JP3244870B2 - Obstacle detection device for railway vehicles - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an obstacle detecting device for a railway vehicle for detecting an obstacle present on the course of a running railway vehicle.

[0002]

2. Description of the Related Art In the operation of railway vehicles such as trains and trains,
In order to ensure the safety of the vehicle, it is conceivable to take an image of the front of the traveling vehicle and determine the presence or absence of an obstacle on the course from the captured image. In this case, the problem is the distance La to the obstacle. Assuming that the braking distance of the vehicle is L, a collision can be avoided if L <La. However, if L> La, a collision will occur even if an obstruction can be detected. Therefore, it is meaningless if the obstacle is not detected beyond L (braking distance) ahead of the vehicle. Furthermore, considering a margin ΔL for the driver to make a decision, (L + Δ
L) It is necessary to detect obstacles beyond the distance.

The following two methods are conceivable as methods for determining the position of the (L + ΔL) front rail in the screen of the photographed image. (1) The distance between the two rails is constant. By utilizing this feature, the number of pixels between the rails in front of (L + ΔL) is calculated in advance from the angle of view of the camera, and the position of the (L + ΔL) front rail in the screen is obtained.

[0004] However, this method is effective only when the track is traveling straight, and when the track is curved, an accurate position cannot be calculated. Then, the following method can be considered. (2) The distance is calculated by triangulation using two cameras, and the position of the rail in front of (L + ΔL) is determined.

[0005] If the position of the rail in front of (L + ΔL) is known on the screen, an area (obstruction search area) for inspecting the presence / absence of an obstacle is set centering on the position, and image processing is performed in the area. The presence or absence of an obstacle is determined based on the fact.

[0006]

In the methods (1) and (2), it is necessary to identify and recognize the position of the rail on the screen by performing image processing and the like. Moreover,
The position in front of (L + ΔL) is obtained by the methods (1) and (2). However, in (1), it is impossible to determine the position when the track is curved, and in (2), the distance between the cameras cannot be greater than the lateral width of the vehicle body. There is a problem in accuracy because the distance between cameras cannot be sufficiently obtained.
Furthermore, since two cameras are used, there is a problem that the entire system is complicated, the time required for calculation is long, and the cost is high.

In addition, an obstacle detected by performing image processing in the obstacle search area is located in front of the vehicle (L).
+ ΔL) to an infinity point (theoretically). The driver's response changes according to the distance La to the obstacle. If La is slightly larger than (L + ΔL), it is necessary to apply a sudden brake. If La is considerably larger than (L + ΔL), a whistle can be sounded and the situation can be checked.
As a method of knowing the distance to the obstacle, a method of calculating from the size of the obstacle on the screen and the angle of view of the camera is conceivable, but the size of the obstacle is various, and this method is not possible It is.

On the other hand, the distance (L + ΔL) is determined by the speed of the train, and it is more effective to change the distance (L + ΔL) according to the vehicle speed. The present invention has been made in view of the above points, and is based on the vehicle speed (L + ΔL).
, And the position of the rail in front of (L + ΔL) in the screen is calculated accurately and in a short time to set an obstacle search area, and the presence or absence of an obstacle in the area can be accurately determined. It is another object of the present invention to provide a railway vehicle obstacle detection device that can measure a distance to an obstacle and notify a driver of the distance.

Further, the present invention can accurately and quickly determine an area in which to check for the presence of a preceding train, and can reliably determine the presence or absence of a preceding vehicle in an area beyond the braking distance, and calculate a speed limit. It is an object of the present invention to provide a highly safe obstruction detection device for railway vehicles, which can control the vehicle speed.

[0010]

[Means for Solving the Problems]

(First Invention) An obstacle detection device for a railway vehicle according to the first invention is provided with an image input device installed to capture an image in front of a running railway vehicle, and an image captured by the image input device. Image memory for storing, position detecting means for detecting the current position of the running vehicle, speed detecting means for detecting the speed of the running vehicle, and how the rails are located in the image captured by the image input device. A route data memory for storing in advance as route data corresponding to a vehicle position detected by the position detecting means, and a distance capable of avoiding a collision with an obstacle by a speed signal detected by the speed detecting means. Further, the obstacle search area is displayed in a screen obtained by the image input device from the position detection signal detected by the position detection means and the route data stored in the route data memory. An obstacle search area setting unit that sets the following: a determination unit that determines whether there is an obstacle in the obstacle search area with respect to an image stored in the image memory; and a vibration that detects vibration of the vehicle. Angle detecting means, distance measuring means for measuring the distance from the vehicle to the obstacle, and obstacles based on the position of the obstacle on the screen obtained by the image input device and the vibration angle obtained by the vibration angle detecting means. Calculating means for calculating the direction of the object; distance measuring direction control means for controlling and driving the distance measuring direction of the distance measuring means based on the direction information obtained by the calculating means; An informing means for informing the driver of the presence or absence and the distance to the obstacle measured by the distance measuring means is provided.

