Periphery monitoring device, method and program

Abstract

To release a periphery monitoring device from a limit of a loading amount of a towed vehicle or restriction of an attachment position of a camera more than in a conventional device.SOLUTION: A periphery monitoring device for predicting contact between a plurality of towed vehicles that are towed to make a column by a tractor vehicle and an object existing in a periphery comprises: imaging means in which a pixel number per a unit field angle between a first field angle including a center of an optical axis and a second field angle of a more peripheral side than the first field angle is different and a pixel number per a unit field angle in the second field angle is more than the pixel number per the unit field angle in the first field angle; and contact prediction means that predicts contact between the towed vehicle and the object from a result in which the towed vehicle and the object are simultaneously imaged by the imaging means.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a surroundings monitoring device, method, and program. [Background technology]

[0002] For example, when transporting cargo within a building such as a logistics center, a system is known in which cargo is loaded onto a number of towed vehicles towed in a line by a towing vehicle and transported to a specified location. In such a system, the driving operation of the leading towing vehicle causes discrepancies in the operation of each towed vehicle, resulting in an inner wheel difference, which may cause an entrapment accident in which the towed vehicle comes into contact with an obstacle around the towing vehicle. Patent document 1 proposes a system that monitors the towed vehicle by attaching a camera to the front of the towing vehicle in a position where it can see parts of all of the towed vehicles in the line, estimating the movement of the towed vehicle, and preventing contact with nearby obstacles. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2023-048406 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the technology described in Patent Document 1, the load of the towed vehicle may cause some of the towed vehicle to be in a blind spot, limiting the load capacity. In addition, there are restrictions on the location where the camera can be installed.

[0005] An object of the present invention is to provide a tow vehicle that is free from restrictions on the load capacity of the towed vehicle and restrictions on the position where the camera can be attached, as compared to the conventional cases. [Means for solving the problem]

[0006] A peripheral monitoring device according to an embodiment of the present invention is a peripheral monitoring device for predicting contact between a plurality of towed vehicles towed in a row by a towing vehicle and an object existing in the periphery, having a first angle of view including the center of the optical axis and a second angle of view on the peripheral side of the first angle of view, wherein the number of pixels per unit angle of view is different between the two, and the number of pixels per unit angle of view in the second angle of view is larger than the number of pixels per unit angle of view in the first angle of view; and contact prediction means for predicting contact between the towed vehicle and the object from the result of simultaneously imaging the towed vehicle and the object by the imaging means.

Effect of the Invention

[0007] According to the present invention, it is possible to release from the restrictions on the load capacity of the towed vehicle and the constraints on the position where the camera is mounted compared to the prior art.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Mode for Carrying Out the Invention

[0009] Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings. Note that the following embodiments do not limit the invention according to the claims, and not all combinations of the features described in the embodiments are essential for the solution means of the invention. In each figure, the same components may be denoted by the same reference numerals and the description thereof may be omitted.

[0010] [First Embodiment] Hereinafter, a first embodiment of the present invention will be described. FIG. 1 is a diagram schematically showing a peripheral monitoring system according to the first embodiment of the present invention. The peripheral monitoring system 150 is a system that avoids contact between a plurality of towed vehicles 111, 112, 113, and 114 towed in a row by a towing vehicle 110 driven by an operator 100 and obstacles in the vicinity. The peripheral monitoring system 150 images the rear towed vehicles 111, 112, 113, and 114, their respective loads 103, and the vicinity thereof by means of a monitoring camera 101.

[0011] The peripheral monitoring system 150 includes a monitoring camera 101. The monitoring camera 101 is disposed on the towing vehicle 110. The peripheral monitoring system 150 is arranged to face the direction of the towed vehicles 111, 112, 113, and 114, that is, the rear, and images the rear towed vehicles 111, 112, 113, and 114, their respective loads 103, and the vicinity thereof.

