the vehicle door 22 is open or closed based on the three-dimensional image data generated by the camera 5.

[0039] For example, the door open / close detection unit 33 includes an opening determination unit 61, an open / close detection unit 62, and the like. The opening determination unit 61 determines the opening of the vehicle door 22 based on the generated 3D image data. Specifically, the opening determination unit 61 detects an edge extending in the vehicle height direction due to a step between the vehicle door 22 in a closed state and the side of the vehicle 21 based on the generated 3D image data, and determines the detected edge as the opening of the vehicle door 22. The opening determination unit 61 also obtains coordinates of the surface of the vehicle door 22 in a closed state between the detected edges and records the coordinates as a reference plane in the storage unit 35. The storage unit 35 is an example of a first storage unit. Note that, as shown in FIG. 10, it is sufficient to record coordinates on a line L2 of the reference plane that is parallel to the traveling direction of the train 20.

[0040] 10, opening determination unit 61 determines openings only within a range where openings are predicted to be detected in advance by setting opening detection range S2. Therefore, unlike when determining openings from the entire screen, it is possible to improve the determination accuracy.

[0041] The open / close detection unit 62 detects whether the vehicle door 22 is open or closed at the opening determined by the opening determination unit 61. Specifically, the open / close detection unit 62 sequentially acquires the coordinates of each point on the recorded line L2 in the vehicle width direction (Z-axis direction). That is, if the coordinates of each point on the line L2 in the Z-axis direction when the line L2 is recorded as a reference plane with the vehicle door 22 closed are set to zero, the coordinates in the Z-axis direction change when the vehicle door 22 is opened. Then, when the newly acquired coordinates of each point in the Z-axis direction exceed a predetermined threshold T1, the open / close detection unit 62 determines that the vehicle door 22 is open at that point. The open / close detection unit 62 calculates an opening rate, i.e., the ratio of the number of points determined to be open to the total number of points on the line L2. When all of the vehicle doors 22 are open, the opening rate becomes 100%. For example, the open / close detection unit 62 detects that the vehicle door 22 is closed when the opening rate is 30% or less, and detects that the vehicle door 22 is open when the opening rate exceeds 30%.

[0042] Depending on the relationship between the installation position of the camera 5 and the position of the vehicle door 22, the edge in the vehicle height direction may be oblique in the image captured by the camera 5, and the opening of the vehicle door 22 may be captured as a trapezoid. In this case, it is desirable that the opening determination unit 61 performs a projective transformation on the opening of the captured image so that the edge in the vehicle height direction is made vertical in the image and the opening of the vehicle door 22 becomes rectangular (see the two-dot chain line in FIG. 10). In this state, the open / close detection unit 62 acquires the coordinates in the Z-axis direction of each point on the line L2, thereby enabling more accurate detection of the open / closed state of the vehicle door 22.

[0043] After the vehicle door 22 opens, the Z-axis coordinate of each point fluctuates as passengers enter and exit. When the Z-axis coordinate is equal to or less than a predetermined threshold T1 due to the passenger's body being close to the reference plane, the vehicle door 22 is determined to be closed. However, according to the results of experiments conducted by the inventors, the proportion of the opening width occupied by one passenger is calculated to be approximately 10% of the total opening width. Typically, the maximum number of passengers that can enter and exit one vehicle door 22 at the same time is three or four, and the opening ratio may be calculated to be 60% to 70% depending on the number of passengers entering and exiting. However, if the upper limit of the opening ratio for detecting that the vehicle door 22 is closed is set to 30%, there is a sufficient margin, and the entrance and exit of passengers does not affect the detection of whether the vehicle door 22 is open or closed.

[0044] Information that the vehicle door 22 detected by the door opening / closing detection unit 33 is in an open state is used to determine whether or not to start the opening operation of the door section 12 of the platform screen door device 10. Information that the vehicle door 22 detected by the door opening / closing detection unit 33 is in a closed state is used to determine whether or not to start the closing operation of the door section 12 of the platform screen door device 10.

[0045] <Train presence detection unit> The train presence detection unit 34 detects whether the train 20 is present on the platform 15 based on the generated three-dimensional image data.