(Second Invention) An obstacle detecting device for a railway vehicle according to a second invention is provided with an image input device installed so as to capture an image in front of a running railway vehicle, and an image captured by the image input device. Image memory for storing the current image of the traveling vehicle, position detection means for detecting the current position of the traveling vehicle, speed detection means for detecting the speed of the traveling vehicle, and a rail in the image taken by the image input device. A route data memory which stores in advance how the vehicle looks as route data corresponding to the vehicle position detected by the position detecting means, and a collision with the preceding train can be avoided by a speed signal detected by the speed detecting means. The distance obtained by the image input device is calculated from the position detection signal detected by the position detection means and the route data stored in the route data memory. Preceding train search area setting means for setting a row train search area; determining means for determining whether or not there is a preceding train in the preceding train search area with respect to the image stored in the image memory; Distance measuring means for measuring the distance to the preceding train, and means for calculating the speed limit based on the distance to the preceding train measured by the distance measuring means and limiting the vehicle speed.

[0012]

[Action]

(First invention) Route data obtained by converting the laying state of a railway into data is stored in a route data memory in advance, and the current position (for example, distance from a reference point) of a running vehicle is detected by a position detecting means. By reading the stored contents of the route data memory, the laying state of the track in front of the vehicle can be confirmed. That is, when three-dimensional coordinates having the current position as the origin are set, the position p of the rail ahead of an arbitrary distance R is set.
Can be uniquely determined. Where this point p is photographed by an image input device installed to photograph the front of the traveling vehicle, for example, an infrared camera, it can be found by a mathematical coordinate transformation calculation. Therefore, it is possible to know where the rail ahead of an arbitrary distance R can be seen in the screen. Therefore, an obstacle search area of a finite size is set centering on the position of the rail in the screen when R = (L + ΔL), and image processing is performed in the area to determine the presence or absence of an obstacle. judge. Further, the direction of the obstacle is calculated from the position of the obstacle on the screen and the output of the vibration angle detection sensor, and the distance to the obstacle is measured by controlling and driving the distance measuring direction of the distance measuring means. Then, the presence / absence of an obstacle based on the determination result and the measured distance to the obstacle are notified to the driver.

[0013] By using the route data as described above, even if the front line is straight or curved, (L
+ ΔL) The position of the front rail in the screen can be accurately calculated. Further, the braking distance L can be calculated from the vehicle speed obtained by the speed detecting means, and the margin ΔL can be obtained from the braking distance L. For example, the margin ΔL is set to a value of about 30% of the braking distance L. Thus, (L + ΔL) can be set according to the vehicle speed, and obstacle detection can be performed more efficiently. Further, by performing image processing and the like, there is no need to identify and recognize the position of the rail in the screen, and the calculation time can be greatly reduced. Further, since the distance to the obstacle is known by performing the distance measurement, the driver can take a measure corresponding to the distance to the obstacle.

(Second Invention) An image in front of a vehicle taken by an image input device is digitized and stored in an image memory. The image data stored in the image memory is binarized by various well-known image processing algorithms, a rail portion is extracted as a binary image, and the binary image is recorded in the image memory. Further, the current position of the vehicle is read from the position detecting means, and the route data corresponding to the current position is read from the route data memory. Then, a preceding train search area is set in the screen using the binary image and the route data, and various image processings are performed in the set area to determine whether there is a preceding train.

When a preceding train is detected, the distance to the preceding train is calculated by distance measuring means. That is, the distance measuring means measures the distance to the preceding train by image processing using the route data read from the route data memory. The speed limit of the vehicle is obtained by arithmetic processing according to the distance to the preceding train obtained by this measurement processing,
Limit the vehicle speed to the appropriate speed. As a result, the distance from the preceding train can be kept at a safe distance.

[0016]

An embodiment of the present invention will be described below with reference to the drawings. (First Embodiment) FIG. 1 shows a configuration of an obstacle detecting device for a railway vehicle according to a first embodiment of the present invention, which is provided with an infrared camera 11 as an image pickup means. As shown in FIG. 2, the infrared camera 11 is attached to the leading position of the train car 10 and photographs the front of the car. A video signal captured by this camera is converted into digital data by an A / D (analog / digital) converter 12. The output signal from the A / D converter 12 is written to the image memory 13 based on a command from the arithmetic unit 14.

The arithmetic unit 14 includes a vehicle speed signal from a vehicle speed sensor 1 for detecting the speed of the vehicle 10, a kilometer (distance from a reference point) signal from a kilometer sensor 15 for detecting the current position of the vehicle 10, In addition, the route data stored in the route data memory 16 in advance, the vibration angle of the vehicle 10 from the gyro sensor 18, and the distance from the laser distance sensor 19 to the obstacle are supplied.

The above-mentioned vehicle speed sensor 1 and kilometer sensor 15
Is attached to the wheels of the vehicle 10 as shown in FIG. 2, and outputs, for example, speed data and distance data corresponding to the rotation speed.

