Distance Estimation Device, Distance Estimation Method, and Computer Program for Distance Estimation

Abstract

To provide a distance estimation device capable of appropriately estimating a distance to another vehicle without excessively increasing an annotation cost of teacher data used for learning a discriminator.SOLUTION: A distance estimation device includes: a detection unit that detects another vehicle area representing another vehicle by inputting a peripheral image that represents a peripheral situation of a vehicle obtained from an imaging unit mounted on the vehicle to a discriminator, and classifies another vehicle represented in the detected other vehicle area into one of a plurality of pre-registered vehicle types; and an estimation unit that identifies a position of a virtual object corresponding to another vehicle represented in the other vehicle area and estimates a distance from the vehicle to the virtual object as a distance from the vehicle to the other vehicle.SELECTED DRAWING: Figure 8

Description

Technical Field

[0001] The present disclosure relates to a distance estimation device that estimates the distance from a vehicle to other vehicles around the vehicle.

Background Art

[0002] A driving control device that controls the running of a vehicle regardless of the driver's operation requires the relative positional relationship between the vehicle and an object such as other vehicles around the vehicle in order to set a driving route that does not collide with the object.

[0003] Patent Document 1 describes a collision detection system that detects an object that may approach and collide with the host vehicle. The collision detection system described in Patent Document 1 calculates an optical flow from an image representing the situation in front of the vehicle, groups the optical flows for other vehicles shown in the image, and sets a frame so as to surround the grouped optical flows. Then, the collision detection system described in Patent Document 1 calculates the distance to the other vehicle using the width of the frame and the width of a general vehicle in the real space.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] When another vehicle is tilted with respect to the traveling direction of the host vehicle, the object region representing the other vehicle in the image includes not only the rear surface of the other vehicle but also the side surface of the other vehicle. In this case, since the lateral width of the object region becomes wider than the lateral width of the rear surface of the other vehicle in the image, the estimation accuracy of the distance to the other vehicle decreases. In particular, as the distance from the host vehicle to the other vehicle increases, the size of the other vehicle in the image becomes smaller, and it becomes difficult to accurately identify only the rear surface of the other vehicle. On the other hand, it is also conceivable to estimate the distance to the other vehicle using the three-dimensional posture of the other vehicle detected by an identifier capable of detecting the three-dimensional posture of the other vehicle from the image. In this case, the annotation cost for creating the teacher data used for learning the identifier becomes enormous.

[0006] An object of the present disclosure is to provide a distance estimation device that can appropriately estimate the distance to another vehicle without excessively increasing the annotation cost of the teacher data used for learning an identifier.

Means for Solving the Problems

[0007] The distance estimation device according to the present invention inputs a peripheral image representing the peripheral situation of the vehicle acquired from an imaging unit mounted on the vehicle into an identifier, and thereby detects an other vehicle region including at least one of a front / rear region representing the front or rear surface of the other vehicle and a side region representing a region other than the front or rear surface of the other vehicle in the other vehicle, and classifies the other vehicle represented in the detected other vehicle region into any one of a plurality of pre-registered vehicle types; a detection unit; a virtual object having a standard vehicle length and a standard vehicle width stored in a storage unit in association with each of the plurality of vehicle types, the standard vehicle length and the standard vehicle width being associated with the vehicle type to which the other vehicle represented in the other vehicle region is classified, and the angle formed by the orientation of the virtual object and the orientation of the imaging unit being an angle indicated as the ratio of the width of the front / rear region to the width of the side region, and specifying the position of the virtual object; and an estimation unit that estimates the distance from the vehicle to the virtual object as the distance from the vehicle to the other vehicle based on the specified position of the virtual object.

[0008] In the distance estimation device according to the present disclosure, it is preferable that the estimation unit specifies the position of a virtual object for a vehicle represented by a vehicle region excluding the side surface region, the angle formed by the direction of the vehicle being the angle indicating the direction of the vehicle detected from the peripheral image, and estimates the distance from the vehicle to the virtual object based on the specified position of the virtual object.