[0046] Specifically, the distance to a predetermined position within the angle of view captured by the camera 5 before the train 20 stops at the platform 15 is recorded in advance in the memory unit 35. Here, the predetermined position is, for example, a position corresponding to the track (railroad track) 16 captured by the camera 5, as shown in Fig. 11, and the distance from the camera 5 to the track 16 is recorded. In Fig. 11, the position within the angle of view corresponding to the track 16 to be measured is indicated by line L3.

[0047] The vehicle on-track detection unit 34 calculates the distance to a predetermined position (line L3) within the field of view each time the image is updated. Then, the vehicle on-track detection unit 34 detects whether the train 20 is on the platform 15 by comparing the distance recorded in the storage unit 35 with the distance to the predetermined position within the field of view of the 3D imaging data.

[0048] That is, the storage unit 35 stores an average value L0 of the distance from the camera 5 to the track 16, and the vehicle presence detection unit 34 calculates the average distance L to a predetermined position (line L3) within the angle of view corresponding to the track 16 each time the image is updated. Then, as shown in FIG. 12 , when the train 20 enters the platform 15 and the calculated average distance L becomes equal to or less than a predetermined threshold T2, the vehicle presence detection unit 34 detects that the train 20 is present on the platform 15. When the calculated average distance L exceeds the predetermined threshold T2, the vehicle presence detection unit 34 detects that the train 20 is not present on the platform 15. The predetermined threshold T2 is set, for example, to a length shorter than the average value L0 of the distance from the camera 5 to the track 16.

[0049] The on-track status of the vehicle 21 detected by the vehicle on-track detection unit 34 is transmitted to a station monitoring panel or the like. Information that the vehicle 21 is on-track, detected by the vehicle on-track detection unit 34, is used to determine whether or not to start detecting the stop of the train 20, i.e., whether or not to start detecting the amount of movement of the train 20.

[0050] Next, with reference to FIG. 13, the operation of the vehicle detection device 1 according to an embodiment of the present disclosure will be described. While the camera 5 starts capturing images, the presence of the train 20 on the track is detected (step S1). At this time, it is detected whether the train 20 is on the track at the platform 15 (step S2). The detected presence status of the train 21 on the track is sent to a higher-level system such as a station monitoring panel or the control device 13 of the platform screen door device 10.

[0051] When it is detected that the train 20 is not present at the platform 15, it is subsequently detected whether the train 20 is present at the platform 15 or not.

[0052] Furthermore, when it is detected that the train 20 is on the platform 15, it is determined that the train 20 has entered the platform 15, and detection of whether the train 20 has stopped is started (step S3). When detection of whether the train 20 has stopped is started, the speed of the train 20 stopping at the platform 15 is calculated based on the three-dimensional image data generated by the camera 5. Then, based on the calculated speed, it is detected whether the train 20 has stopped (step S4).

[0053] When the calculated speed of the train 20 becomes 0, it is determined that the train 20 is stopped. On the other hand, when the calculated speed exceeds 0, it is determined that the train 20 is not stopped but is moving. If the train 20 continues to move, detection of whether the train 20 is stopped continues while detecting whether the train 20 is located at the platform 15. On the other hand, when the calculated speed of the train 20 becomes 0 and it is determined that the train 20 is stopped, detection of the stop position of the train 20 is started (step S5).

[0054] When detection of the stopping position of the train 20 is started, the position of one of the mutually facing end faces 21a of two adjacent vehicles 21 is detected based on the three-dimensional image data generated by the camera 5. When the position of one of the end faces 21a is detected, the stopping position of the train 20 is calculated based on the average value of the X coordinate of the plane having a normal vector parallel to the X axis and a preset reference position P1, and the stopping position of the train 20 relative to the fixed position is detected.

[0055] Information regarding the detected stopping position is sent to a higher-level system such as the control device 13 of the platform screen door device 10 to determine whether the door section 12 of the platform screen door device 10 can be opened or closed, or to adjust the opening position of the door section 12 of the platform screen door device 10 if the opening position is variable. When the stopping position of the train 20 is detected, detection of the stopping position of the train 20 may be stopped after information regarding the detected stopping position is sent.

