Control processing device, control processing method, and control processing system

The control processing device improves visibility assessment and obstacle detection in autonomous vehicles by using fixed imaging and optional radio wave/laser measurements to adapt control processes to weather changes, ensuring accurate operation.

JP2024165020APending Publication Date: 2024-11-28TOSHIBA INFRASTRUCTE SYSTEMS & SOLUTIONS CORPORATION
View PDF 17 Cites 0 Cited by

Patent Information

Application Number
JP2023080825
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-16
Publication Date
2024-11-28

AI Technical Summary

Technical Problem

Existing control processing systems for autonomous vehicles, such as railway vehicles, are affected by changes in weather conditions, which can impact visibility and obstacle detection accuracy.

Method used

A control processing device that includes an image acquisition unit, track detection unit, and visibility calculation unit to determine visibility values based on track length, using fixed imaging and lighting conditions, and optionally utilizes radio wave attenuation or laser/light measurement to complement visibility assessment.

Benefits of technology

Enhances visibility determination accuracy and obstacle detection, allowing for precise control adjustments, such as deceleration and warning signals, even in varying weather conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024165020000001_ABST
    Figure 2024165020000001_ABST
Patent Text Reader

Abstract

To provide a control processing device, a control processing method, and a control processing system for a railway vehicle, which can prevent an impact due to change in weather conditions.SOLUTION: A control processing device according to an embodiment comprises an image acquisition unit, a track information acquisition unit, a track detection unit, and a first visibility calculation unit. The image acquisition unit obtains a captured image of a railway vehicle in its travel direction. The track detection unit detects a track in the direction in which the railway vehicle in the captured image is moving, in accordance with the prescribed criteria. The first visibility calculation unit calculates a first visibility value regarding visibility on the basis of the length of the detected track.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] FIELD An embodiment of the present invention relates to a control processing device, a control processing method, and a control processing system. [Background technology]

[0002] Advances are being made in the automated driving of railway vehicles, automobiles, and the like. In such automated driving, driving assistance or control processing devices that perform automated driving execute control processes such as slowing down the vehicle, stopping the vehicle when it encounters an obstacle, sounding the horn, etc. However, there is a risk that the control processes may be affected by weather conditions. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2005-338941 A Summary of the Invention [Problem to be solved by the invention]

[0004] A control processing device, a control processing method, and a control processing system capable of suppressing the effects of changes in weather conditions are provided. [Means for solving the problem]

[0005] The control processing device according to this embodiment includes an image acquisition unit, a track information acquisition unit, a track detection unit, and a first visibility calculation unit. The image acquisition unit acquires a captured image of the direction of travel of the railcar. The track detection unit detects the track in the captured image in the direction of travel of the railcar according to a predetermined criterion. The first visibility calculation unit calculates a first visibility value related to visibility based on the detected length of the track. [Brief description of the drawings]

[0006] [Figure 1] FIG. 1 is a block diagram showing an example of the configuration of a control processing system according to the present embodiment. [Diagram 2] FIG. 2 is a block diagram showing a detailed configuration example of a control processing device according to the embodiment. [Diagram 3] FIG. 4 is a diagram showing an example of processing in a first mode. [Figure 4] FIG. 11 is a diagram showing an example of processing in the second mode. [Diagram 5] 6 is a flowchart showing an example of processing by a first visibility processing unit. [Figure 6] FIG. 11 is a block diagram showing an example of the arrangement of a control processing device according to a second embodiment. [Figure 7] 11 is a flowchart showing an example of processing by a control processing device. [Figure 8] FIG. 13 is a block diagram showing an example of the arrangement of a control processing device according to a third embodiment. [Figure 9] 13 is a flowchart showing an example of processing by a control processing device according to the third embodiment. [Figure 10] FIG. 13 is a block diagram showing an example of the arrangement of a control processing device according to a fourth embodiment. [Figure 11] 13 is a flowchart showing an example of processing by a control processing device according to the fourth embodiment. [Figure 12] FIG. 13 is a block diagram showing an example of the arrangement of a control processing device according to a fifth embodiment. [Figure 13] 13 is a flowchart showing an example of processing by a control processing device according to the fifth embodiment. [Figure 14] FIG. 13 is a block diagram showing an example of the arrangement of a control processing device according to a sixth embodiment. [Figure 15] 13 is a flowchart showing an example of processing by a control processing device according to the sixth embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In the drawings attached to this specification, the scale and aspect ratios have been appropriately changed and exaggerated from those of the actual objects for the convenience of illustration and understanding.

[0008] (First embodiment) Fig. 1 is a block diagram showing an example of the configuration of a control processing system 1 according to this embodiment. As shown in Fig. 1, the control processing system 1 according to this embodiment includes a control processing device 10 mounted on a railway vehicle 5, a traveling position information collection device 20, an obstacle detection device 30, a motor 40, a horn unit 50, and a communication device 60. The railway vehicle 5 runs on a track R100, which is a fixed track. A monitoring device 70 and a display device 80 are arranged in a centralized control room M110.

[0009] The control processing device 10 executes control processing for the railway vehicle 5 using images captured by the camera 111. For example, the control processing device 10 is capable of calculating visibility and executing control processing according to the visibility.