[0009] The distance estimation method according to the present disclosure includes inputting a peripheral image representing the peripheral situation of the vehicle acquired from an imaging unit mounted on the vehicle into an identifier to detect a vehicle region including at least one of a front and rear region representing the front or rear of another vehicle and a side surface region representing a region other than the front or rear of another vehicle from the peripheral image, classifying the other vehicle represented by the detected vehicle region into any one of a plurality of pre-registered vehicle types, and specifying the position of a virtual object having a standard vehicle length and a standard vehicle width stored in a storage unit in association with each of the plurality of vehicle types, the standard vehicle length and the standard vehicle width being associated with the vehicle type into which the other vehicle represented by the vehicle region is classified, the angle formed by the direction of the virtual object and the direction of the imaging unit being the angle indicated as the ratio of the width of the front and rear region to the width of the side surface region, and estimating the distance from the vehicle to the virtual object as the distance from the vehicle to the other vehicle based on the specified position of the virtual object.

[0010] The computer program for distance estimation according to the present disclosure causes a processor mounted on a vehicle to perform the following steps: input a peripheral image representing the peripheral situation of the vehicle, acquired from an imaging unit mounted on the vehicle, into an identifier to detect, from the peripheral image, a vehicle region of another vehicle including at least one of a front-back region representing the front or the back of the other vehicle and a side region representing a region other than the front or the back of the other vehicle; classify the other vehicle represented by the detected vehicle region of the other vehicle into any one of a plurality of pre-registered vehicle types; identify a position of a virtual object having a standard vehicle length and a standard vehicle width stored in a storage unit in association with each of the plurality of vehicle types, the standard vehicle length and the standard vehicle width being associated with the vehicle type to which the other vehicle represented by the vehicle region of the other vehicle is classified, and an angle formed by the orientation of the virtual object and the orientation of the imaging unit being an angle indicated as a ratio of the width of the front-back region to the width of the side region; and estimate, based on the identified position of the virtual object, the distance from the vehicle to the virtual object as the distance from the vehicle to the other vehicle.

[0011] According to the distance estimation device of the present disclosure, it is possible to appropriately estimate the distance to another vehicle without excessively increasing the annotation cost of the teacher data used for learning of the identifier.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Embodiments for Carrying Out the Invention

[0013] Hereinafter, with reference to the drawings, a distance estimation device capable of appropriately estimating the distance to another vehicle without excessively increasing the annotation cost of teacher data used for learning an identifier will be described in detail. The distance estimation device of the present disclosure inputs a peripheral image representing the peripheral situation of the vehicle acquired from an imaging unit mounted on the vehicle into an identifier, thereby detecting an other vehicle area representing the other vehicle, and classifying the other vehicle represented by the detected other vehicle area into any one of a plurality of pre-registered vehicle types. In the distance estimation device of the present disclosure, the other vehicle area includes at least one of a front-back area representing the front or back of the other vehicle and a side area representing an area other than the front or back of the other vehicle. The distance estimation device of the present disclosure specifies the position of a virtual object corresponding to the other vehicle represented by the other vehicle area. The virtual object has a standard vehicle length and a standard vehicle width stored in the storage unit in association with each of a plurality of vehicle types, and the standard vehicle length and the standard vehicle width are stored in association with the vehicle type to which the other vehicle represented by the other vehicle area is classified. Further, in specifying the position of the virtual object, the angle formed by the orientation of the virtual object and the orientation of the imaging unit is an angle shown as the ratio of the width of the front-back area to the width of the side area. Then, the distance estimation device of the present disclosure estimates the distance from the vehicle to the virtual object as the distance from the vehicle to the other vehicle based on the specified position of the virtual object.

[0014] FIG. 1 is a schematic configuration diagram of a vehicle on which the distance estimation device is mounted.

[0015] Vehicle 1 has a camera 2 and an ECU 3 (Electronic Control Unit). The ECU 3 is an example of a distance estimation device. The camera 2 and the ECU 3 are communicably connected via an in-vehicle network conforming to a standard such as a controller area network.

[0016] Camera 2 is an example of an imaging unit that outputs a peripheral image representing the surrounding situation of the vehicle. Camera 2 includes a two-dimensional detector composed of an array of photoelectric conversion elements sensitive to visible light, such as a CCD or a C-MOS, and an imaging optical system that forms an image of the area to be photographed on the two-dimensional detector. Camera 2 is disposed, for example, at the upper front inside the vehicle cabin, facing forward, and photographs the surrounding situation of vehicle 1 through the windshield at a predetermined photographing cycle (e.g., 1 / 30 second to 1 / 10 second), and outputs a peripheral image corresponding to the surrounding situation. The image is an example of the output data of the sensor.