[0056] After the detection of the stopping position of the train 20 is started, it is determined whether or not the stopping position of the train 20 has been detected (step S6). When the stopping position of the train 20 has been detected, the detection of the stopping position of the train 20 is ended (step S7), and the detection of whether the car door 22 is open or closed is started (step S8). When the stopping position of the train 20 has not been detected, the detection of the stopping position of the train 20 continues.

[0057] When detection of whether the vehicle door 22 is open or closed is started, an opening of the vehicle door 22 is determined based on the three-dimensional image data generated by the camera 5. Then, the opening or closing of the vehicle door 22 is detected at the opening. Specifically, coordinates of the surface of the vehicle door 22 are detected, and the coordinates are recorded in the storage unit 35 as a reference plane. Then, when the coordinate in the Z-axis direction of each point recorded as the reference plane in a closed state of the vehicle door 22 is set to zero, if the newly acquired coordinate in the Z-axis direction of each point exceeds a predetermined threshold T1, it is determined that the vehicle door 22 is open at that point. Then, an opening rate, i.e., a ratio of the number of points determined to be open to the total number of points on the reference plane, is calculated. For example, when the opening rate is 30% or less, the vehicle door 22 is detected as closed, and when the opening rate exceeds 30%, the vehicle door 22 is detected as open.

[0058] The information that the detected vehicle door 22 is in an open state is sent to a higher-level system such as the control device 13 of the platform screen door device 10, which determines whether or not to start the opening operation of the door section 12 of the platform screen door device 10.

[0059] When detection of the opening and closing of the vehicle door 22 has begun, if it is detected that the coordinates of the surface of the vehicle door 22 recorded as the reference plane are fluctuating due to the shaking of the vehicle 21, adjustments may be made to correct the coordinates of the reference plane.

[0060] When the opening and closing of the vehicle door 22 is being detected and it is determined that the vehicle door 22 is open, and then it is detected that the vehicle door 22 is closed, the information that the detected vehicle door 22 is in a closed state is sent to a higher-level system such as the control device 13 of the platform screen door device 10, which determines whether or not to start the closing operation of the door section 12 of the platform screen door device 10.

[0061] While the opening and closing of the car doors 22 is being detected, it is determined whether the movement of the train 20 is zero (step S9). If the movement of the train 20 is zero, the detection of the presence of the train 20 on the track continues, while the detection of the stop of the train 20 and the detection of the opening and closing of the car doors 22 continue. On the other hand, when it is determined that the movement of the train 20 is no longer zero, it is determined that the train 20 has started moving, and the detection of the stop of the train 20 and the detection of the opening and closing of the car doors 22 are stopped (step S10). Then, only the detection of the presence of the train 20 on the track continues. Subsequently, the detected presence state of the car 21 on the track is sent to a higher-level system such as a station monitoring panel or the control device 13 of the platform screen door device 10. Note that in step S9, after it is confirmed that the closing operation of the door section 12 of the platform screen door device 10 has been completed, it may be determined whether the movement of the car doors 22 is zero.

[0062] As described above, according to this embodiment, detection of the presence of the train 20 on the track, detection of the stopped state of the train 20, detection of the stopping position of the train 20, and detection of the open / closed state of the car doors 22 are performed based on 3D image data generated from a single camera 5, thereby simplifying the configuration for detecting the car 21. Conventionally, when detecting cars using a 3D distance sensor that uses a laser, due to the limitations of the 3D distance sensor, it was necessary to use separate sensors for detecting the presence of the train 20 on the track, detection of the stopped state of the train 20, detection of the stopping position of the train 20, and detection of the open / closed state of the car doors 22. In contrast, in this embodiment, the number of devices to be installed can be reduced, and the effort and costs involved in installation and maintenance can be reduced.

[0063] Furthermore, the three-dimensional image data generated by the camera 5 is used to detect whether the train 20 is on the track, whether the train 20 is stopped, where the train 20 is stopped, and whether the car door 22 is open or closed. This makes it less susceptible to changes due to weather or time of day, unlike when a three-dimensional distance sensor using a laser is used, and reduces the time and effort required for adjustments before installation to improve detection accuracy.