The route data memory 16 stores route data indicating a track shape corresponding to about a kilometer as shown in FIGS. 3A and 3B. In the example shown in FIG. 3, the range from 0 to 100 km is a right (R) curve with a radius of 50 m and an intersection angle of 90 °, followed by a straight line of 400 m.
m, a left (L) curve with an intersection angle of 60 °, and then 100
A straight line of m continues. In FIG. 3, BTC (Bi
ginning of Transition Curve) is the starting point of the transition curve, BC
C (Biginning of Circular Curve) is the starting point of the circular curve, E
CC (END of Circular Curve) is the end point of the circular curve, ETC
(END of Transition Curve) indicates the end point of the transition curve. Although the route data shown in FIG. 3 is for the horizontal direction, the route data for the vertical direction is also recorded in the route data memory 16 in the same manner, for example, the gradient of the track corresponding to about km.

The gyro sensor 18 and the laser ranging sensor 19 are installed near the infrared camera 11 as shown in FIG. 2, and the gyro sensor 18 outputs the yawing angle and the pitching angle of the vehicle 10 at the camera mounting position. I do.

The arithmetic unit 14 in FIG. 1 is roughly divided into four parts, namely, a binarizing means 14a, an obstacle search area setting means 14b, and an obstacle presence / absence determining means 14c.
And a laser beam direction setting means 14d.
After obtaining the image data from the image memory 13, the binarizing means 14 a performs binarization using various image processing algorithms and records the binary image in the image memory 13. The obstacle search area setting means 14 b uses the vehicle speed signal from the vehicle speed sensor 1, the kilometer signal from the kilometer sensor 15, the route data from the route data memory 16 and the binary image from the image memory 13 to determine whether there is an obstacle. An area (obstruction search area) where the inspection is performed is set in the screen. The obstacle presence / absence determination unit 14c determines the presence / absence of an obstacle by performing various image processing in the above-described area (obstacle search area). The laser beam direction setting means 14 d calculates the direction of the obstacle from the position of the obstacle in the screen and the output of the gyro sensor 18, and outputs the calculated direction to the laser distance sensor 19.

The laser distance measuring sensor 19 comprises a laser beam direction setting means 19a and a laser distance measuring means 19b. The laser beam direction setting means 19a brakes the direction of the laser beam based on the direction of the obstacle output by the laser beam direction setting means 14d. The laser distance measuring means 19b is provided with the laser beam direction control driving means 1
Laser distance measurement is performed in the direction determined by 9a, and the distance to the obstacle is output to the arithmetic unit 14.

The presence / absence of an obstacle and the distance to the obstacle determined by the arithmetic unit 14 are sent to the output device 17 to notify the driver. FIG. 4 shows a flow of the operation in the arithmetic unit 14. In step 101,
Set the kilometer corresponding to the current position of the vehicle. In the next step 102, the output of the infrared camera 11 is digitized by the A / D converter 12 and stored in the image memory 13. In step 103, the image data stored in the image memory 13 is binarized by various well-known image processing algorithms to extract a rail portion as a binary image, and the binary image is recorded in the image memory 13.

In step 104, a kilometer corresponding to the current position of the vehicle is read from the kilometer sensor 15. In step 105, the route data corresponding to this kilometer is read from the route data memory 16. Next, in step 120,
A vehicle speed signal (vehicle speed) detected by the vehicle speed sensor 1 is read. In step 106, an obstacle search area is set in the screen using the binary image and the route data according to a method described later. In step 107, the presence / absence of an obstacle is determined by performing various image processing described later in the obstacle search area.

Then, in the next step 108, it is determined whether or not an obstacle is detected in the above step 107. If an obstacle is detected, the process proceeds to step 109, where the direction of the laser beam is set by a method described later. , Step 1
At 10, laser distance measurement is performed to measure the distance to the obstacle. In step 111, an output display for notifying the driver of the existence of the obstacle and the distance to the obstacle is executed. At step 112, it is determined whether or not the operation is completed. If the operation is completed, the present process is completed. If not, the process returns to step 102 to repeat the above operation.

Next, a method of setting the obstacle search area in step 106 will be described. FIG. 5 shows an example of the processing flow of the above method. Step 201 corresponds to steps 104 and 105 described above. By this operation, the laying state of the track ahead in the traveling direction can be known. Step 205 is a braking distance L corresponding to the vehicle speed.
And a margin ΔL for the driver to determine. The braking distance L can be calculated from the vehicle speed, the vehicle body weight, the braking characteristics and the like, and the margin ΔL may be set to, for example, about 30% of the braking distance L.

Next, in step 202, the three-dimensional coordinate system 20 as shown in FIG. 6 is set, and the coordinates (x, y, z) of the center point p21 of the left and right rails in front of (L + ΔL) m are calculated. . In step 203, the infrared camera 11 uses the point p2
When the image 1 is photographed, a position (m, n) 24 at which the point p can be seen in the image 23 is calculated as shown in FIG.

