JP6722529B2 - Obstacle detection system for railway - Google Patents

Description

The present invention relates to a railway obstacle detection system.

In the case of land transportation vehicles such as railroad vehicles, obstacles on the road surface on which they run may lead to serious accidents. Therefore, if it is possible to detect whether or not there is an obstacle on the road surface at an early stage, such an accident can be prevented.

Therefore, conventionally, a device for detecting whether there is an obstacle on the road surface has been proposed. For example, a map is created by imaging with a polarization imaging device, a location where the polarization angle (polarization direction) is uniform and continuous is identified as the road surface, and obstacles located at the location identified as this road surface are detected. A road surface obstacle detection device that does is proposed as an application example of a polarization imaging device (for example, refer to Patent Document 1).

Japanese Patent No. 4974543

By the way, since the road surface obstacle detection device described in Patent Document 1 specifies the road surface only by the polarization angle (polarization direction), the reliability of detecting the obstacle is lacking. Therefore, if the vehicle running on the road surface is an automobile or the like and is capable of avoiding obstacles by steering to the left and right at a relatively low speed, the road surface obstacle described in Patent Document 1 is unreliable. Even an object detection device can be actually applied.

However, the road surface obstacle detection device described in Patent Document 1 is unreliable if it is a vehicle that runs on a rail at high speed and cannot avoid obstacles by steering, such as a railway vehicle. If so, it cannot be applied because it may lead to a serious accident. On the other hand, when the road surface obstacle detection device described in Patent Document 1 is made to perform a complicated calculation for improving reliability, such a calculation may not catch up with the speed of the railway vehicle. , It may not be applicable to railway vehicles.

Therefore, it is an object of the present invention to provide an obstacle detection system for a railway that can improve reliability with a simple configuration.

In order to solve the above problems, a railway obstacle detection system according to a first aspect of the present invention is mounted on a railway vehicle and detects an obstacle on a rail on which the railway vehicle is about to travel. A system,
A polarization imaging camera that captures an image of the rail in front of the railway vehicle,
An information processing device for detecting an obstacle on the rail based on information of an image taken by the polarization imaging camera,
The information processing device is
A luminance information extraction unit that extracts luminance information in each pixel of the image,
A polarization information calculation unit that calculates the polarization direction and the polarization degree of each pixel based on the brightness information extracted by the brightness information extraction unit,
A rail detection unit for a pixel corresponding to the polarization direction and the polarization degree of each plant Teihan囲内and rail a predetermined value or more pixels for a given axis calculated in the polarization information calculating unit,
And an obstacle detection unit for detecting an obstacle on the rail based on the pixel which is said to correspond to the rail in the rail detection unit,
The obstacle detection unit has a continuity determination unit and/or a past information providing unit and a past information collating unit,
The continuity determination unit, if the pixels determined to correspond to the rail in the rail detection unit is non-continuous, determines that there is an obstacle on the rail,
The past information providing unit provides a pixel corresponding to the rail acquired in advance,
If the past information collating unit determines that the pixel corresponding to the rail in the rail detecting unit and the pixel corresponding to the rail provided from the past information providing unit do not match within the allowable range, the above-mentioned rail It is determined that there is an obstacle.

Furthermore, railway obstacle detection system according to the second invention, when the obstacle detecting unit in the railway obstacle detection system according to the first invention, detects an obstacle on the rail, the rail vehicle It controls the traveling speed.

According to the railway obstacle detection system, since the pixels corresponding to the rails are detected based on the polarization direction and the degree of polarization, the pixels corresponding to the rails are detected with high accuracy without complicated calculation, resulting in simple The reliability can be improved with a simple configuration.

It is a schematic perspective view which shows the obstacle detection system for railroads which concerns on embodiment of this invention. FIG. 3 is a schematic exploded perspective view of a polarization imaging camera included in the railway obstacle detection system. FIG. 3 is a block diagram of an information processing device included in the railway obstacle detection system. It is the figure which showed typically an example of the image photoed with the same polarization imaging camera. FIG. 5 is a partially enlarged view of FIG. 4. It is a figure which shows the polarization direction in each pixel of FIG. It is a figure which shows the polarization degree in each pixel of FIG. It is the figure which performed the binarization process in FIG. It is a figure which shows the past information for collating with FIG. It is a flowchart which shows operation|movement of the same obstacle detection system for railroads.

Hereinafter, a railway obstacle detection system according to an embodiment of the present invention will be described with reference to the drawings.
As shown in FIG. 1, this railway obstacle detection system is mounted on a railroad vehicle T, and obstacles on a rail 11 (that is, a rail 11 in front of the railroad vehicle T) on which the railroad vehicle T is about to travel. An object is detected.