[0064] In the above-described embodiment, the image processing unit 6 includes all of the train stop detection unit 31, stop position detection unit 32, door open / close detection unit 33, and vehicle presence detection unit 34, but the present disclosure is not limited to this example. That is, one or more of the train stop detection unit 31, stop position detection unit 32, door open / close detection unit 33, and vehicle presence detection unit 34 may be omitted from the image processing unit 6. In this case, the omitted detection process may be performed by a separate device, thereby realizing the vehicle detection method according to the present disclosure.

[0065] The vehicle detection device and vehicle detection method described in each of the above-described embodiments can be understood, for example, as follows.

[0066] The vehicle detection device (1) of the present disclosure is capable of capturing images of the space between two adjacent vehicles (21) of a train (20) stopped on a platform (15) and at least one vehicle door (22) as subjects within a single angle of view, and includes a three-dimensional imaging unit (5) that generates three-dimensional imaging data as the imaging results, a train stop detection unit (31) that detects whether the train imaged by the three-dimensional imaging unit is stopped based on the generated three-dimensional imaging data, a stop position detection unit (32) that detects the stop position of the train imaged by the three-dimensional imaging unit based on the generated three-dimensional imaging data, and a door opening / closing detection unit (33) that detects the opening / closing of the vehicle door imaged by the three-dimensional imaging unit based on the generated three-dimensional imaging data.

[0067] According to this configuration, the 3D imaging unit captures an image of the space between two adjacent cars of a train stopped at a platform and at least one car door as subjects within one angle of view, and generates 3D imaging data as the imaging results. Then, based on the generated 3D imaging data, it is possible to detect whether the train imaged by the 3D imaging unit is stopped, to detect the stopping position of the train imaged by the 3D imaging unit, and to detect whether the car door imaged by the 3D imaging unit is open or closed.

[0068] This simplifies the vehicle detection configuration because train stop detection, stop position detection, and door open / close detection are all performed based on 3D image data generated from a single 3D imaging unit. Furthermore, because these detections use 3D image data generated by the 3D imaging unit, they are less susceptible to changes due to weather or time of day, reducing the time and effort required for adjustments to improve detection accuracy.

[0069] The vehicle detection device according to the present disclosure may further include a vehicle presence detection unit (34) that detects whether the train is present on the platform based on the generated three-dimensional imaging data.

[0070] According to this configuration, whether or not a train is present at the platform is detected based on the generated 3D imaging data, eliminating the need to install a separate imaging device, and simplifying the configuration for vehicle detection.

[0071] In the vehicle detection device of the present disclosure, the train stop detection unit may calculate the speed of the train stopping at the platform based on the generated 3D imaging data, and detect whether the train is stopped or not based on the calculated speed.

[0072] According to this configuration, the speed of the train stopping at the platform is calculated based on the generated three-dimensional imaging data, and it is detected whether the train is stopped or not based on the calculated speed.

[0073] In the vehicle detection device according to the present disclosure, the stop position detection unit may extract one of the facing end faces of the two adjacent vehicles based on the generated three-dimensional imaging data, and detect the stop position of the train based on the extracted end face.

[0074] According to this configuration, one of the mutually facing end faces of two adjacent vehicles is extracted based on the generated three-dimensional imaging data, and the stopping position of the train is detected based on the extracted end face.

[0075] In the vehicle detection device according to the present disclosure, the door open / close detection unit may detect the opening width of the vehicle door based on the generated three-dimensional imaging data, and detect whether the vehicle door is open or closed.

[0076] According to this configuration, the opening width of the vehicle door is detected based on the generated three-dimensional imaging data, and the opening and closing of the vehicle door is detected.

[0077] The vehicle detection device according to the present disclosure may further include a first memory unit (35) that records the distance to a predetermined position within the angle of view captured by the three-dimensional imaging unit before the train stops at the platform, and the vehicle presence detection unit may detect whether the train is present at the platform by comparing the distance recorded in the first memory unit with the distance to the predetermined position within the angle of view of the three-dimensional imaging data.