FIG. 7 shows a digital image stored in the image memory 13 after photographing by the infrared camera 11.
The coordinates (m, n) 24 are given by a mathematical coordinate conversion calculation using the camera mounting position, angle, and camera angle of view, which can be uniquely determined by the three-dimensional coordinate system 20, as parameters. In step 204, an obstacle search area 25 is set around the position (m, n) 24 where the point p can be seen in the screen. The size of the obstacle search area is arbitrary, but if it is too large, it is meaningless, and if it is too small, it does not include the area to be inspected.

An example of a method for setting the size of the obstacle search area will be described below. Considering the construction limit of the vehicle, it is considered that there is no problem if there are no obstacles in the area of 3.8 m x 3.8 m on the track. Therefore, it is calculated how large the area of 3.8 m × 3.8 m in front of (L + ΔL) m is within the screen. For example, (L + ΔL) is 1500
Consider the case of m. This depends on the number of pixels in the horizontal and vertical directions, and the angle of view in the horizontal and vertical directions of the camera. The number of pixels is 640 × 486, and the angle of view is 3.5 ° × 2.7.
In this case, the area of 3.8 m × 3.8 m in front of 1500 m has a size of 27 × 27 (pixel) in the screen. Therefore, an obstacle search area 25 having a size of 27 × 27 (pixels) is set around the coordinates (m, n) 24 as shown in FIG. When the distance (L + ΔL) is other than 1500 m, the size of the obstacle search area on the screen can be determined in the same manner.

In this embodiment, the coordinates (m, n) 24 are calculated each time using the data indicating the state of the laying of the track as shown in FIG. 3 as the route data.
It is also conceivable that the coordinates (m, n) 24 obtained in 03 are stored in association with about kilometers and used as route data. That is, the route data may be stored in any form as long as the coordinates (m, n) 24 corresponding to kilometers are known.

The method shown in FIG. 5 is applicable when the influence of vehicle vibration can be ignored. Actually, the camera mounting position and the angle with respect to the vehicle change due to the vibration, and the image is displaced. That is, an image different from the image when the vehicle is stationary is captured. Step 2 above
Position (m, n) at which point p found in 03 can be seen in image 23
Reference numeral 24 denotes a position on the screen when the vehicle is stationary. When the camera mounting position and the angle are greatly changed due to vibration, the position (m, n) 24 shifts in the screen, which causes a problem. FIG. 8 shows a processing flow of a method for eliminating the influence of vibration.

Step 201 in FIG. 8 has the same contents as step 201 in FIG. In step 301, a rail image 30 shown in FIG. 9 in which left and right rails are drawn using the route data stored in the route data memory 16 is generated in the image memory 13. The rail image 30 is, for example, a binary image in which a rail is drawn with a bit “1” on the background of a bit “0”.

An example of a method for generating the rail image 30 will be described below. In step 202 of FIG. 5, not only the point in front of (L + ΔL) m but also, for example, a point in front of 200 to 1500 m is calculated every 100 m. In step 203, the coordinates in the screen are obtained. Since these are the coordinates of the center part of the rail, the coordinates of the left and right rails are obtained by adding the number of pixels between the rails according to the distance. The coordinates are connected by a straight line to generate left and right rail images 200 to 1500 m ahead. It is not absolutely necessary to calculate 200 to 1500 m every 100 m, and it is needless to say that the calculation may be changed as needed. Also, as described above, the above step 3
It is also conceivable to store the coordinates of the left and right rails in the screen for each 200 m to 1500 m ahead and 100 m calculated in 01 in association with the distance of about km, and use the coordinates as route data.
In addition, any method can be used for storing the route data as long as a rail image 30 corresponding to about a kilometer can be generated.

In step 302, the shift amounts ρm and ρn are obtained by correlating the rail image 30 with the binary image 31 obtained by extracting the rail portion shown in FIG. The binary image 31 is shown in FIG.
As shown in the figure, for example, the rail 34a has a bit "1".
This is a binary image as represented by. Above displacement ρm3
As shown in FIG. 11, 5m is the number of pixels that are shifted in the horizontal direction (m-axis direction) between the actual rail 34 and the drawn rail 33, and the shift amount ρn35n is shifted in the vertical direction (n-axis direction). The number of pixels.

As shown in FIG. 9, a window 32 is set in the rail image 30 so as to surround the drawn rail 33. A correlation value in the window 32 is obtained by shifting one image up, down, left and right from a state in which the two images are completely overlapped. Specifically, a logical product image of the rail image 30 and the binary image 31 is obtained, and the sum of the bits “1” in the window 32 is set as the correlation value. The shift amount in the horizontal direction when the correlation value is maximum is regarded as the shift amount ρm, and the shift amount in the vertical direction is regarded as the shift amount pn. The method of setting the window for taking the correlation is not necessarily required to be the above-described method, and the shift amounts ρm, ρn
Any window can be used as long as it can be obtained accurately.