[0010] The camera 111 can continuously capture, for example, R, G, and B images as a running video. This camera 111 is fixed, for example, to the front of the railcar 5. Therefore, when each image constituting the running video captured while the railcar 5 is running on the tracks is captured at the same position, for example, it will be an image captured at the same angle and with the same imaging magnification. The camera 111 according to this embodiment corresponds to an image acquisition unit.

[0011] Furthermore, the railway vehicle 5 is equipped with a lighting device (not shown). The lighting device is fixed, for example, to the front of the railway vehicle 5, and irradiates light of the same illuminance and the same wavelength forward. For this reason, each image constituting a running video captured while the railway vehicle 5 is running on a track can be captured with the same illuminance if the external environment is the same. For this reason, images captured at the same position in the same environment will be reproducible images. In other words, changes in the state of the object captured in an image captured at the same position, for example, the track, are influenced by changes in the external environment. Details of the control processing device 10 will be described later.

[0012] The traveling position information collecting device 20 acquires the current position of the railcar 5, and outputs information on a predetermined track range relative to the current position in the traveling direction of the railcar 5. For example, the traveling position information collecting device 20 outputs information on the track R100 according to the current position of the railcar 5. The information on the track R100 is measured in advance, taking into account the reference weather conditions. For example, the weather conditions include relative humidity, temperature, date and time, and illuminance.

[0013] The traveling position information collection device 20 can acquire the current position by, for example, an odometer, or may acquire the current position by a Global Positioning System (GPS: Global Positioning Satellite).

[0014] The obstacle detection device 30 detects obstacles that may impede the travel of the railway vehicle 5, based on the captured image captured by the control processing device 10 and the detected tracks. This obstacle detection device 30 can change warning information according to the visibility value calculated by the control processing device 10. For example, the obstacle detection device 30 can differentiate between a first warning signal for an obstacle detected at a distance closer to the vehicle than the visibility value calculated by the control processing device 10 and a second warning signal for an obstacle detected at a distance farther than the first visibility value.

[0015] The motor 40 drives the wheels of the railway vehicle 5. The motor 40 can be controlled by an operation signal from a driver or a control signal from the control processing device 10.

[0016] The warning horn unit 50 emits a warning horn. The warning horn unit 50 can be controlled by an operation signal from the driver or a control signal from the control processing device 10.

[0017] The above-mentioned control processing device 10 outputs a deceleration control signal to the motor 40 and outputs a horn output signal to the horn unit 50 in response to the warning signal generated by the obstacle detection device 30. For example, the control processing device 10 executes different controls on the motor 40 for the first warning signal and the second warning signal. For example, the control processing device 10 executes control on the motor 40 so that the stopping distance for the first warning signal is shorter than the stopping distance for the second warning signal. Alternatively, the control processing device 10 executes control to cause the horn unit 50 to emit only the horn in response to the second warning signal.

[0018] The communication device 60 communicates with the monitoring device 70 in the centralized control room M110. For example, the communication device 60 transmits an image captured by the camera 111 to the monitoring device 70. The communication may be wired or wireless. The communication device 60 can also transmit an image captured by the camera 111 to the monitoring device 70 in response to a control signal from the control processing device 10. For example, the communication device 60 may transmit an image to the monitoring device 70 when the control processing device 10 outputs a deceleration control signal, a horn output signal, or the like in response to a warning signal.

[0019] The monitoring device 70 is used, for example, to monitor the operating state of the railway vehicle 5. For example, the monitoring device 70 accumulates information such as images, visibility values, warning signals, deceleration control signals, and horn output signals transmitted from the control processing device 10 via the communication device 60, and displays the information on the display device 80. The display device 80 is, for example, a monitor, and displays the images transmitted from the communication device 60.

[0020] Fig. 2 is a block diagram showing a detailed configuration example of the control processing device 10 according to this embodiment. As shown in Fig. 2, the control processing device 10 is a device that can change the control processing of the railway vehicle 5 according to the external environment. For example, the control processing device 10 changes the control processing method according to the visibility value, as described above.

[0021] The visibility value according to the present embodiment is a value related to visibility, and may be a value of visibility. This visibility value is a value that has a correlation with the density of fog, etc. For example, in the present embodiment, an evaluation value in the control process, such as whether or not it is necessary to adjust the driving speed, may be referred to as the visibility value. For this reason, the visibility value according to the present embodiment has a correlation with a general visibility indicating the limit of visibility with the naked eye, but a deviation may occur. For example, when visibility is deteriorated due to heavy rain, snow, darkness, etc., visibility generally decreases. On the other hand, the decrease in the visibility value in the control process may be suppressed by the control process including image processing more than the decrease in the limit of visibility.

[0022] This control processing device 10 is capable of controlling the motor 40 and the horn unit 50 of the railway vehicle 5, and includes a first visibility processing unit 11 and a determination processing unit 12. The first visibility processing unit 11 generates a first visibility value related to visibility based on the track length using an image captured by a camera 111. Note that the visibility value according to this embodiment may be referred to as visibility.