The railway obstacle detection system 1 is provided in a driver's cab C of the railway vehicle T and has a polarization imaging camera 2 for taking a front view through a window glass W of the driver's cab C. An information processing device 3 (for example, a laptop computer) that processes information of the obtained image, and an alarm device 4 that issues an alarm when an obstacle is detected by the information processing device 3.

[Polarization imaging camera 2]
As shown in FIG. 2, the polarization imaging camera 2 includes a camera body 21 capable of continuously capturing a large number of still images (that is, a moving image), and a solid-state image sensor such as a CCD image sensor provided in the camera body 21. 22 and a polarization imaging filter 23 that covers the CCD image sensor.

The camera body 21 is arranged so as to capture an image of a building limit area (including the rail 11 of course) in front of the railway vehicle T. The solid-state image pickup device 22 only needs to be able to pick up an image from which the information processing device 3 can extract the luminance information, and therefore a device capable of picking up a monochrome image (for example, a monochrome CCD image pickup device) is sufficient. The polarization imaging filter 23 includes a polarizer array 5 in which polarizers 6 having different transmission axis directions 7 are arranged in 2 rows and 2 columns in order to obtain the polarization information (polarization direction and degree of polarization) of the light L passing therethrough. , And are arranged in a large number of rows and a large number of columns (3 rows and 3 columns in FIG. 2 as an example). In the polarizer array 5, for example, as shown in FIG. 2, the transmission axis directions 7 of the vertically and horizontally adjacent polarizers 6 may be different by 45°, and although not shown, it is arbitrary such as 30° or 60°. The angles may be different. The polarizer array 5 is configured in this way by using the data fitting method or the like in the information processing device 3 based on each intensity of the light L that has passed through each polarizer 6 of the polarizer array 5. This is for obtaining the polarization direction in each polarizer array 5 of. The method is not limited to the data fitting method, and any method such as Fourier analysis for obtaining the polarization direction may be used.

[Information processing device 3]
The information processing device 3 schematically includes a brightness information extraction unit 30 that extracts brightness information on each pixel of an image from the polarization imaging camera 2 and the brightness information extraction unit, as shown in FIGS. 1 and 3. A polarization information calculation unit 31 that calculates the polarization direction and the polarization degree of each pixel based on the brightness information extracted in 30. Further, the information processing device 3 further includes a rail detection unit 32 in which a pixel whose polarization direction and degree of polarization calculated by the polarization information calculation unit 31 are within a predetermined range and a predetermined value or more is a pixel corresponding to the rail 11. And an obstacle detection unit 36 for detecting an obstacle on the rail 11 based on a pixel which is determined to correspond to the rail 11 by the rail detection unit 32.

The brightness information extraction unit 30 acquires the information of the image 8 as shown in FIG. 4 in front of the railway vehicle T from the polarization imaging camera 2 and extracts the brightness information of each pixel of the acquired image 8. .. It should be noted that in the following description, when the above image is described, it is difficult to understand because the number of pixels is extremely large based on the image 8 shown in FIG. It shall be based on the image 80 shown.

The polarization information calculation unit 31 calculates the polarization direction of each pixel as shown in FIG. 6 and the polarization degree of each pixel as shown in FIG. 7 based on the luminance information of each pixel of the image 80 as shown in FIG. It is to be calculated. As is clear from the comparison between FIG. 5 and FIG. 6 corresponding thereto, in the pixel 81 corresponding to the rail 11 and some other pixels 82, the polarization direction is within a predetermined range (for example, 130 in FIG. 6 with respect to the horizontal axis). The characteristic is within (° to 140°). On the other hand, as is clear from a comparison between FIG. 5 and FIG. 7 corresponding thereto, it can be seen that the pixel 81 corresponding to the rail 11 has a polarization degree of a predetermined value (for example, 0.8 in FIG. 7) or more. To be

As shown in FIG. 3, the rail detection unit 32 has a polarization direction comparison unit 33, a polarization degree comparison unit 34, and a binarization processing unit 35. The polarization direction comparison unit 33 compares the polarization direction of each pixel with the predetermined range to tentatively detect pixels 81 and 82 whose polarization direction is within the predetermined range as pixels that can correspond to the rail 11. The polarization degree comparing unit 34 compares the polarization degree of each pixel with the predetermined value to temporarily detect a pixel 81 having a polarization degree of the predetermined value or more as a pixel that can correspond to the rail 11. The binarization processing unit 35 detects a pixel 81 tentatively detected as capable of corresponding to the rail 11 in both the polarization direction comparison unit 33 and the polarization degree comparison unit 34 as a pixel 81 corresponding to the rail 11. .. Further, as shown in FIG. 8, the binarization processing unit 35 sets the pixel 81 detected as corresponding to the rail 11 to 1 (or 0) and sets the other pixels to 0 (or 1). That is, the binarization process is performed.