Next, at step 303, the deviation amount ρm35
The obstacle search area 25 is set by correcting m and pn35n. As shown in FIG. 12, the position (m,
(n) 24 centered on a point (m + ρm, n + ρn) 36 in which 24 is corrected by shift amounts ρm35m and pn35n (L + Δ
An obstacle search area 25 having a size corresponding to L) is set. That is, an accurate obstacle search area 25 can be set by obtaining a shift amount in the screen and correcting the shift amount.

FIG. 13 shows an example of the obstacle presence / absence determination processing in step 107 in FIG. This apparatus uses an infrared camera 11 as an imaging means. Infrared camera 11
When an obstacle such as a car is photographed by the camera, a high-temperature portion such as an engine is reflected brightly. Utilizing this feature, if there is a high-luminance portion in the obstacle search area 25, it is determined that there is an obstacle. In step 401, image data in the obstacle search area 25 is extracted from the digital image 23 stored in the image memory 13. In step 402, for example, the image data is binarized using an appropriate threshold value, and a high-luminance portion (a portion having higher luminance than the background)
Is extracted. In this case, for example, the high-luminance portion is bit “1”, and the other portions are “0”.

In step 403, step 402
It is determined whether or not a high-luminance portion has been extracted from the binary image generated by. As an example of the determination method, if there is a bit “1”, it is determined that there is an obstacle, and the process proceeds to step 404Y. Step 404 if there is no obstacle
Go to N. In this method, the presence or absence of an obstacle is determined based on the presence or absence of a high-luminance portion in the obstacle search area 25. The binarization method in step 402 uses any method that can extract a high-luminance portion. May be a method,
Also, there is no reason that the method of determining the presence or absence of a high-luminance portion in step 403 must necessarily be the above method.

The obstacle presence / absence determination result 404Y or 404N obtained by the above processing is output to step 108 in FIG. 4, and if there is an obstacle, the process proceeds to step 109 to measure the distance to the obstacle. Here, a method of performing distance measurement using a laser beam will be described. There is no reason that a laser beam must always be used as the distance measuring means, and any means may be used as long as the distance to the obstacle can be measured.

An example of the laser beam direction setting processing in step 109 in FIG. 4 will be described below. FIG. 14 is an image in which an obstacle exists. The screen size is 2M × 2N (pixels), and the camera angle of view is 2θh (°) in the horizontal direction and 2θv (°) in the vertical direction. The coordinates 41 of the obstacle in the screen are (m0, n0), and the center 40 of the screen is (M, N). At this time, the direction angle of the obstacle viewed from the optical axis of the camera (Δh in the horizontal direction and Δv in the vertical direction) is given by the following equation. However, in the horizontal direction, the right side from the center is positive,
In the vertical direction, the portion above the center is defined as positive.

Δh = (m0−M) · θh / M Δv = − (n0−N) · θv / N FIG. 15 is a view of the vehicle as viewed from the front. Infrared camera 1
1. The laser ranging sensor 19 is installed coaxially and installed on its optical axis, and the optical axis is in the same direction.
Therefore, the direction angles Θh ′ and Θv ′ of the obstacle viewed from the laser distance sensor 19 are obtained by correcting the difference Δh42 between the height of the mounting position of the laser distance sensor 19 and the infrared camera 11. This calculation is given by a mathematical coordinate transformation. On the other hand, the vehicle is traveling while capturing images from the infrared camera 11 and performing the above processing. For this reason, the obstacle direction angle at the time of performing laser ranging differs from the obstacle direction angle at the time of capturing an image. In order to avoid the above situation, as shown in FIG.
Is mounted near the infrared camera 11. The gyro sensor 18 detects the yaw angle α of the vehicle at the camera mounting position.
And the pitching angle β. The yawing angle at the time of image capture is α0, and the pitching angle is β0. Assume that the yawing angle immediately before performing the laser ranging is α1, and the pitching angle is β1. Obstacle direction angles Θh 'and Θv' viewed from the laser distance sensor 19 are finally given by the following equations.

.DELTA.h '=. DELTA.h' + (. Alpha.1-.alpha.0) .DELTA.v '=. DELTA.v' + (. Beta.1-.beta.0) Next, an example of laser ranging in step 110 in FIG. The above-mentioned ′ h 'and 渡 v' are passed from the laser beam direction setting means 14d of FIG. 1 to the laser beam direction control driving means 19a to perform laser ranging.

FIG. 16 shows a laser beam direction control driving means 1.
An example of the principle of 9a is shown. This is called a wedge prism rotation method. Wedge-shaped prism 4
By rotating 4, 45, the laser beam is swung in an arbitrary direction. FIG. 17 is a view of the prisms 44 and 45 viewed from the lateral direction. Assuming that the angle 48 at which the laser beam is refracted at the wedge is θ as shown in the figure, the scanable range 46 of the beam becomes a 4θ conical range as shown in FIG. One of the two prisms 44 and 45 can change the position in the circumferential direction, and the other prism can change the position in the radial direction. That is, the prism 4
By controlling the rotation angles of 4, 45, the laser beam can be swung in a predetermined direction.