[0078] According to this configuration, the memory unit records the distance to a predetermined position within the field of view captured by the 3D imaging unit before the train stops at the platform, and by comparing the distance recorded in the memory unit with the distance to the predetermined position within the field of view of the 3D imaging data, it is possible to detect whether the train is located at the platform.

[0079] The vehicle detection device according to the present disclosure may further include a second storage unit (4) that records the generated three-dimensional imaging data.

[0080] According to this configuration, the generated 3D imaging data is recorded in the second memory unit, so that the situation before and after the train stops at the platform, the situation of the doors opening and closing, and the situation before and after the train departs from the platform can be played back and checked in the event of a problem, etc.

[0081] The vehicle detection method of the present disclosure includes the steps of: a three-dimensional imaging unit capable of capturing an image of the space between two adjacent vehicles of a train stopped on a platform and at least one vehicle door within a single angle of view, generating three-dimensional imaging data as the imaging results; a train stop detection unit detecting whether the train imaged by the three-dimensional imaging unit is stopped based on the generated three-dimensional imaging data; a stop position detection unit detecting the stop position of the train imaged by the three-dimensional imaging unit based on the generated three-dimensional imaging data; and a door opening / closing detection unit detecting whether the vehicle door imaged by the three-dimensional imaging unit is open or closed based on the generated three-dimensional imaging data. [Explanation of symbols]

[0082] 1: Vehicle detection device 2: Detection section 3: Control section 4: Storage section (second storage section) 5: Camera (3D imaging unit) 6: Image processing section 10: Platform door device 11: Main body 12: Door section 13: Control device 14: Monitoring device 15: Platform 16: Orbit 20: Train 21: Vehicle 21a: End face 22: Car door 31: Train stop detection unit 32: Stop position detection unit 33: Door opening / closing detector 34: Vehicle presence detection unit 35: Storage section (1st storage section) 41: Speed ​​calculation section 42: Stop detection unit 51: Vehicle end face extraction section 52: End face position detection unit 61: Opening judgment section 62: Open / close detector

Claims

1. a three-dimensional imaging unit that can capture an image of the area between two adjacent cars of a train stopped at a platform and at least one car door as subjects within a single angle of view, and generates three-dimensional imaging data as the imaging results; a train stop detection unit that detects whether the train imaged by the three-dimensional imaging unit is stopped based on the generated three-dimensional imaging data; a stop position detection unit that detects a stop position of the train imaged by the three-dimensional imaging unit based on the generated three-dimensional imaging data; a door opening / closing detection unit that detects whether the vehicle door imaged by the three-dimensional imaging unit is opened or closed based on the generated three-dimensional imaging data; a train presence detection unit that detects whether the train is present on the platform based on the generated three-dimensional image data; a first storage unit that records distances to predetermined positions within an angle of view captured by the three-dimensional imaging unit before the train stops at the platform; Equipped with The vehicle presence detection unit is a vehicle detection device that detects whether the train is present on the platform by comparing the distance recorded in the first memory unit with the distance to the specified position within the angle of view of the three-dimensional imaging data.

2. The vehicle detection device according to claim 1 , further comprising a second storage unit that records the generated three-dimensional image data.

3. a step in which a three-dimensional imaging unit capable of capturing an image of the space between two adjacent cars of a train stopped at a platform and at least one car door as a subject within a single angle of view generates three-dimensional imaging data as an imaging result; a train stop detection unit detecting whether the train imaged by the three-dimensional imaging unit is stopped based on the generated three-dimensional imaging data; a stop position detection unit detecting a stop position of the train imaged by the three-dimensional imaging unit based on the generated three-dimensional imaging data; a door opening / closing detection unit detecting whether the vehicle door imaged by the three-dimensional imaging unit is opened or closed based on the generated three-dimensional imaging data; a vehicle presence detection unit detecting whether the train is present on the platform based on the generated three-dimensional image data; Equipped with a first storage unit records a distance to a predetermined position within an angle of view captured by the three-dimensional imaging unit before the train stops at the platform; A vehicle detection method in which the vehicle presence detection unit detects whether the train is present on the platform by comparing the distance recorded in the first memory unit with the distance of the specified position within the angle of view of the three-dimensional imaging data.

Images