[0012] FIG. 2 is a block diagram showing the configuration of the peripheral monitoring system according to the first embodiment of the present invention. The peripheral monitoring system 150 includes an imaging unit 200, an information processing device 250, a vehicle driving unit 207, and a display unit 208. The information processing device 250 includes a system control unit 201, an image processing unit 202, a cutout area setting unit 203, a danger area setting unit 204, an obstacle collision determination unit 205, and a storage unit 206. The information processing device 250 is an example of a peripheral monitoring device. The information processing device 250 is, for example, a computer. The peripheral monitoring device may include an imaging unit 200, a vehicle driving unit 207, and a display unit 208.

[0013] The imaging unit 200 includes the surveillance camera 101 in FIG. 1. The image data captured by the imaging unit 200 is transmitted to the system control unit 201.

[0014] In this embodiment, the surveillance camera 101 is attached to the leading towing vehicle 110. However, in the present invention, it is not necessarily attached to the front. It may be attached to the rear of the towed vehicles 111, 112, or 113 other than the last towed vehicle 114. That is, the surveillance camera 101 may be installed behind a towing vehicle or a towed vehicle in front of the last towed vehicle among a plurality of towed vehicles.

[0015] FIGS. 3(A) and 3(B) are diagrams showing an optical explanation of the peripheral surveillance system according to the first embodiment of the present invention. Hereinafter, with reference to FIGS. 3(A) and 3(B), the shooting range of the surveillance camera 101 will be described. FIG. 3(A) is a diagram showing the whole as seen from above. FIG. 3(B) is a diagram showing how it looks from the surveillance camera 101.

[0016] As shown in FIG. 3(A), the towing vehicle 110 is towing the towed vehicles 111, 112, 113, and 114, and the surveillance camera 101 attached to the rear of the towing vehicle 110 monitors the rear of the towing vehicle 110.

[0017] As shown in FIG. 3(B), the optical system of the surveillance camera 101 has a first angle of view which is an angle of view capable of shooting an image of a first field of view including the first region 102a. Also, as shown in FIG. 3(B), the optical system of the surveillance camera 101 has a second angle of view which is an angle of view capable of shooting an image of a second field of view including the second region 102b. The optical system of the surveillance camera 101 is an optical system with different imaging magnifications for the first angle of view and the second angle of view. The optical system of the surveillance camera 101 includes, for example, an inverse varifocal lens. The surveillance camera 101 is an example of an inverse varifocal camera. The first angle of view includes the center of the optical axis. The second angle of view is an angle of view on the peripheral side rather than the first angle of view.

[0018] The imaging surface (light-receiving surface) of the surveillance camera 101 includes a first location that images an object included in the first region 102a and a second location that images an object included in the second region 102b. At this time, the number of pixels per unit angular field of view at the second location of the imaging surface is larger than the number of pixels per unit angular field of view at the first location. In other words, the resolution of the image captured in the second region 102b of the surveillance camera 101 is higher than the resolution of the image captured in the first region 102a.

[0019] The surveillance camera 101 is installed at the first angular field of view of the surveillance camera 101 so that the towed vehicle 111 located immediately behind the surveillance camera 101 can fit within it.

[0020] Figures 4(A) and 4(B) are diagrams showing the optical characteristics of the optical system of the surveillance camera 101 according to the first embodiment of the present invention. Hereinafter, with reference to Figures 4(A) and 4(B), the optical characteristics of the above-described optical system will be explained. Figure 4(A) is a diagram showing the image height y at each half angular field of view on the imaging surface (light-receiving surface) of the surveillance camera 101 in the form of contour lines. Figure 4(B) is a diagram showing the relationship (projection characteristics of the optical system) between the half angular field θ and the image height y in the first quadrant of Figure 4(A).

[0021] As shown in Figure 4(B), the optical system of the surveillance camera 101 is configured such that its projection characteristics y(θ) are different for an angular field less than a predetermined half angular field θa and an angular field greater than or equal to the half angular field θa. Therefore, when the increase amount of the image height y with respect to the half angular field θ per unit is defined as the resolution, the optical system is configured such that the resolution varies depending on the angular field (region on the light-receiving surface of the imaging device). This local resolution can be represented by the differential value dy(θ) / dθ of the projection characteristics y(θ) at the half angular field θ. For example, it can be said that the higher the slope of the projection characteristics y(θ) in Figure 4(B), the higher the resolution. Also, in Figure 4(A), it shows that the higher the interval between the contour lines of the image height y at each half angular field, the higher the resolution.