FIG. 18 shows a laser beam direction control driving means 1.
9 shows an example of 9a. Direction angle of laser beam {h ', Θ
v 'is passed from the laser beam direction setting means 14d to the servo driver 50 in the laser beam direction control driving means 19a. The servo driver 50 rotates the motor 51a by an amount corresponding to the angle Θh 'to
Rotate 4. An encoder 52a is attached to the motor 51a, and its rotation angle is fed back to the servo driver 50 and controlled. Similarly, the motor 51b is rotated by an amount corresponding to Θv 'to
Rotate 5 An encoder 52b is attached to the motor 51b, and its rotation angle is fed back to the servo driver 50 and controlled. On the other hand, the laser beam 47 output from the laser distance measuring means 19b passes through the wedge prisms 44 and 45, and moves toward the obstacle. Thereby, the distance to the obstacle is measured by, for example, the pulse time difference counting method, and the value is passed to the arithmetic unit 14. As a result, in step 111 of FIG.
Thus, the driver is notified of the presence of the obstacle and the distance to the obstacle via the output device 17.

In the above embodiment, for example, a case where a car stopped at a railroad crossing is detected as an obstacle is shown. However, when the distance from the preceding train is short, the same as in the above embodiment is performed. Thus, the preceding train can be dealt with as an obstacle. That is, the presence or absence of a preceding train is determined by the same processing as in the above-described embodiment, and if there is a preceding train, the distance to the preceding train is measured, and the speed limit of the vehicle is obtained by arithmetic processing according to the distance. Limit vehicle speed to speed. As a result, the distance from the preceding train can be kept at a safe distance.

(Second Embodiment) Next, a second embodiment of the present invention will be described. The second embodiment shows another example in which the preceding train is detected as an obstacle.

FIG. 19 is a block diagram showing a configuration of an obstacle detecting device for a railway vehicle according to a second embodiment of the present invention. Referring to FIG. 1, reference numeral 11a denotes a CCD camera for photographing the front of the vehicle. A video signal photographed by the CCD camera 11a is converted into digital data by an A / D converter 12, and based on a command from an arithmetic unit 14, Image memory 13
Is written to.

The arithmetic unit 14 stores the vehicle speed signal from the vehicle speed sensor 1 for detecting the speed of the vehicle, the kilometer signal from the kilometer sensor 15 for detecting the current position of the vehicle, and the route data memory 16 in advance. Route data is supplied.

The arithmetic unit 14 includes a binarizing means 14A,
It comprises a preceding train search area setting means 14B, a preceding train presence / absence determining means 14C, and a distance measuring means 14D to the preceding train. After obtaining the image data from the image memory 13, the binarizing means 14 A performs binarization using various image processing algorithms, and records the binary image in the image memory 13. The preceding train search area setting means 14B uses the vehicle speed signal from the vehicle speed sensor 1, the kilometer signal from the kilometer sensor 15, the route data from the route data memory 16 and the binary image from the image memory 13 to determine whether or not the preceding train exists. Set the area (preceding train search area) where the inspection is performed on the screen.
The preceding train presence / absence determination means 14C determines the presence / absence of the preceding train by performing various image processing in the above-mentioned area (preceding train search area). Distance measuring means 14D to preceding train
Calculates the distance to the preceding train based on the position of the preceding train in the screen, the kilometer signal from the kilometer sensor 15 and the route data from the route data memory 16, and outputs the calculated distance to the speed limit control device 2.

Then, the speed of the vehicle is limited based on the speed information obtained by the speed limit control device 2.
Next, the operation of the above embodiment will be described.

FIG. 20 shows the flow of operation in the arithmetic unit 14. First, at step 101, a kilometer corresponding to the current position of the vehicle is set. In the next step 102, the output of the CCD camera 11a is output to the A / D converter 1
2 and is stored in the image memory 13. In step 103, the image data stored in the image memory 13 is binarized by various well-known image processing algorithms to extract a rail portion as a binary image, and the binary image is recorded in the image memory 13.

In step 104, a kilometer corresponding to the current position of the vehicle is read from the kilometer sensor 15. In step 105, the route data corresponding to this kilometer is read from the route data memory 16. Next, in step 120,
The vehicle speed signal detected by the vehicle speed sensor 1 is read. In step 121, a preceding train search area is set in the screen using the binary image and the route data in the same manner as in the first embodiment. In step 122, the presence / absence of a preceding train is determined by performing various image processing described later in the preceding train search area.

Then, in the next step 123, it is determined whether or not the preceding train is detected in the above step 122. If the preceding train is detected, the process proceeds to step 124, and the distance to the preceding train is measured by the distance measuring means 14D. Obtained by calculation. That is, the distance measuring means 14D reads the route data from the route data memory 16 in accordance with the kilometer detected by the kilometer sensor 15, and measures the distance to the preceding train by image processing using the route data. Based on the distance to the preceding train determined by the measurement process, the speed limit of the vehicle is calculated by an arithmetic process, and the speed of the vehicle is limited to an appropriate speed (step 125). As a result, the distance from the preceding train can be kept at a safe distance.