As shown in FIG. 3, the obstacle detection unit 36 includes a continuity determination unit 37, a recording unit 38 (an example of a past information providing unit), and a past information collation unit 39.
The continuity determination unit 37 determines that if there are a plurality of pixel groups 81u and 81d (see FIG. 8) corresponding to one rail 11 (see FIG. 5) in the binarized image, that is, the pixel group. If 81u and 81d are discontinuous, it is determined that the obstacle 10 (see FIG. 5) is present on the rail 11, and other than that, it is determined that the obstacle 10 is not present on the rail 11. In the example shown in FIG. 8, the pixel groups 81u and 81d corresponding to the rail 11 are divided into the upper side 81u and the lower side 81d, that is, since there are a plurality of groups, it is determined that the obstacle 10 is on the rail 11. It An allowable range may be provided as to whether or not the pixel groups 81u and 81d are plural. For example, when the distance separating the plurality of pixel groups 81u and 81d corresponding to the rail 11 is several pixels or less, the plurality of pixel groups 81u and 81d corresponding to the rail 11 may be regarded as one pixel group 81.

The recording unit 38 stores information obtained by performing binarization processing on a past image when there is no obstacle 10 on the rail 11 (hereinafter referred to as past information), and stores the past information in the past. It is provided to the information matching unit 39. The past information is stored in the recording unit 38 in advance before the railway vehicle T travels.

The past information collating unit 39 collates the information from the binarization processing unit 35 as shown in FIG. 8 with the past information from the recording unit 38 as shown in FIG. 9, and this collation shows in FIG. If the pixels 81 and 84 corresponding to the rail 11 do not match between the information and the past information as shown in FIG. 9, it is determined that there is the obstacle 10 on the rail 11, and the rest is on the rail 11. It is determined that there is no obstacle 10. In the example shown in FIGS. 8 and 9, the pixel group 83 corresponding to the obstacle 10 on the rail 11 shown in FIG. 8 is different from that shown in FIG. To be judged. It should be noted that an allowable range may be provided as to whether or not they do not match. For example, if the number of mismatched pixels is equal to or less than a few% of the total number of pixels to be collated, it may be considered that they do not match (match).

[Alarm 4]
The alarm device 4 issues an alarm by voice or video when it is determined by either the continuity determination unit 37 or the past information comparison unit 39 that the obstacle 10 is on the rail 11. Although the alarm device 4 is illustrated as a configuration different from the information processing device 3 in FIGS. 1 and 3, the information processing device 3 may include the alarm device 4. As an example in which the alarm device 4 is incorporated in the information processing device 3, when the information processing device 3 is a laptop computer and the alarm is a voice, the alarm device 4 corresponds to a speaker incorporated in the laptop computer. If the alarm is an image, the alarm device 4 corresponds to the display provided on the laptop computer.

The operation of the railway obstacle detection system 1 will be described below.
As shown in FIG. 1, when the railway vehicle T is about to travel or is traveling, a moving image in front of the railway vehicle T is captured by the polarization imaging camera 2 (S1 in FIG. 10). At this time, the diaphragm of the lens (not shown) of the polarization imaging camera 2 is adjusted according to the headlight of the railway vehicle T and the sunshine conditions. The images 8 and 80 as shown in FIGS. 4 and 5 taken by the polarization imaging camera 2 are sent to the brightness information extraction unit 30 of the information processing device 3 as shown in FIG. Luminance information of each pixel is extracted at 30 (S2 in FIG. 10). The polarization information (polarization direction and degree of polarization) of each pixel is calculated by the polarization information calculator 31 based on the extracted brightness information (S3 in FIG. 10). Based on the calculated polarization direction and polarization degree, the rail detection unit 32 detects the pixel 81 corresponding to the rail 11 and the binarization process is performed (S4 in FIG. 10). The continuity determination unit 37 determines whether the pixel 81 corresponding to the rail 11 is discontinuous (S5 in FIG. 10), and if discontinuous, the alarm device 4 issues an alarm (S7 in FIG. 10). If the pixels 81 corresponding to the rails 11 are not discontinuous (that is, continuous), the past information collating unit 39 does not match the information from the binarization processing unit 35 with the past information from the recording unit 38. It is judged (S6 in FIG. 10), and if there is no mismatch (that is, if there is a match), a loop for processing the information of the next image sent from the polarization imaging camera 2 is entered. An alarm is issued (S7 in FIG. 10). After the alarm is issued, the railway vehicle T is decelerated (S8 in FIG. 10). As a result of this deceleration, the railway vehicle T may be stopped.