[0023] The determination processing unit 12 outputs a control signal according to the first visibility value generated by the first visibility processing unit 11, and is capable of changing a control processing method for the railway vehicle 5. Alternatively, the determination processing unit 12 outputs a control signal according to the first warning signal and the second warning signal output by the obstacle detection device 30 to the motor 40 and the horn unit 50. Details of the determination processing unit 12 will be described later.

[0024] Here, the first visibility processing unit 11 will be described in detail. This first visibility processing unit 11 has a camera 111, a track detection unit 112, and a first visibility calculation unit 113. As described above, the camera 111 captures an image including the track at a fixed angle. The first visibility processing unit 11 according to this embodiment has a first mode in which a first visibility value is calculated based on the difference between a first reference length and a detected track length, and a second mode in which the first visibility value is calculated based on the difference between a second reference length, the value of which is changed according to the current position of the railcar 5, and the detected track length.

[0025] Fig. 3 is a diagram showing an example of processing in the first mode. The first mode is mainly used on routes with many highly linear tracks. Figs. 3(a), (b), (c), and (d) are diagrams showing examples of tracks R100 detected by the track detection unit 112. The relative humidity increases in the order of Figs. 3(a), (b), (c), and (d), and for example, the fog becomes thicker in order, and the track length detected by the track detection unit 112 becomes shorter.

[0026] Fig. 4 is a diagram showing an example of processing in the second mode. The second mode is mainly used for railroad tracks with many curved tracks. Figs. 3(a), (b), (c), and (d) are diagrams showing examples of railroad tracks R100 detected by the railroad track detection unit 112. The relative humidity increases in the order of Figs. 3(a), (b), (c), and (d), and for example, the fog becomes thicker in order, and the railroad track length detected by the railroad track detection unit 112 becomes shorter.

[0027] The track detection unit 112 detects the track based on a predetermined criterion. As shown in FIG. 3, the track R100 generally extends from the near side toward the far side in the y direction from the viewpoint of the camera 111. For this reason, in the first mode, the track detection unit 112 according to this embodiment calculates the gradient of the luminance value in the horizontal axis (x-axis) direction as a feature amount, and detects the track using a point having a predetermined gradient value or more as a reference point. More specifically, the track detection unit 112 calculates the difference value of the luminance value in the horizontal axis (x-axis) direction, and detects a range in which the difference value between a pixel showing a predetermined positive value and a pixel showing a predetermined negative value is within a predetermined distance as the area of ​​the track R100. That is, the track detection unit 112 detects a range in which the absolute value of the difference value is a predetermined value or more, and the distance between the position of the difference value showing a positive value and the position of the difference value showing a negative value is within a predetermined distance (within a predetermined number of pixels) as the area of ​​the track R100. Note that the positive and negative values ​​of the difference value may be reversed depending on the image used and the direction of the difference calculation. Also, the track detection method is an example, and other detection methods may be used.

[0028] As shown in FIG. 4, in the curved track R100, there may be an image region in which the gradient of the luminance value in the vertical axis (y-axis) direction is larger than the gradient of the luminance value in the horizontal axis direction. For this reason, in the second mode, attention is paid to both the gradient of the luminance value in the horizontal axis direction and the gradient of the luminance value in the vertical axis direction, and feature data is acquired while switching the gradient to be focused on depending on the area (pixel group) to be detected. In the second mode, the track detection unit 112 acquires the calculation area and the calculation method of the difference value from the running position information collection device 20 depending on the position of the railcar 5. That is, since the imaging angle of the camera 111 is fixed, the running position information collection device 20 can store in advance the calculation area and the calculation method of the difference value depending on the position of the railcar 5. As a result, in the second mode, the track detection unit 112 detects the track R100 while changing the calculation area and the calculation method of the difference value depending on the position of the railcar 5.

[0029] The first visibility calculation unit 113 calculates the first visibility value based on the difference between the first reference length and the detected length of the line R100. That is, the first visibility calculation unit 113 calculates the first visibility value so that the smaller the absolute value of the difference between the first reference length and the detected length of the line R100, the larger the first visibility value becomes. In this case, the first visibility calculation unit 113 uses the first reference length, which is a predetermined fixed value, in the first mode, so that the visibility calculation can be performed faster.

[0030] On the other hand, in the case of a curved track R100, even if the visibility is the same, the detected length of the track R100 on the image changes depending on the curvature of the track R100. Similarly, the visibility may be affected by the gradient angle of the track R100. Therefore, in the second mode, the first visibility calculation unit 113 acquires a second reference length corresponding to the position of the railcar 5 from the running position information collection device 20, and sets the second reference length as the reference length. That is, in the second mode, the first visibility calculation unit 113 calculates the first visibility value so that the smaller the absolute value of the difference between the second reference length and the detected length of the track R100 becomes, the larger the first visibility value becomes. This makes it possible to suppress a decrease in the accuracy of the visibility calculation for the track R100 with a high curvature and for the area in the image where the gradient of the track R100 changes. It is possible to use the second mode for the track R100 with a high linearity. The calculation of the first visibility value may be performed at predetermined time intervals. For example, the first visibility calculation unit 113 calculates the first visibility value at one-minute intervals.