When the processing in step 125 is completed, or when it is determined in step 123 that there is no preceding train, it is determined in step 112 whether or not the operation is to be completed. If not, the process returns to step 102 and the above operation is repeated.

FIG. 21 shows an example of the preceding train presence / absence determination processing in step 122 in FIG. First, in step 501, a tracking process of the rail is performed. FIG. 22 shows an example of this rail tracking method. Since the position of the rail is known in the preceding train search area setting processing shown in step 121 in FIG. 20, the original image is horizontally scanned as shown by arrows a1, a2,... In FIG. At this time, if there is no preceding train, there is a luminance difference between the position of the rail 34 and the rail.

However, when the preceding train 60 is present, the difference between the position of the rail 34 and the luminance between the rails disappears, so that the rail is closed. Accordingly, by checking the position of the rail 34 and the luminance difference between the rails in step 502 in FIG. 21, it is possible to determine the presence or absence of the preceding train. Step 50 if there is no preceding train
In step 3, it is determined whether or not the tracked position of the rail has reached the search area. If not, the flow returns to step 501 to further track the rail. If it has reached the search area in step 503, it is determined in step 504N that there is no preceding train. If the rail is closed in step 502, it is determined in step 504Y that there is a preceding train.

If it is determined in step 504Y that there is a preceding train, the process proceeds to step 124 in FIG. 20 to calculate the distance to the preceding train. The point where the rail is closed can be calculated how many meters ahead from the route data stored in the route data memory 16, so that the distance to the preceding train can be calculated. By repeating this operation, the speed of the preceding train can be calculated. Then, in step 125, the speed limit is calculated from the distance to the preceding train and the speed of the preceding train to control the speed of the vehicle. According to the second embodiment, it is possible to calculate where the rail in front of an arbitrary distance is visible in the screen, and to calculate the braking distance of the vehicle by calculating the speed of the preceding train. Can be determined accurately and in a short time, the presence or absence of a preceding vehicle can be reliably determined in an area beyond the braking distance, and the speed limit can be calculated to control the vehicle speed.

[0058]

As described above in detail, according to the obstacle detecting device for a railway vehicle according to the present invention, a rail ahead of an arbitrary distance can be displayed on the screen regardless of the laying state of the line in front of the vehicle by using the route data. It is possible to calculate where the vehicle can be seen in the vehicle and calculate the braking distance from the vehicle speed detected by the vehicle speed sensor. Therefore, it is possible to accurately and quickly determine an obstacle search area to be inspected for an obstacle. For this reason, it is possible to accurately determine the presence or absence of an obstacle in an area beyond the braking distance and notify the driver, and high safety is guaranteed. Moreover, since the distance to the obstacle is measured and reported to the driver, the driver can respond to the obstacle according to the distance. Further, there is no need to install two cameras, and there are no problems such as complication of the system, extension of required calculation time, and high cost.

Further, according to the present invention, it is possible to calculate where the rail in front of an arbitrary distance can be seen in the screen and to calculate the braking distance of the vehicle by calculating the speed of the preceding train. The area to be inspected for the presence or absence of a train can be determined accurately and in a short time, and safety is guaranteed by always inspecting the area beyond the braking distance. That is, it is possible to reliably prevent a situation in which the distance to the preceding train at the time when the preceding train is detected is shorter than the braking distance, and since the distance to the preceding train is known, the vehicle speed is calculated by calculating the speed limit. Speed can be controlled.

[Brief description of the drawings]

FIG. 1 is a configuration diagram of an obstacle detecting device for a railway vehicle according to a first embodiment of the present invention.

FIG. 2 is an explanatory view of a vehicle on which the obstacle detection device is mounted.

FIG. 3 is a diagram showing an example of route data.

FIG. 4 is a flowchart illustrating a flow of processing of the obstacle detection device.

FIG. 5 is a flowchart for explaining the operation of an obstacle search area setting process in step 106 in FIG. 4;

FIG. 6 is an operation explanatory view in FIG. 5;

FIG. 7 is a view for explaining a method of setting an obstacle search area in FIG. 5;

FIG. 8 is a flowchart illustrating an example of processing for eliminating the influence of vibration in setting an obstacle search area.

FIG. 9 is a view for explaining a method of setting a window on a rail image when obtaining a correlation value.

FIG. 10 is a diagram showing a binary image in which a rail portion is extracted.

FIG. 11 is a diagram illustrating shift amounts ρm and ρn.

FIG. 12 is a view for explaining a method of setting an obstacle search area in FIG. 8;

FIG. 13 is a flowchart illustrating an obstacle presence / absence determination process in step 107 in FIG. 4;

FIG. 14 is a diagram illustrating an example of an image when an obstacle exists.

FIG. 15 is a diagram showing an example of the arrangement of devices when the vehicle is viewed from the front.