[0017] ECU 3 includes a communication interface, a memory, and a processor. ECU 3 estimates the distance to an object existing around vehicle 1 based on the peripheral image received from camera 2 via the communication interface.

[0018] Further, ECU 3 creates a driving route in which the distance between vehicle 1 and an object existing around it is a certain value or more, and outputs a control signal to the driving mechanism (not shown) of vehicle 1 so that vehicle 1 travels along the driving route. The driving mechanism includes, for example, an engine or a motor that supplies power to vehicle 1, a brake that reduces the driving speed of vehicle 1, and a steering mechanism that steers vehicle 1.

[0019] Figure 2 is a hardware schematic diagram of ECU 3. ECU 3 includes a communication interface 31, a memory 32, and a processor 33.

[0020] Communication interface 31 is an example of a communication unit and has a communication interface circuit for connecting ECU 3 to the in-vehicle network. Communication interface 31 supplies the received data to processor 33. Further, communication interface 31 outputs the data supplied from processor 33 to the outside.

[0021] The memory 32 is an example of a storage unit and includes a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 32 stores various data used for processing by the processor 33, such as the focal length of the imaging lens of the camera 2, and a group of parameters (number of layers, layer configuration, kernel, weight coefficients, etc.) for defining a neural network that operates as an identifier for detecting the other vehicle region and the vehicle type of the other vehicle from the surrounding image. The memory 32 also stores the standard vehicle length and the standard vehicle width in association with each of a plurality of vehicle types. The memory 32 also stores various application programs, such as a distance estimation program for executing distance estimation processing.

[0022] The processor 33 is an example of a control unit and includes one or more processors and their peripheral circuits. The processor 33 may further include other arithmetic circuits such as a logical arithmetic unit, a numerical arithmetic unit, or a graphic processing unit.

[0023] FIG. 4 is a functional block diagram of the processor 33 included in the ECU 3.

[0024] The processor 33 of the ECU 3 includes, as functional blocks, a detection unit 331 and an estimation unit 332. Each of these units included in the processor 33 is a functional module implemented by a program executed on the processor 33. A computer program for realizing the functions of each unit of the processor 33 may be provided in a form recorded on a computer-readable portable recording medium such as a semiconductor memory, a magnetic recording medium, or an optical recording medium. Alternatively, each of these units included in the processor 33 may be implemented in the ECU 3 as an independent integrated circuit, microprocessor, or firmware.

[0025] The detection unit 331 inputs a peripheral image representing the peripheral situation of the vehicle to the identifier, thereby detecting an other vehicle region representing the other vehicle, and classifying the other vehicle represented by the detected other vehicle region into any one of a plurality of vehicle types such as a passenger car, a truck, and a bus, which are predetermined.

[0026] The other vehicle area includes at least one of a front-back area representing the front or back of another vehicle and a side area representing an area other than the front or back of another vehicle.

[0027] FIG. 4 is a schematic diagram for explaining the detection of the other vehicle area.

[0028] In the peripheral image P shown in FIG. 4, there are represented a lane L1 in which the vehicle 1 travels, which is demarcated by lane demarcation lines LL1 and LL2, and a lane L2 in which another vehicle 10 travels, which is adjacent to the lane L1 and demarcated by lane demarcation lines LL2 and LL3.

[0029] The detection unit 331 inputs the peripheral image P to the discriminator to detect the other vehicle area and identify the vehicle type of the other vehicle represented in the other vehicle area. In the example of FIG. 4, the detection unit 331 detects the other vehicle area 100 in which the other vehicle 10 is represented and identifies the vehicle type "passenger car" as the vehicle type of the other vehicle 10. In the memory 32, "4.5 m" is stored as the standard vehicle length corresponding to the vehicle type "passenger car", and "1.75 m" is stored as the standard vehicle width. In addition to the vehicle type "passenger car", in the memory 32, for example, the standard vehicle length "10 m" and the standard vehicle width "2.4 m" for the vehicle type "truck", and the standard vehicle length "12 m" and the standard vehicle width "2.5 m" for the vehicle type "bus" are stored.