[0022] The optical system of this embodiment has a projection characteristic in which the increase rate of the image height y (the slope of the projection characteristic y(θ) in FIG. 4(B)) is small in the central region near the optical axis, and the increase rate of the image height y increases as the angle of view increases in the peripheral region outside the central region.

[0023] In FIG. 4(A), a first region 102a including the center corresponds to an angle of view less than the half angle of view θa, and a second region 102b outside the first region corresponds to an angle of view greater than or equal to the half angle of view θa. As described above, the first region 102a is a relatively low-resolution region. The second region 102b is a relatively high-resolution region. That is, the first region 102a is a region with lower resolution than the second region 102b.

[0024] Note that the characteristics shown in FIGS. 4(A) and 4(B) are examples, and the present invention is not limited thereto. For example, the low-resolution region and the high-resolution region of the optical system do not have to be configured in concentric circles, and each region may have a distorted shape. Also, the center of gravity of the low-resolution region and the center of gravity of the high-resolution region do not have to coincide. Further, the center of gravity of the low-resolution region and the center of gravity of the high-resolution region may be offset from the center of the light-receiving surface of the imaging device. In the optical system of this embodiment, it is sufficient that the low-resolution region is formed near the optical axis and the high-resolution region is formed on the peripheral side near the optical axis.

[0025] When the optical system has a focal length of f, a half angle of view of θ, an image height on the image plane of y, a projection characteristic representing the relationship between the image height y and the half angle of view θ of y(θ), and a maximum half angle of view of the optical system of θmax, it is configured to satisfy Equation A shown in Equation 1. That is, the optical system 201 is configured such that the projection characteristic y(θ) is different from 2ftan(θ / 2) (stereoscopic projection method).

Equation

[0026] In an optical system having such optical characteristics, by adjusting the projection characteristic y(θ), the magnification in the radial direction with respect to the optical axis can be adjusted. As a result, the aspect ratio in the radial direction and the circumferential direction with respect to the optical axis can be controlled. Therefore, unlike a conventional fish-eye lens or the like, a high-resolution image with less distortion in the peripheral region can be obtained while the angle of view is wide.

[0027] Further, by satisfying the formula A shown in Equation 1, the resolution in the second region 102b can be made higher than that of an optical system of a stereoscopic projection method. If the upper limit of the formula A shown in Equation 1 is exceeded, the resolution in the second region 102b becomes low, and the difference from the resolution in the first region 102a becomes small, which is not preferable. Also, if it is below the lower limit of the formula A shown in Equation 1, it becomes difficult to correct various aberrations such as field curvature favorably, which is not preferable.

[0028] Note that the formula A shown in Equation 1 described above is an example, and the optical system in the present embodiment is not limited thereto.

[0029] According to the present embodiment, by configuring the optical system as described above, high resolution can be obtained in the high-resolution region, while in the low-resolution region, the increase amount of the image height y with respect to the half angle of view θ per unit is made small, and it becomes possible to image a wider angle of view. Therefore, while having a wide angle of view equivalent to that of a fish-eye lens as an imaging range, a high resolution can be obtained in the high-resolution region.

[0030] Also, in the present embodiment, in the high-resolution region, it is approximated as a projection characteristic of a stereoscopic projection method, which is a projection characteristic of a general imaging optical system (y = 2×f×tan(θ / 2)). Therefore, in the high-resolution region, the optical distortion is small, and it becomes possible to generate a detailed image.

[0031] The system control unit 201 shown in FIG. 2 controls the entire peripheral monitoring system 150. Specifically, the system control unit 201 transmits image data to the image processing unit 202. Further, the system control unit 201 calculates information necessary for obstacle avoidance from the data obtained by the obstacle collision determination unit 205. Further, the system control unit 201 controls the drive command of the towing vehicle 110 to the vehicle drive unit 207. Further, the system control unit 201 exchanges various information with the storage unit 206.