[0031] 2 again, the determination processing unit 12 includes a storage unit 121, a visibility determination unit 122, and a control unit 123. The storage unit 121 stores, for example, position information of the railway vehicle 5, a time, the detected track length of the track R100, and a first visibility value in association with each other. For example, the time may be the time of a reference clock included in the determination processing unit 12. Furthermore, the position information of the railway vehicle 5 may be information output by the traveling position information collection device 20.

[0032] The visibility determiner 122 outputs a control command signal corresponding to the first visibility value calculated by the first visibility calculator 113 to the controller 123. For example, when the first visibility value becomes smaller than a predetermined distance value, the visibility determiner 122 outputs a control command signal having information on the first visibility value to the controller 123. For example, when the first visibility value becomes smaller than a predetermined distance value, the visibility determiner 122 outputs a control command signal having information on the first visibility value to the controller 123.

[0033] The control unit 123 is capable of performing control processing of the railway vehicle 5. For example, when the first visibility value becomes smaller than a predetermined distance, the control unit 123 executes control on the motor 40 to decelerate the railway vehicle 5. Alternatively, when the first visibility value becomes smaller than a predetermined distance, the control unit 123 transmits an alarm signal having information on the first visibility value to the monitoring device 70 via the communication device 60. As a result, the monitoring device displays an image of the camera 111 together with alarm information having information on the visibility, for example, via the display device 80. Also, when the railway vehicle 5 is being operated by a person, the control unit 123 notifies the driver's seat of the railway vehicle 5 of alarm information when the first visibility value becomes smaller than a predetermined distance. For example, the control unit 123 can notify the driver of the alarm information together with the first visibility value via a display unit, a speaker, or the like in the driver's seat. As a result, the driver can objectively grasp the situation of the outside world, and can reflect this in the operation of the railway vehicle 5.

[0034] 5 is a flowchart showing an example of processing by the first visibility processing unit 11 according to this embodiment. Here, an example of the first mode will be described.

[0035] As shown in Fig. 5, first, the camera 111 captures an image (step S11). Next, the track detection unit 112 detects the track R100 from the image (step S12). Next, the first visibility calculation unit 113 calculates the length of the track R100 detected by the track detection unit 112 (step S13). Next, the first visibility calculation unit 113 calculates a difference value between the first reference length and the calculated length of the track R100 (step S14), and calculates a first visibility value according to the difference value (step S15).

[0036] As described above, the control processing device 10 according to this embodiment captures an image of the track R100, detects the track R100 from the image using the same criteria, and calculates the first visibility value based on the length of the track R100 in the image. The track R100 has the same size and quality regardless of the position. As a result, when the track R100 is detected from the image using the same detection criteria such as the magnitude of the difference value, the length of the track R100 changes depending on the external environment such as the density of fog. For this reason, by comparing the length of the track R100 detected from the image with the length of the reference value, it is possible to obtain the first visibility value with high accuracy. In particular, since the length of the track R100 in the captured image and the visibility limit of the driver's naked eye are highly similar, it is easy to set a standard for detecting the track R100 so as to be closer to the visibility limit of the naked eye. As a result, it is possible to obtain a first visibility value closer to the visibility limit of the naked eye.

[0037] Second embodiment The control processing device 10 according to the second embodiment differs from the control processing device 10 according to the first embodiment in that it further includes a second visibility processing unit 13 that calculates a second visibility value from the received radio waves. The differences from the control processing device 10 according to the first embodiment will be described below.

[0038] FIG. 6 is a block diagram showing a configuration example of the control processing device 10 according to the second embodiment. As shown in FIG. 6, the control processing device 10 according to the second embodiment further includes a second visibility processing unit 13. The second visibility processing unit 13 calculates a second visibility value from the attenuation of the received radio wave. This second visibility processing unit 13 has an irradiation unit 131, a receiving unit 132, and a second visibility calculation unit 133. The irradiation unit 131 irradiates millimeter waves or laser light. For example, when the railcar 5 reaches a reference position based on an instruction signal from the running position information collection device 20, the irradiation unit 131 irradiates millimeter waves or laser light. In front of this reference position, a measurement target that is at a position at a known distance from the reference position and has a known reflectance is set in advance.

[0039] The receiving unit 132 receives the reflected light of the millimeter wave or the laser light. The second visibility calculation unit 133 calculates a second visibility value according to the amount of attenuation of the received signal received by the receiving unit 132 within a predetermined time. For example, a preliminary experiment is performed in advance according to the relative humidity or the fog density, and the second visibility calculation unit 133 calculates the second visibility value using the measurement data. That is, the second visibility calculation unit 133 executes a calculation to reduce the second visibility value as the amount of attenuation of the received signal increases. The second visibility calculation unit 133 is not affected by the amount of light in the outside world, so it is possible to perform measurements in a dark place even without illumination light.

[0040] When using laser light, the second visibility calculation unit 133 can also measure the distance to the measurement target based on ToF (Time of Flight). It is known that the distance to the measurement target varies depending on the humidity. For this reason, the second visibility calculation unit 133 can also calculate the second visibility value depending on the distance to the measurement target. In this case, preliminary experiments are also performed in advance according to relative humidity or fog density, and the second visibility calculation unit 133 calculates the second visibility value using the measurement data. That is, the second visibility calculation unit 133 executes a calculation to reduce the second visibility value as the distance to the measurement target decreases. In this case, the second visibility calculation unit 133 is not affected by the amount of light from the outside, so that measurement is possible in a dark place even without shooting light.