[0030] The discriminator can be, for example, a convolutional neural network (CNN) having a plurality of convolutional layers connected in series from the input side to the output side. By inputting, as teacher data, an image in which another vehicle is represented, the designation of the boundary between the front-back area and the side area in the other vehicle represented in the image, and the designation of the vehicle type corresponding to the other vehicle represented in the image, and performing learning, the CNN operates as a discriminator for detecting the other vehicle area and the vehicle type from the image.

[0031] Teacher data involving the specification of the boundary between the front and rear regions and the side regions in other vehicles can be created at an annotation cost approximately 1.05 times that of the annotation cost of teacher data that only specifies the other vehicle regions corresponding to the other vehicles represented in the image. That is, the annotation cost of teacher data involving the specification of the boundary between the front and rear regions and the side regions in other vehicles is much smaller than the annotation cost of teacher data that specifies the three-dimensional bounding box corresponding to the other vehicles.

[0032] The estimation unit 332 identifies the position of the virtual object corresponding to the other vehicle represented in the other vehicle region. The virtual object has a standard vehicle length and a standard vehicle width stored in the memory in association with each of a plurality of vehicle types, and is stored in association with the vehicle type to which the other vehicle represented in the other vehicle region belongs. Also, in identifying the position of the virtual object, the angle formed by the virtual object and the orientation of the vehicle is an angle indicated as the ratio of the width of the front and rear regions to the width of the side regions.

[0033] FIG. 5 is a first schematic diagram for explaining the arrangement of the virtual object corresponding to the other vehicle.

[0034] Assume that a virtual object VO1 corresponding to the other vehicle 10 is arranged in a camera coordinate system in which the position of the optical center in the imaging optical system of the camera 2 mounted on the vehicle 1 is taken as the origin, the traveling direction of the vehicle 1 is taken as the y-axis, and the x-axis orthogonal to the y-axis is set along the road surface on which the vehicle 1 travels. The width W and length L of the virtual object VO1 represented as a rectangular parallelepiped respectively correspond to the standard vehicle width and the standard vehicle length stored in the memory 32 in association with the vehicle type to which the other vehicle belongs. The estimation unit 332 identifies the coordinates of the point (point A(X A , Y A )) closest to the origin of the virtual object VO1, and the angle θ formed by the longitudinal direction of the virtual object VO1 and the y-axis.

[0035] The image of the virtual object VO1 is projected onto a plane arranged at a position away from the origin by the focal length f pix relative to the virtual object VO1 with respect to the y-axis. Points a, b, and c in the image are points A(XA , Y A ), B(X B , Y B ), C(X C , Y C ) respectively correspond to. The focal length f pix is the distance obtained by converting the focal length of the imaging optical system of camera 2 into pixel distance by dividing it by the resolution (mm / pixel).

[0036] Let the angle formed by the light incident from point A through the origin to point a and the x-axis be α, the angle formed by the light incident from point B through the origin to point b and the x-axis be β, and the angle formed by the light incident from point C through the origin to point c and the x-axis be γ. At this time, the following equations (1), (2), and (3) hold for angles α, β, and γ.

[0037]

Equation

[0038] In the xy plane shown in FIG. 5, points A, B, and C of the virtual object VO1 are the vertices of a rectangle with width W and length L. Since this rectangle is inclined by θ with respect to the y-axis, the coordinates of points A, B, and C can be expressed as follows respectively.

[0039]

Equation

[0040] Here, δ is a variable indicating whether the angle φ (hereinafter also referred to as the azimuth angle) formed by the straight line connecting the center of the virtual object VO1 and the origin and the y-axis is larger than the angle θ (hereinafter also referred to as the rotation angle) formed by the longitudinal direction of the virtual object VO1 and the y-axis.

[0041] FIG. 6 is a second schematic diagram for explaining the arrangement of the virtual object corresponding to the other vehicle.

[0042] In the virtual objects VO21 and VO22 shown in FIG. 6, the azimuth angles formed by the straight line connecting the center and the origin and the y-axis are both φ1. The rotation angle θ1 of the virtual object VO21 is smaller than the azimuth angle φ1. In this case, δ is 1. On the other hand, the rotation angle θ2 of the virtual object VO22 is larger than the azimuth angle φ1. In this case, δ is -1.

[0043] The variable δ can be expressed by the following formula (4) using the values of points b and c without using the azimuth angle φ and the rotation angle θ.