[0032] The image processing unit 202 performs object recognition and correction in the image data transmitted from the system control unit 201. As an example of object recognition, object data corresponding to the object is stored in the storage unit 207 in advance, and recognition is performed by comparing feature points in the image data. The image processing unit 202 performs distortion correction and brightness correction on the high-angle-of-view image data captured by the imaging unit 200 if necessary.

[0033] Further, the cutout area setting unit 203 cuts out a part of the image data for the towed vehicles 111, 112, 113, and 114 and the objects recognized as obstacles by the image processing unit 202 and transmits it to the danger area setting unit 204.

[0034] The danger area setting unit 204 estimates the trajectories of the towed vehicles 111, 112, 113, and 114 from the towed vehicle information in the received image data, and sets a collision danger area based on the trajectory estimation information. Methods of motion estimation include a method of calculating the motion vector of an object by imaging a plurality of frames and a method of estimating from the direction of the wheels provided on the towed vehicles 111, 112, 113, and 114 of the object.

[0035] The obstacle collision determination unit 205 determines whether there is an obstacle recognized by the image processing unit 202 within the collision danger area set by the danger area setting unit 205, and performs a collision determination between the obstacle and the towed vehicle collision danger area.

[0036] The vehicle drive unit 207 drives the towing vehicle 110. Although the vehicle drive unit 207 is driven by the driver's own control, when the obstacle determination unit 205 determines that there is a risk of collision, the system control unit 201 calculates vehicle drive information and controls the brakes and steering of the towing vehicle 110. Also, when the obstacle determination unit 205 determines that there is a risk of collision, the system control unit 201 may use the display unit 208 to notify the operator 100 of the result of the collision determination between the obstacle and the towed vehicle and prompt avoidance.

[0037] The display unit 208 may be something that visually displays on a liquid crystal display, lamp, etc., or something that audibly notifies with a buzzer, etc.

[0038] Next, the obstacle avoidance of the towing vehicle according to the present embodiment will be described with reference to FIG. 5. FIG. 5 is a diagram showing a flowchart of the peripheral monitoring system according to the first embodiment of the present invention. FIG. 5 shows the process related to the obstacle avoidance of the towing vehicle.

[0039] The information processing device 250 has a CPU, RAM, ROM, etc. (not shown). The CPU is an abbreviation for Central Processing Unit. The RAM is an abbreviation for Random Access Memory. The ROM is an abbreviation for Read Only Memory. The storage unit 206 shown in FIG. 2 includes RAM, ROM, etc. The storage unit 206 stores programs executed by the CPU, data related to the execution of the programs, etc. The system control unit 201, image processing unit 202, cutout area setting unit 203, danger area setting unit 204, and obstacle collision determination unit 205 shown in FIG. 2 are realized by the CPU executing the programs stored in the storage unit 206. The CPU calls a program corresponding to the processing content from the ROM and expands it into the RAM to execute the processing.

[0040] In step S101, as shown in FIG. 3(A), the system control unit 201 activates the monitoring camera 101 of the imaging unit 200 attached to the rear of the leading towing vehicle 110. The imaging unit 200 starts imaging by the monitoring camera 101. The system control unit 201 acquires the image data captured by the imaging unit 200.

[0041] In step S102, the system control unit 201 determines the presence or absence of the towed vehicle. In this example, as shown in FIG. 3(B), the towed vehicle 111 is imaged by the monitoring camera 101. The determination in step S102 may be made, for example, based on whether a towed vehicle exists in the image data acquired from the imaging unit 200. Whether a towed vehicle exists in the image data may be determined by the image processing unit 201 performing image processing on the image data and performing object recognition. The determination in step S102 may be made by the operator inputting and setting in advance the presence or absence of the towed vehicle and reading it out for determination. If the system control unit 201 determines that there is no towed vehicle, the process ends. If the system control unit 201 determines that there is a towed vehicle, the process of step S103 is executed.