[0041] The storage unit 121 stores the visibility calculated by the second visibility calculation unit 133 in association with the time and the measurement position. The visibility determination unit 122 according to this embodiment is capable of determining and generating a visibility value in a complementary manner based on the first visibility value calculated by the first visibility processing unit 11 and the second visibility value calculated by the second visibility processing unit 13.

[0042] For example, in a time period or place where the detection accuracy of the first visibility processing unit 11 is reduced due to nighttime or a dark place, the visibility determination unit 122 generates a visibility value based on the second visibility value calculated by the second visibility processing unit 13. Alternatively, when the railway detection unit 112 cannot detect the railway R100, the visibility determination unit 122 generates a visibility value based on the second visibility value calculated by the second visibility processing unit 13. In this case, it is possible to generate a visibility value with higher accuracy even at nighttime.

[0043] On the other hand, when the railroad detection unit 112 can detect the railroad R100, the visibility value is generated based on the first visibility value. In this case, the visibility value can be generated even at a position other than the reference position.

[0044] 7 is a flowchart showing an example of processing by the control processing device 10 according to this embodiment. An example of the first mode will be described here.

[0045] As shown in Fig. 7, steps S11, 13, 14, and 15 execute the same processing as in Fig. 5. Meanwhile, the track detection unit 112 according to this embodiment executes a process of detecting the track R100 from the image, and then executes a process of determining the detection accuracy (step S12a). For example, when the track detection unit 112 cannot detect the track R100 due to conditions such as nighttime, it outputs an error signal to the visibility determination unit 122 (NO in step S12a). Meanwhile, when the track detection unit 112 can detect the track R100 from the image (YES in step S12a), it outputs information on the detected track R100 to the first visibility calculation unit 113. As a result, the first visibility processing unit 11 executes the processes from steps S13 to S15.

[0046] On the other hand, when the second visibility processing unit 13 reaches the reference position, the irradiation unit 131 irradiates the millimeter wave or laser forward (step S16). Next, the receiving unit 132 receives the reflected light of the millimeter wave or laser light (step S17). The second visibility calculation unit 133 calculates a second visibility value according to the amount of attenuation of the reception signal received by the receiving unit 132 within a predetermined time period (step S18).

[0047] As described above, the control processing device 10 according to this embodiment generates a visibility value by complementarily using the first visibility value generated by the first visibility processing unit 11 and the second visibility value generated by the second visibility processing unit 13 using millimeter waves or laser light. As a result, in a time period or place where the generation accuracy of the first visibility processing unit 11 decreases, the visibility value generated by the second visibility processing unit 13 is used, thereby making it possible to suppress a decrease in the measurement accuracy of the visibility value.

[0048] Third embodiment The control processing device 10 according to the third embodiment differs from the control processing device 10 according to the second embodiment in that it further includes an image processing unit 140 that executes image processing according to the visibility value. The differences from the control processing device 10 according to the second embodiment will be described below.

[0049] FIG. 8 is a block diagram showing an example of the configuration of the control processing device 10 according to the third embodiment. As shown in FIG. 8, the control processing device 10 according to the third embodiment further includes an image processing unit 140. The image processing unit 140 executes image processing on the image captured by the camera 111 according to the visibility value generated by the visibility determination unit 122. For example, the image processing unit 140 executes image processing on the image captured by the camera 111 with the strength of the fog removal processing strengthened as the visibility value becomes smaller. For example, the distribution of humangrams for the luminance value of the image captured by the camera 111 is changed to a distribution in which the density of fog or the like is reduced. The image processing unit 140 strengthens the degree of this change as the visibility value becomes smaller. Alternatively, the image processing unit 140 executes sharpening processing to emphasize contrast. In this case as well, the image processing unit 140 strengthens the strength of the sharpening as the visibility value becomes smaller.

[0050] The obstacle detection device 30 detects obstacles using an image in which the image processor 140 changes the distribution of humangrams according to the visibility, for example. In this case, the detection accuracy of the obstacle detection device 30 is improved. As a result, the accuracy of the generation of the warning signal generated by the obstacle detection device 30 is also improved.

[0051] Fig. 9 is a flowchart showing an example of processing by the control processing device 10 according to the third embodiment. As shown in Fig. 9, the image processing unit 140 acquires the visibility value generated by the visibility determination unit 122 and the image captured by the camera 111 (step S21). Next, the image processing unit 140 executes image processing according to the visibility value on the image captured by the camera 111 (step S22).

[0052] As described above, the image processing unit 140 of the control processing device 10 according to this embodiment performs image processing of fog removal processing according to the visibility value generated by the visibility determination unit 122 on the image captured by the camera 111. This allows the image processing unit 140 to perform image processing according to the visibility value, making it possible to perform image processing with appropriate processing strength.