[0044]

Number

[0045] The angles α, β, and γ can be expressed as follows in formulas (5), (6), and (7) using the rotation angle θ.

[0046]

Number

[0047] By arranging formulas (5), (6), and (7) with respect to the rotation angle θ, the following formulas (8), (9), and (10) are obtained.

[0048]

Number

[0049] Formulas (8), (9), and (10) can be solved for the rotation angle θ as in formula (11), and X A and Y A can be expressed as in the following formulas (12) and (13), respectively.

[0050]

Number

[0051] Depending on the position and angle of other vehicles, for example, when the difference between the azimuth angle φ of the other vehicle and the rotation angle θ of the other vehicle is near a multiple of π / 2 (0, π / 2, π, 3π / 2, …), the three points A, B, and C may not be detected from the other vehicle area. At this time, since only one of the front, back, or side surfaces of the other vehicle is represented in the other vehicle area, the position of the virtual object cannot be specified using the above formula.

[0052] FIG. 7 is a third schematic diagram for explaining the arrangement of the virtual object corresponding to the other vehicle.

[0053] FIG. 7 shows the arrangement of the virtual object when the azimuth angle φ of the other vehicle and the rotation angle θ of the other vehicle are approximate. The azimuth angle φ is the angle formed by the center of the virtual object and the axis in the camera coordinate system. Since the position of the center of the other vehicle is not represented in the peripheral image, the midpoint p of the two end points (a, b) of the other vehicle area in the peripheral image is taken as the center of the virtual object, and the azimuth angle φ is expressed by the following formula (14).

[0054]

Number

[0055] By the approximation of φ≈θ, the width W (or length L) can be projected onto a straight line parallel to the x-axis of the camera coordinate system. And X A and Y A can be expressed as follows using a basic ranging method based on width using the similarity of triangles.

[0056]

Number

[0057] In formula (16), w represents the horizontal width of the other vehicle area in the peripheral image, that is, the distance between point a and point b.

[0058] In the detection of the other vehicle region from the surrounding image representing the situation in front of the vehicle 1, it is common for the azimuth angle φ of the other vehicle and the rotation angle θ of the other vehicle to be approximated when the other vehicle is at a position far ahead of the vehicle 1. When the other vehicle is at a position far ahead of the vehicle 1, the azimuth angle φ approaches 0, the error in the approximation of Equation (16) becomes small, and the position of the virtual object can be specified more appropriately.

[0059] The estimation unit 332 obtains the distance from the vehicle 1 to the virtual object based on the position of the specified virtual object, and estimates it as the distance from the vehicle 1 to the other vehicle.

[0060] The estimation unit 332 is for the point A(X A , Y A ) closest to the origin of the virtual object, and calculates the square root of X A 2 + Y A 2 to obtain the distance from the vehicle 1 to the virtual object.

[0061] Figure 8 is a flowchart of the position estimation process. Each time the ECU 3 receives a surrounding image from the camera 2, it executes the distance estimation process described below.

[0062] The detection unit 331 of the ECU 3 inputs the surrounding image acquired from the camera 2 to the discriminator to detect the other vehicle region representing the other vehicle (step S1). Further, the detection unit 331 classifies the other vehicle into any one of a plurality of vehicle types registered in advance by inputting the surrounding image to the discriminator (step S2). The detection unit 331 may execute the detection of the other vehicle region and the classification into the vehicle type in one processing step by inputting the surrounding image to the discriminator trained to perform the detection of the other vehicle region and the classification into the vehicle type in parallel.

[0063] Next, the estimation unit 332 of the ECU 3 specifies the position of the virtual object corresponding to the vehicle type into which the other vehicle is classified (step S3). Then, the estimation unit 332 estimates the distance from the vehicle to the virtual object as the distance from the vehicle to the other vehicle (step S4), and ends the distance estimation process.

[0064] By executing the distance estimation process in this way, the ECU 3 can perform appropriate distance estimation to other vehicles without excessively increasing the annotation cost of the teacher data used for learning of the discriminator.

[0065] Those skilled in the art should understand that various changes, substitutions, and modifications can be added to this without departing from the spirit and scope of the present invention.