[0042] In step S103, the system control unit 201 sets the area that can be a blind spot due to the towed vehicle 111 in the image data as the low-resolution area 102a, and sets the surrounding area to be monitored as the high-resolution area 102b. The discrimination between the low-resolution area 102a and the high-resolution area 102b is determined in advance according to the characteristics of the optical system of the monitoring camera 101, and the image processing unit 201 may discriminate the determined area from the image data.

[0043] FIGS. 6(A), 6(B), and 6(C) are diagrams showing the cutting out of an obstacle in the peripheral monitoring system according to the first embodiment of the present invention. FIG. 6(A) is a diagram showing the whole as viewed from above. FIG. 6(B) is a diagram showing the image captured by the monitoring camera 101 in the state of FIG. 6(A). FIG. 6(C) is a diagram showing the image obtained by performing distortion correction on the cut-out area 302 of FIG. 6(B). The monitoring camera 101 is installed so that the rearmost towed vehicle 114 fits within the second angle of view of the monitoring camera 101.

[0044] In this example, while the towing vehicle 110 is towing the towed vehicles 111, 112, 113, and 114, it is traveling near the obstacle 301. The obstacle 301 is an object that wants to avoid a collision between the towing vehicle 110 and the towed vehicles 111, 112, 113, and 114. When the towing vehicle 110 is traveling, as shown in FIG. 6(B), the monitoring camera 101 images the obstacle 301 and the towed vehicle 114 within the high-resolution region 102b. In this case, there is a risk that the obstacle 301 and the towed vehicle 114 will collide. In addition, when there is a deviation in the positional relationship between the towing vehicle and the towed vehicles, the angle of view of the monitoring camera 101, which is an anamorphic lens camera, may be adjusted to image both the obstacle and the towed vehicle.

[0045] In step S104, the system control unit 201 determines whether both any obstacle and a towed vehicle are imaged within the high-resolution region 102b. When the system control unit 201 determines that both the obstacle and the towed vehicle are not imaged, the process of step S103 is executed. When the system control unit 201 determines that both the obstacle and the towed vehicle are imaged, the process of step S105 is executed.

[0046] The image processing unit 201 performs object recognition on the image data. This object recognition may use any known method. For example, in the object recognition within the high-resolution region 102b, the image processing unit 201 recognizes the towed vehicle based on the towed vehicle data stored in the storage unit 206 in advance. Also, in the recognition of the obstacle, the image processing unit 201 may recognize as an obstacle something other than the towed vehicle recognized as described above.

[0047] In step S105, the system control unit 201 cuts out the cut-out area 302 set by the cut-out area setting unit 203. The cut-out area setting unit 203, according to the instruction of the system control unit 201, as shown in FIG. 6(B), sets, as the cut-out area 302, an area in which both the obstacle 301 and the towed vehicle 114 are imaged in order to improve the detection accuracy of the collision. In FIG. 6(B), the cut-out area 302 is shown as a rectangle, but the shape of the cut-out area 302 is not limited to this. The process of step S105 is an example of image cutting means for cutting out a part of an image including the towed vehicle and an object imaged by the monitoring camera 101 to generate a cut-out image. The cut-out area 302 is an example of a cut-out image.

[0048] The image processing unit 201 performs distortion correction on the cut-out area 302, which is the area cut out in step S105, according to the instruction of the system control unit 201. FIG. 6(C) is an image after distortion correction is performed on the cut-out area 302. This distortion correction may use any known method. The process of this distortion correction is an example of image correction means for correcting a cut-out image to generate a corrected image.

[0049] In step S106, the system control unit 201 estimates the moving direction of the towed vehicle 114 from the image of the cut-out area 302 after distortion correction, and sets the collision danger area. For example, the danger area setting unit 204 receives an instruction from the system control unit 201 and sets the collision danger area. The method for estimating the moving direction of the towed vehicle 114 includes a method of calculating a motion vector by imaging a plurality of frames and a method of estimating from the direction of the wheels provided on the towed vehicle 114. That is, the danger area setting unit 204 estimates the moving direction of the towed vehicle based on, for example, the direction of the wheels of the towed vehicle or the motion vector of the towed vehicle calculated from a plurality of frames of the image. Any known method may be used for the method of estimating the moving direction of the towed vehicle 114. The collision danger area is an area where the towed vehicle 114 may pass in the future, obtained from the estimated moving direction of the towed vehicle 114. The process of step S106 is an example of a danger area setting means for setting a collision danger area from the towed vehicle in the image captured by the monitoring camera 101. Note that the process of step S106 may be executed on an image that has not been subjected to distortion correction processing, or may be executed on an image that has been subjected to distortion correction processing. When the process of step S106 is executed on an image that has been subjected to distortion correction processing, the process of step S106 is an example of a second danger area setting means for setting a second collision danger area.