[0053] (Fourth embodiment) The control processing device 10 according to the fourth embodiment differs from the control processing device 10 according to the third embodiment in that it further includes a rainfall processing unit 14. The differences from the control processing device 10 according to the third embodiment will be described below.

[0054] FIG. 10 is a block diagram showing a configuration example of the control processing device 10 according to the fourth embodiment. As shown in FIG. 10, the control processing device 10 according to the fourth embodiment further includes a rainfall processing unit 14. The rainfall processing unit 14 generates rainfall. This rainfall processing unit 14 has a water drop sensor 141 and a rainfall calculation unit 142. The water drop sensor 141 detects the amount of water drops within a predetermined area per time. The rainfall calculation unit 142 calculates the amount of rainfall based on the amount of water drops measured by the water drop sensor 141. The visibility also varies depending on the amount of rainfall. Therefore, the control processing device 10 according to this embodiment is capable of correcting the visibility value according to the amount of rainfall.

[0055] That is, the first visibility calculation unit 113 corrects the first visibility value based on the rainfall calculated by the rainfall calculation unit 142. The control processing device 10 obtains first correction data indicating the relationship between the rainfall and the first visibility value by a preliminary experiment in advance and stores the data in the storage unit 121. This allows the first visibility calculation unit 113 to correct the first visibility value based on the rainfall calculated by the rainfall calculation unit 142 and the first correction data. Similarly, the second visibility calculation unit 133 corrects the second visibility value based on the rainfall calculated by the rainfall calculation unit 142. The control processing device 10 obtains second correction data indicating the relationship between the rainfall and the second visibility value by a preliminary experiment in advance and stores the data in the storage unit 121. This allows the second visibility calculation unit 133 to correct the second visibility value based on the rainfall calculated by the rainfall calculation unit 142 and the second correction data. The visibility determining unit 122 generates a final visibility value according to the corrected first visibility value and the corrected second visibility value.

[0056] Fig. 11 is a flowchart showing an example of processing by the control processing device 10 according to the fourth embodiment. As shown in Fig. 11, the water droplet sensor 141 detects the amount of water droplets (step S31). Next, the rainfall calculation unit 142 calculates the amount of water droplets within a predetermined time (step S32). Then, the rainfall calculation unit 142 determines whether the amount of water droplets within the predetermined time exceeds a threshold value (step S33). If the amount of water droplets within the predetermined time is less than the threshold value, the rainfall calculation unit 142 determines that it is not raining (NO in step S33) and repeats the processing from step S31.

[0057] On the other hand, if the amount of water droplets within the predetermined time is equal to or greater than the threshold (YES in step S33), the rainfall calculation unit 142 determines that it is raining (step S34). Next, the rainfall calculation unit 142 calculates the amount of rainfall based on the amount of water droplets (step S35).

[0058] The first visibility calculation unit 113 corrects the first visibility value based on the amount of rainfall calculated by the rainfall calculation unit 142. Similarly, the second visibility calculation unit 133 corrects the second visibility value based on the amount of rainfall calculated by the rainfall calculation unit 142. The visibility determination unit 122 generates a final visibility value according to the corrected first visibility value and the second visibility value (step S36).

[0059] As described above, the first visibility calculation unit 113 and the second visibility calculation unit 133 of the control processing device 10 according to this embodiment execute correction according to the amount of rainfall calculated by the rainfall processing unit 14. As a result, the first visibility calculation unit 113 and the second visibility calculation unit 133 can execute correction according to the amount of rainfall, and therefore it becomes possible to generate a visibility value in which the influence of the amount of rainfall is suppressed.

[0060] Fifth embodiment The control processing device 10 according to the fifth embodiment differs from the control processing device 10 according to the fifth embodiment in that it further includes a wind speed processing unit 15. The differences from the control processing device 10 according to the fourth embodiment will be described below.

[0061] FIG. 12 is a block diagram showing an example of the configuration of a control processing device 10 according to the fifth embodiment. As shown in FIG. 12, the control processing device 10 according to the fifth embodiment further includes a wind speed processing unit 15. The wind speed processing unit 15 generates a wind speed. This wind speed processing unit 15 has an air flow sensor 151 and a wind speed calculation unit 152. The air flow sensor 151 detects the air flow per unit time. The wind speed calculation unit 152 calculates the wind speed based on the air flow per unit time of the air flow sensor 151. The visibility also varies depending on the wind speed. Therefore, the control processing device 10 according to this embodiment is capable of correcting the visibility value according to the wind speed.

[0062] That is, the first visibility calculation unit 113 corrects the first visibility value based on the wind speed calculated by the wind speed calculation unit 152. The control processing device 10 acquires third correction data indicating the relationship between the wind speed and the first visibility value by a preliminary experiment in advance, and stores the data in the storage unit 121. This allows the first visibility calculation unit 113 to correct the first visibility value based on the wind speed calculated by the wind speed calculation unit 152 and the third correction data. Similarly, the second visibility calculation unit 133 corrects the second visibility value based on the wind speed calculated by the wind speed calculation unit 152. The control processing device 10 acquires fourth correction data indicating the relationship between the wind speed and the second visibility value by a preliminary experiment in advance, and stores the data in the storage unit 121. This allows the second visibility calculation unit 133 to correct the second visibility value based on the wind speed calculated by the rainfall calculation unit 142 and the fourth correction data. The visibility determining unit 122 generates a final visibility value according to the corrected first visibility value and the corrected second visibility value.