FIG. 16 is a view for explaining an example of the principle of the laser beam direction control drive means in FIG. 1;

FIG. 17 is a view of the wedge prism in FIG. 16 viewed from a lateral direction.

FIG. 18 is a diagram showing a configuration example of a laser beam direction control drive unit in FIG. 1;

FIG. 19 is a configuration diagram of an obstacle detection device for a railway vehicle according to a second embodiment of the present invention.

FIG. 20 is a flowchart illustrating detection and control operations of a preceding train in the embodiment.

FIG. 21 is a flowchart illustrating a preceding train presence / absence determination process in step 122 in FIG. 20;

FIG. 22 is a flowchart illustrating a rail tracking method in step 501 in FIG. 21;

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Vehicle speed sensor, 2 ... Speed limit calculation control apparatus, 10 ... Vehicle, 11 ... Infrared camera, 11a ... CCD camera, 12
... A / D converter, 13 ... image memory, 14 ... arithmetic unit,
14a: binarization means, 14b: obstacle search area setting means, 14c: obstacle presence / absence determination means, 14d: laser beam direction setting means, 14A: binarization means, 14B: preceding train search area setting means, 14C ... Preceding train presence / absence determining means, 14D: distance measuring means to the preceding train, 15: km sensor, 16: route data memory, 17: output device,
18 gyro sensor, 19 laser range sensor, 19
a: laser beam direction control driving means, 19b: laser distance measuring means, 20: three-dimensional coordinates, 21: (L + ΔL) m rail center point p forward, 22: rail, 23: digital image stored in image memory , 24: position where point p can be seen in the digital image, 25: obstacle search area, 30
... rail image, 31 ... binary image, 32 ... window for obtaining correlation value, 33 ... rail drawn using route data, 34 ... actual rail, 34a ... binary actual rail, 35m ... displacement amount .rho.m, 35n...
6: Point corrected by shift amounts ρm, ρn, 40: Center of the screen (m, n), 41: Coordinates of obstacles, 42: Difference Δh between mounting height of laser ranging sensor and infrared camera, 43:
Laser light source, 44, 45 ... wedge prism, 46: laser beam scanable range, 47 ... laser beam, 4
8: Angle θ at which light is refracted at the wedge, 50: servo driver, 51a, 51b: motor, 52a, 52b: encoder, 60: preceding train.

──────────────────────────────────────────────────続 き Continuing from the front page (72) Hiroshi Yamashita Hiroshi Yamashita, Hiroshima Pref., Hiroshima Pref. No.6-22, Mitsubishi Heavy Industries, Ltd. Hiroshima Laboratory (56) References JP-A-59-156089 (JP, A) (58) Fields investigated (Int. Cl. ⁷ , DB name) B61L 23/00

Claims (2)

(57) [Claims] 1. An image input device installed to take an image of the front of a traveling railway vehicle, an image memory storing an image captured by the image input device, and detecting a current position of the traveling vehicle. Position detecting means, speed detecting means for detecting the speed of the traveling vehicle, and how the rail looks in an image taken by the image input device corresponding to the vehicle position detected by the position detecting means. A route data memory that is stored in advance as route data obtained, a distance capable of avoiding a collision with an obstacle is obtained by a speed signal detected by the speed detecting means, and a position detection signal detected by the position detecting means; Obstacle search area setting means for setting an obstacle search area in a screen obtained by the image input device from the route data stored in the route data memory; Determining means for determining whether there is an obstacle in the obstacle search area for the image stored in the image memory, vibration angle detecting means for detecting vibration of the vehicle, and from the vehicle to the obstacle. Distance measuring means for measuring the distance of the obstacle; calculating means for calculating the direction of the obstacle from the position of the obstacle on the screen obtained by the image input device and the vibration angle obtained by the vibration angle detecting means; Distance measuring direction control means for controlling and driving the distance measuring direction of the distance measuring means based on the direction information obtained by the calculating means; presence or absence of an obstacle determined by the determining means and an obstacle measured by the distance measuring means And an informing means for informing a driver of a distance to the vehicle. 2. An image input device installed to take an image of the front of a running railway vehicle, an image memory storing an image taken by the image input device, and detecting a current position of the running vehicle. Position detecting means, speed detecting means for detecting the speed of the traveling vehicle, and how the rail looks in an image taken by the image input device corresponding to the vehicle position detected by the position detecting means. A route data memory that is stored in advance as route data obtained, and a distance that can avoid collision with the preceding train is obtained based on the speed signal detected by the speed detecting means, and a position detection signal detected by the position detecting means and Preceding train search area setting means for setting a preceding train search area in a screen obtained by the image input device from the route data stored in the route data memory Determining means for determining whether or not there is a preceding train in the preceding train search area with respect to the image stored in the image memory; distance measuring means for measuring a distance from the vehicle to the preceding train; Means for calculating a speed limit based on the distance to the preceding train measured by the means, and for limiting the vehicle speed.