Explanation of Signs

[0066] 1 Vehicle 3 ECU 331 Detection Unit 332 Estimation Unit

Claims

1. By inputting a peripheral image representing the peripheral situation of the vehicle, acquired from an imaging unit mounted on the vehicle, into an identifier, a vehicle region including at least one of a front / rear region representing the front or rear of another vehicle and a side region representing a region other than the front or rear of the other vehicle is detected from the peripheral image, and a detection unit that classifies the other vehicle represented by the detected vehicle region into any one of a plurality of pre-registered vehicle types; The position of the vertex of a virtual object having a standard vehicle length and a standard vehicle width stored in a storage unit in association with each of the plurality of vehicle types, and associated with the vehicle type to which the other vehicle represented by the vehicle region is classified, is the position corresponding to the vertex in the image projected by the virtual object onto a plane disposed at a position separated from the optical center of the optical system of the imaging unit by the focal length of the optical system, when the virtual object is disposed in a coordinate system having the traveling direction of the vehicle as one axis and a direction orthogonal to the one axis along the road surface of the road on which the vehicle travels as the other axis. The position is specified by solving an equation obtained using the width of the front / rear region and the width of the side region included in the vehicle region detected by inputting the peripheral image into the identifier, and based on the position of the vertex of the virtual object closest to the vehicle, the distance from the vehicle to the virtual object is estimated as the distance from the vehicle to the other vehicle. An estimation unit; A distance estimation device comprising the above.

2. For the other vehicle represented by the vehicle region not including the side region, the estimation unit assumes the positions of a plurality of the virtual objects, and among the positions of the plurality of the virtual objects, specifies the position of the virtual object at which the angle formed with the direction of the vehicle is the angle indicating the direction of the other vehicle detected from the peripheral image, and estimates the distance from the vehicle to the virtual object based on the specified position of the virtual object. The distance estimation device according to claim 1.

3. By inputting a peripheral image representing the peripheral situation of the vehicle, which is acquired from an imaging unit mounted on the vehicle, into an identifier, a vehicle region including at least one of a front-back region representing the front or rear of another vehicle and a side region representing a region other than the front or rear of the other vehicle is detected from the peripheral image, and the other vehicle represented by the detected vehicle region is classified into any one of a plurality of pre-registered vehicle types. The position of the vertex of a virtual object having a standard vehicle length and a standard vehicle width stored in a storage unit in association with each of the plurality of vehicle types, which is stored in association with the vehicle type into which the other vehicle represented by the vehicle region is classified, is determined by solving an equation obtained using the width of the front-back region and the width of the side region included in the vehicle region detected by inputting the peripheral image into the identifier. The position of the vertex is the position corresponding to the vertex in the image projected by the virtual object onto a plane located at a distance equal to the focal length of the optical system from the optical center of the optical system of the imaging unit when the virtual object is arranged in a coordinate system having the traveling direction of the vehicle as one axis and a direction perpendicular to the one axis along the road surface on which the vehicle travels as the other axis. Based on the position of the vertex of the virtual object closest to the vehicle, the distance from the vehicle to the virtual object is estimated as the distance from the vehicle to the other vehicle. A distance estimation method including the above.

4. By inputting a peripheral image representing the peripheral situation of the vehicle, which is acquired from an imaging unit mounted on the vehicle, into an identifier, a vehicle region including at least one of a front-back region representing the front or rear of another vehicle and a side region representing a region other than the front or rear of the other vehicle is detected from the peripheral image, and the other vehicle represented by the detected vehicle region is classified into any one of a plurality of pre-registered vehicle types. The position of the vertex of the virtual object having the standard vehicle length and the standard vehicle width stored in the storage unit in association with each of the plurality of vehicle types and associated with the vehicle type to which the other vehicle represented in the other vehicle area belongs, in a coordinate system having the traveling direction of the vehicle as one axis and a direction orthogonal to the one axis along the road surface on which the vehicle travels as the other axis, is the position corresponding to the vertex in the image projected by the virtual object onto the plane arranged at a position separated from the optical center of the optical system of the imaging unit by the focal length of the optical system. Identifying by solving an equation obtained using the width of the front and rear area and the width of the side area included in the other vehicle area detected by inputting the peripheral image into the identifier, estimating the distance from the vehicle to the virtual object as the distance from the vehicle to the other vehicle based on the position of the vertex of the virtual object closest to the vehicle; A distance estimation computer program that causes a processor mounted on the vehicle to execute.

Images