[0063] Fig. 13 is a flowchart showing an example of processing by the control processing device 10 according to the fifth embodiment. As shown in Fig. 11, the wind speed calculation unit 152 calculates a wind speed based on the wind volume per unit time measured by the air volume sensor 151 (step S51). The first visibility calculation unit 113 corrects the first visibility value based on the wind speed calculated by the wind speed calculation unit 152. Similarly, the second visibility calculation unit 133 corrects the second visibility value based on the wind speed calculated by the wind speed calculation unit 152. The visibility determination unit 122 generates a final visibility value according to the corrected first visibility value and second visibility value (step S52).

[0064] As described above, the first visibility calculation unit 113 and the second visibility calculation unit 133 of the control processing device 10 according to this embodiment execute correction according to the wind speed calculated by the wind speed calculation unit 152. As a result, the first visibility calculation unit 113 and the second visibility calculation unit 133 can execute correction according to the wind speed, and therefore it becomes possible to generate a visibility value in which the influence of the wind speed is suppressed.

[0065] Sixth embodiment The control processing device 10 according to the sixth embodiment differs from the control processing device 10 according to the fifth embodiment in that it further includes a speed processing unit 16. The differences from the control processing device 10 according to the fifth embodiment will be described below.

[0066] Fig. 14 is a block diagram showing an example of the configuration of the control processing device 10 according to the sixth embodiment. As shown in Fig. 14, the control processing device 10 according to the sixth embodiment further includes a speed processing unit 16. The speed processing unit 16 can correct the wind speed calculated by the wind speed calculation unit 152 and the rainfall calculated by the rainfall processing unit 14.

[0067] The speed processing unit 16 has an acceleration sensor 161 and a speed calculation unit 162. The acceleration sensor 161 detects the acceleration of the railcar 5. The wind speed calculation unit 152 integrates the output value of the acceleration sensor 161 over time to calculate the speed.

[0068] The amount of rainfall calculated by the rainfall processing unit 14 and the wind speed calculated by the wind speed calculation unit 152 also vary depending on the speed of the railway vehicle 5. Therefore, the control processing device 10 according to this embodiment is capable of correcting the amount of rainfall calculated by the rainfall processing unit 14 and the wind speed calculated by the wind speed calculation unit 152 according to the speed of the railway vehicle 5.

[0069] That is, the amount of rainfall calculated by the rainfall processing unit 14 is corrected according to the speed of the railway vehicle 5. The control processing device 10 acquires fifth correction data indicating the relationship between the speed of the railway vehicle 5 and the amount of rainfall in advance by a preliminary experiment, and stores the data in the memory unit 121. This enables the rainfall processing unit 14 to correct the amount of rainfall based on the speed calculated by the speed processing unit 16 and the fifth correction data. The first visibility calculation unit 113 and the second visibility calculation unit 133 correct the first visibility value and the second visibility value based on this corrected amount of rainfall.

[0070] Similarly, the wind speed calculated by the wind speed calculation unit 152 is corrected in accordance with the speed of the railway vehicle 5. The wind speed calculation unit 152 is capable of correcting the wind speed based on the speed calculated by the speed processing unit 16. The first visibility calculation unit 113 and the second visibility calculation unit 133 correct the first visibility value and the second visibility value based on this corrected wind speed. The visibility determination unit 122 generates a final visibility value in accordance with the corrected first visibility value and second visibility value.

[0071] FIG. 15 is a flowchart showing an example of processing by the control processing device 10 according to the sixth embodiment. As shown in FIG. 15, first, the acceleration sensor 161 measures acceleration (step S61). The speed processing unit 16 integrates the output value of the acceleration sensor 161 over time to calculate a speed (step S62). Next, the rainfall processing unit 14 generates a rainfall amount corrected according to the speed of the railcar 5. The first visibility calculation unit 113 and the second visibility calculation unit 133 further correct the first visibility value and the second visibility value based on the corrected rainfall. Similarly, the wind speed calculation unit 152 generates a wind speed corrected according to the speed of the railcar 5. The first visibility calculation unit 113 and the second visibility calculation unit 133 further correct the first visibility value and the second visibility value based on the corrected wind speed (step S63).

[0072] As described above, the first visibility calculation unit 113 and the second visibility calculation unit 133 of the control processing device 10 according to this embodiment perform correction according to the amount of rainfall corrected according to the speed of the railway vehicle 5. Similarly, the first visibility calculation unit 113 and the second visibility calculation unit 133 perform correction according to the wind speed corrected according to the speed of the railway vehicle 5. As a result, the first visibility calculation unit 113 and the second visibility calculation unit 133 can perform correction according to the amount of rainfall and the wind speed corrected according to the speed of the railway vehicle 5, so it is possible to generate a visibility value in which the effects of the speed of the railway vehicle 5, the wind speed, and the amount of rainfall are suppressed.