[0050] FIG. 7 is a diagram showing a collision risk area in the peripheral monitoring system according to the first embodiment of the present invention. Here, the side closer to the monitoring camera 101 is referred to as the front side, and the side farther from the monitoring camera 101 is referred to as the rear side. In the present embodiment, the collision risk area 303 is set as a triangular prism having a triangle with the rear end of the towed vehicle 114 as the apex and spreading toward the front side as the base. That is, in the present embodiment, the collision risk area 303 is a triangular prism area represented by a triangular prism having an upper base 304 shown by a thick broken line triangle and a lower base 305 shown by a thin broken line triangle. In the present embodiment, the collision risk area 303 is three-dimensionally represented in consideration of the height of the towed vehicle 114. The monitoring camera 101 is installed so that the collision risk area 303 fits within the second viewing angle of the monitoring camera 101. The monitoring camera 101 is installed so that at least a part of the obstacle 301 can fit within the second viewing angle of the monitoring camera 101.

[0051] In step S107, the system control unit 201 determines whether or not there is an obstacle in the collision risk area 303 generated for the towed vehicle 114. For example, the obstacle collision determination unit 205 receives an instruction from the system control unit 201 and makes the determination in step S107. This process is an example of a contact prediction means for predicting contact between the towed vehicle 114 and the obstacle 301 from the result of simultaneously imaging the towed vehicle 114 and the obstacle 301 by the imaging unit 200. If the system control unit 201 determines that there is no obstacle in the collision risk area 303, the process ends. If the system control unit 201 determines that there is an obstacle in the collision risk area 303, the process of step S108 is executed. In the present embodiment, as shown in FIG. 7, there is an obstacle 301 in the collision risk area 303.

[0052] In step S108, since there is a risk that the towed vehicle 114 will collide with the obstacle 301, the system control unit 201 announces to the operator 100 and controls the towing vehicle 110.

[0053] As an announcement method, the display unit 208 that can be confirmed by the operator 100 displays that there is a risk of collision. The display unit 208 is a device such as a liquid crystal screen attached to the towing vehicle 110, for example. The information processing device 250 may include the display unit 208. Also, as an announcement method, a warning sound may be emitted from a speaker attached to the towing vehicle 110 to notify the operator 100. The announcement method is not limited to the above, and anything can be used as long as it can be confirmed by the operator 100.

[0054] Also, in the control of the towing vehicle 110 when there is a risk of collision, the system control unit 201 sends a control signal to the vehicle drive unit 207. The vehicle drive unit 207 controls the drive of the towing vehicle 110 according to the received control signal. The system control unit 201, for example, sends a control signal to automatically apply the brakes to the vehicle drive unit 207. Also, the system control unit 201, for example, sends a control signal to avoid a collision by automatically controlling the steering wheel to the vehicle drive unit 207. The control is not limited to being performed automatically, and an instruction to apply the brakes or an instruction to operate the steering wheel may be given to the operator 100.

[0055] In this embodiment, the operator 100 drives the towing vehicle 110, but it is not limited to this, and the towing vehicle 110 may be configured as an autonomous vehicle.

[0056] Also, in this embodiment, an example of avoiding obstacles around the towing vehicle is described. The present invention is not limited to this, and it can also be applied when monitoring the area around the towing vehicle in order to avoid the towed vehicle from falling off due to a ditch or a cliff during driving in the wild or the like.