As described above, according to the railway obstacle detection system 1, the pixel 81 corresponding to the rail 11 is detected based on the polarization direction and the degree of polarization. Therefore, the pixel 81 corresponding to the rail 11 is high without performing complicated calculation. The accuracy is detected, and as a result, the reliability can be improved with a simple configuration.

Further, since the past information providing unit (recording unit 38) and the past information collating unit 39 perform collation with past information for detecting an obstacle, the reliability can be further improved with a simple configuration.
By the way, in the above embodiment, the obstacle detection unit 36 has been described as having the continuity determination unit 37, the recording unit 38 (an example of the past information providing unit), and the past information collation unit 39. Anything that detects whether there is the obstacle 10 on the rail 11 based on the information may be used. For example, the obstacle detection unit 36 may include only the continuity determination unit 37, or may include only the past information providing unit (recording unit 38) and the past information collating unit 39.

In the above embodiment, the recording unit 38 has been described as an example of the past information providing unit, but any device that provides past information to the past information collating unit 39 may be used. For example, the past information providing unit may be a receiving unit that receives past information from outside the information processing device 3 by wire or wirelessly and provides the past information to the past information matching unit 39.

Further, in the above embodiment, the recording unit 38 has been described as storing the past information in advance before the railway vehicle T travels, but binarization is performed when the obstacle 10 on the rail 11 is not detected. The information from the processing unit 35 may be configured to be overwritten at any time. With this configuration, the recording unit 38 provides the latest past information of the rail 11 that changes depending on the season and the years, so that the reliability can be further improved with a simple configuration.

In addition, in the above-described embodiment, it is described that the obstacle detector 36 gives an alarm by the alarm device 4 when the obstacle detector 36 detects the obstacle 10 on the rail 11. However, the railway vehicle T May be automatically decelerated or stopped (that is, the traveling speed is controlled). In this case, the obstacle detection unit 36 is connected to the speed control device (not shown) of the railway vehicle T, and the brake of the speed control device is activated by the detection of the obstacle 10 by the obstacle detection unit 36. To be done. With this configuration, when the obstacle 10 on the rail 11 is detected, the railway vehicle T is automatically decelerated or stopped, so that the reliability can be further improved with a simple configuration.

T Railway vehicle 1 Obstacle detection system for railway 2 Polarization imaging camera 3 Information processing device 4 Alarm device 5 Polarizer array 6 Polarizer 7 Transmission axis direction 21 Camera body 22 Solid-state image sensor 23 Polarization imaging filter 30 Luminance information extraction unit 31 Polarization Information calculation unit 32 Rail detection unit 33 Polarization direction comparison unit 34 Polarization degree comparison unit 35 Binarization processing unit 36 Obstacle detection unit 37 Continuity determination unit 38 Recording unit 39 Past information collation unit 81 Pixels corresponding to rails

Claims (2)

An obstacle detection system for a railway, which is mounted on a railway vehicle and detects an obstacle on a rail on which the railway vehicle is about to travel,
A polarization imaging camera that captures an image of the rail in front of the railway vehicle,
An information processing device for detecting an obstacle on the rail based on information of an image taken by the polarization imaging camera,
The information processing device is
A luminance information extraction unit that extracts luminance information in each pixel of the image,
A polarization information calculation unit that calculates the polarization direction and the polarization degree of each pixel based on the brightness information extracted by the brightness information extraction unit,
A rail detection unit for a pixel corresponding to the polarization direction and the polarization degree of each plant Teihan囲内and rail a predetermined value or more pixels for a given axis calculated in the polarization information calculating unit,
And an obstacle detection unit for detecting an obstacle on the rail based on the pixel which is said to correspond to the rail in the rail detection unit,
The obstacle detection unit has a continuity determination unit and/or a past information providing unit and a past information collating unit,
The continuity determination unit, if the pixels determined to correspond to the rail in the rail detection unit is non-continuous, determines that there is an obstacle on the rail,
The past information providing unit provides a pixel corresponding to the rail previously acquired,
If the past information collating unit determines that the pixel corresponding to the rail in the rail detecting unit and the pixel corresponding to the rail provided by the past information providing unit do not coincide with each other beyond the allowable range, the above-mentioned rail An obstacle detection system for railroads, characterized in that it is determined that there is an obstacle. The railway obstacle detection system according to claim 1, wherein the obstacle detection unit controls the traveling speed of the railway vehicle when an obstacle is detected on the rail.

Images