[0073] Although several embodiments of the present invention have been described above, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0074] 1: control processing system, 5: railway vehicle, 10: control processing device, 11: first visibility processing unit, 12: judgment processing unit, 13: second visibility processing unit, 14: rainfall processing unit, 15: wind speed processing unit, 16: speed processing unit, 30: obstacle detection device, 111: camera, 112: track detection unit, 113: first visibility calculation unit, 123: control unit, 131: illumination unit, 132: receiving unit, 140: image processing unit, R100: track.

Claims

1. an image acquisition unit that acquires an image of a train traveling direction; a track detection unit that detects a track in the captured image in a direction in which the railcar travels according to a predetermined criterion; A first visibility calculation unit that calculates a first visibility value related to visibility based on the detected line length; A control processing device comprising:

2. The control processing device according to claim 1 , wherein the first visibility calculation unit increases the first visibility value as the length of the detected line increases.

3. The control processing device according to claim 1 , wherein the first visibility calculation unit calculates the first visibility value in accordance with a difference between the detected length of the line and a first reference value.

4. The control processing device according to claim 1 , wherein the first visibility calculation unit calculates the first visibility value according to a difference between the detected length of the railroad track and a second reference value that varies according to a position of the railroad vehicle.

5. An irradiation unit that irradiates either millimeter waves or laser light; a receiving unit that receives a reflected wave of either the millimeter wave or the laser light; The control processing device according to claim 1 , further comprising: a second visibility calculation unit that calculates a second visibility value related to visibility in accordance with a signal strength based on the reflected wave received by the receiving unit within a predetermined time period.

6. The first visibility value and the second visibility value are each a visibility value, The control processing device according to claim 5 , further comprising a visibility determining unit that generates a visibility value based on at least one of the first visibility value and the second visibility value.

7. The control processing device according to claim 6 , wherein the visibility determining unit determines whether to select at least one of the first visibility value and the second visibility value in accordance with a detection result of the railroad detection unit.

8. The control processing device according to claim 7 , wherein the visibility determining unit determines whether to select one of the first visibility value and the second visibility value, depending on at least one of an external illuminance and a time of day.

9. The control processing device according to claim 7 , further comprising a control unit that changes a control process for the railway vehicle in accordance with the visibility value.

10. The control processing device according to claim 9 , wherein the control unit changes at least one of a braking distance and a speed of the railway vehicle in accordance with the visibility value.

11. The control processing device according to claim 7 , further comprising an image processing unit that changes image processing to be executed on the captured image in accordance with the visibility value.

12. The control processing device according to claim 11, wherein the image processing is a defogging process, and the intensity of the defogging process is increased as the visibility value becomes shorter.

13. A rainfall processing unit that generates a rainfall amount is further provided, The control processing device according to claim 6 , wherein the first visibility calculation unit and the second visibility calculation unit correct the first visibility value and the second visibility value, respectively, in accordance with the amount of rainfall.

14. Further comprising a wind speed processing unit that generates a wind speed, The control processing device according to claim 6 , wherein the first visibility calculation unit and the second visibility calculation unit respectively correct the first visibility value and the second visibility value in accordance with the wind speed.

15. A speed processing unit that generates a speed of the railway vehicle, The rainfall processing unit corrects the rainfall amount in accordance with a speed of the railcar; The control processing device according to claim 13 , wherein the first visibility calculation unit and the second visibility calculation unit generate the first visibility value and the second visibility value, respectively, in accordance with the corrected rainfall amount.

16. A speed processing unit that generates a speed of the railway vehicle, The wind speed processing unit corrects the wind speed in accordance with a speed of the railway vehicle, The control processing device according to claim 14 , wherein the first visibility calculation unit and the second visibility calculation unit generate the first visibility value and the second visibility value, respectively, in accordance with the corrected wind speed.

17. an image acquisition step of acquiring an image of a direction in which the railway vehicle is traveling; a track detection step of detecting a track in the captured image in a direction in which the railcar travels according to a predetermined criterion; A first visibility calculation step of calculating a first visibility value related to visibility based on the detected line length; A control processing method comprising:

18. A control processing unit; An obstacle detection device that detects an obstacle based on a railroad track, The control processing device includes: an image acquisition unit that acquires an image of a train traveling direction; a track detection unit that detects the track in the captured image in a direction in which the railcar travels according to a predetermined criterion; A first visibility calculation unit that calculates a first visibility value related to visibility based on the detected line length; A control processing system having:

19. 19. The control processing system according to claim 18, wherein the obstacle detection device changes the alarm signal depending on whether the position of the detected obstacle is closer to the railway vehicle than the first visibility value.

20. A traveling position information collection device for detecting a position of the railroad vehicle is further provided. The control processing system according to claim 19 , wherein the first visibility calculation unit changes a method of calculating the first visibility value depending on a position of the railway vehicle.

Citation Information

Patent Citations

  • Night vision device for vehicle

    JP2004172828A

  • Driving assist control system of vehicle

    JP2015011615A

  • Travel control device of vehicle

    JP2016002893A

  • Special signal light emitting machine inspection equipment and road-rail vehicle including special signal light emitting machine inspection equipment

    JP2016078528A

  • Travel control unit of vehicle

    JP2016088180A