[0057] (Other Embodiments) The present invention can also be realized by supplying a program that realizes one or more functions of the above-described embodiments to a system or device via a network or a storage medium, and causing one or more processors in a computer of the system or device to read and execute the program. Further, it can also be realized by a circuit (for example, ASIC) that realizes one or more functions.

[0058] As described above, the preferred embodiments of the present invention have been described. However, the present invention is not limited to these embodiments, and various modifications and changes are possible within the scope of the gist thereof.

[0059] The disclosure of the present embodiment includes the following configurations. (Configuration 1) A peripheral monitoring device for predicting contact between a plurality of towed vehicles towed in a row by a towing vehicle and an object existing in the periphery, An imaging means in which the number of pixels per unit angular field is different between a first angular field including the center of the optical axis and a second angular field on the peripheral side of the first angular field, and the number of pixels per unit angular field in the second angular field is larger than the number of pixels per unit angular field in the first angular field, Contact prediction means for predicting contact between the towed vehicle and the object from the result of simultaneously imaging the towed vehicle and the object by the imaging means, A peripheral monitoring device comprising the same. (Configuration 2) The imaging device is installed such that the towed vehicle located immediately behind the imaging means is accommodated within the first angular field of the imaging means. The peripheral monitoring device according to Configuration 1, characterized in that. (Configuration 3) The imaging device is installed such that at least a part of the object is accommodated within the second angular field of the imaging means. The peripheral monitoring device according to Configuration 1 or Configuration 2, characterized in that. (Configuration 4) The imaging means is installed behind the towing vehicle or a towed vehicle in front of the last towed vehicle among the plurality of towed vehicles. The peripheral monitoring device according to any one of Configuration 1 to Configuration 3, characterized in that... (Configuration 5) It includes an image extraction means for extracting a part of an image including the towed vehicle and the object imaged by the imaging means to generate an extracted image. The contact prediction means predicts contact between the towed vehicle and the object from the extracted image. The peripheral monitoring device according to any one of Configuration 1 to Configuration 4, characterized in that... (Configuration 6) It includes an image correction means for correcting the extracted image to generate a corrected image. The contact prediction means predicts contact between the towed vehicle and the object from the corrected image. The peripheral monitoring device according to Configuration 5, characterized in that... (Configuration 7) It includes a danger area setting means for setting a collision danger area from the towed vehicle in the image imaged by the imaging means. When the object is detected within the collision danger area, the contact prediction means determines that there is a possibility of contact. The peripheral monitoring device according to any one of Configuration 1 to Configuration 6, characterized in that... (Configuration 8) It includes a second danger area setting means for setting a second danger area from the towed vehicle in the corrected image. When the object is detected within the second collision danger area, the contact prediction means determines that there is a possibility of contact. The peripheral monitoring device according to Configuration 6, characterized in that... (Configuration 9) The contact prediction means estimates the moving direction of the towed vehicle based on the direction of the wheels of the towed vehicle or the movement vector of the towed vehicle calculated from a plurality of frames of the image. The peripheral monitoring device according to any one of Configuration 1 to Configuration 8, characterized in that... (Method 1) A method for controlling a peripheral monitoring device for predicting contact between a plurality of towed vehicles towed in a row by a towing vehicle and an object existing in the surroundings, The number of pixels per unit angular field is different between a first angular field including the center of the optical axis and a second angular field on the peripheral side of the first angular field, An imaging step of imaging an image with an imaging means in which the number of pixels per unit angular field in the second angular field is larger than the number of pixels per unit angular field in the first angular field, A contact prediction step of predicting contact between the towed vehicle and the object from the result of simultaneously imaging the towed vehicle and the object in the imaging step, A method characterized by comprising the above. (Program 1) A program executed by a computer of a peripheral monitoring device for predicting contact between a plurality of towed vehicles towed in a row by a towing vehicle and an object existing in the surroundings, The computer is configured such that the number of pixels per unit angular field is different between a first angular field including the center of the optical axis and a second angular field on the peripheral side of the first angular field, From the result of simultaneously imaging the towed vehicle and the object with an imaging means in which the number of pixels per unit angular field in the second angular field is larger than the number of pixels per unit angular field in the first angular field, A program characterized by causing the computer to function as contact prediction means for predicting contact between the towed vehicle and the object.

Explanation of Signs

[0060] 100 Operator 101 Monitoring Camera 102a First Region 102b Second Region 103 Cargo 110 Towing Vehicle 111 Towed Vehicle 112 Towed Vehicle 113 Towed Vehicle 114 Towed Vehicle 200 Imaging Unit 201 System Control Means 202 Image processing unit 203 Cut-out area setting unit 204 Danger area setting unit 205 Obstacle collision determination unit 206 Memory unit 207 Vehicle drive unit 208 Display unit 301 Obstacle 302 Cut-out area 303 Collision danger area

Claims

1. A peripheral monitoring device for predicting contact between a plurality of towed vehicles towed in a row by a towing vehicle and an object existing in the periphery, comprising: Imaging means in which the number of pixels per unit angular field is different between a first angular field including the center of the optical axis and a second angular field on the peripheral side of the first angular field, and the number of pixels per unit angular field in the second angular field is larger than the number of pixels per unit angular field in the first angular field; Contact prediction means for predicting contact between the towed vehicle and the object from a result of simultaneously imaging the towed vehicle and the object by the imaging means; A peripheral monitoring device, characterized by comprising the above.

2. The imaging device is installed such that the towed vehicle located immediately behind the imaging means is accommodated within the first angular field of the imaging means. The peripheral monitoring device according to claim 1, characterized by the above.

3. The imaging device is installed such that at least a part of the object is accommodated within the second angular field of the imaging means. The peripheral monitoring device according to claim 1, characterized by the above.

4. The imaging means is installed behind the towing vehicle or a towed vehicle in front of the last towed vehicle among the plurality of towed vehicles. The peripheral monitoring device according to claim 1, characterized by the above.

5. Image cutting means for cutting out a part of an image including the towed vehicle and the object imaged by the imaging means to generate a cut-out image; The contact prediction means predicts contact between the towed vehicle and the object from the cut-out image. The peripheral monitoring device according to claim 1, characterized by the above.

6. Image correction means for correcting the cut-out image to generate a corrected image; The contact prediction means predicts contact between the towed vehicle and the object from the corrected image. The peripheral monitoring device according to claim 5, characterized in that.

7. It includes a danger area setting means for setting a collision danger area from the towed vehicle in the image captured by the imaging means. When the object is detected within the collision danger area, the contact prediction means determines that there is a possibility of contact. The peripheral monitoring device according to claim 1, characterized in that.

8. It includes a second danger area setting means for setting a second danger area from the towed vehicle in the corrected image. When the object is detected within the second collision danger area, the contact prediction means determines that there is a possibility of contact. The peripheral monitoring device according to claim 6, characterized in that.

9. The contact prediction means estimates the moving direction of the towed vehicle based on the direction of the wheels of the towed vehicle or the movement vector of the towed vehicle calculated from a plurality of frames of the image. The peripheral monitoring device according to claim 1, characterized in that.

10. A method for controlling a peripheral monitoring device for predicting contact between a plurality of towed vehicles towed in a row by a towing vehicle and an object existing in the periphery, A step of imaging an image with an imaging means in which the number of pixels per unit angular field is different between a first angular field including the center of the optical axis and a second angular field on the peripheral side of the first angular field, and the number of pixels per unit angular field in the second angular field is more than the number of pixels per unit angular field in the first angular field. A contact prediction step of predicting contact between the towed vehicle and the object from the result of simultaneously imaging the towed vehicle and the object in the imaging step. A method characterized by comprising.

11. A program executed by a computer of a peripheral monitoring device for predicting contact between a plurality of towed vehicles towed in a row by a towing vehicle and an object existing in the periphery, wherein the computer is caused to function as contact prediction means for predicting contact between the towed vehicle and the object from a result of simultaneously imaging the towed vehicle and the object by imaging means in which the number of pixels per unit angular field is different between a first angular field including the center of the optical axis and a second angular field on the peripheral side of the first angular field, and the number of pixels per unit angular field in the second angular field is larger than the number of pixels per unit angular field in the first angular field.

Images