Gradient recognition device

Abstract

The slope recognition device includes: a photographing unit; a vanishing point calculation unit that calculates a position of a vanishing point in an image acquired by the photographing unit; a distance calculation unit that calculates a distance from a host vehicle to a front vehicle based on the calculated position of the vanishing point and a position of a lower end portion of the front vehicle in the image; an area calculation unit that calculates an area of the front vehicle in the image; and a determination unit that determines whether a slope of a road changes in front of the host vehicle based on the calculated distance and area. The determination unit determines that the slope of the road changes in front of the host vehicle when a change amount or a change rate of the distance calculated by the distance calculation unit is a first prescribed value or more and a change amount or a change rate of the area calculated by the area calculation unit is a second prescribed value or less.

Description

Technical Field

[0001] This invention relates to a slope recognition device for identifying changes in road surface slope in the direction of travel of a vehicle. Background Technology

[0002] As such a device, there is a known prior art that, when a vehicle ahead is included in a camera image, calculates a predicted position of the lower end of the vehicle ahead, assuming a constant road slope, and determines whether the difference between the predicted position and the lower end position of the vehicle ahead detected by the camera image exceeds a threshold. If the difference exceeds the threshold, it is determined that a slope exists. Such a device is described, for example, in Patent Document 1. In the device described in Patent Document 1, the predicted position is calculated based on the position of the vanishing point determined by the camera image.

[0003] However, in the device described in Patent Document 1, it is sometimes difficult to accurately identify changes in the slope in situations such as changes in the position of the vanishing point due to the up-and-down movement of the vehicle.

[0004] Existing technical documents

[0005] Patent documents

[0006] Patent Document 1: Japanese Patent Application Publication No. 2019-079182 (JP2019-079182A). Summary of the Invention

[0007] The slope recognition device of this invention comprises: a camera unit mounted on a vehicle, which captures images of a predetermined area including a vehicle ahead of the vehicle; a vanishing point calculation unit that calculates the position of the vanishing point in the image captured by the camera unit; a distance calculation unit that calculates the distance from the vehicle to the vehicle ahead based on the position of the vanishing point calculated by the vanishing point calculation unit and the position of the lower end of the vehicle ahead in the image captured by the camera unit; an area calculation unit that calculates the area of ​​the vehicle ahead in the image captured by the camera unit; and a determination unit that determines whether the slope of the road surface has changed in front of the vehicle based on the distance calculated by the distance calculation unit and the area calculated by the area calculation unit. The determination unit determines that the slope of the road surface has changed in front of the vehicle when the change in distance or rate of change calculated by the distance calculation unit is greater than or equal to a first predetermined value, and the change in area or rate of change calculated by the area calculation unit is less than or equal to a second predetermined value. Attached Figure Description

[0008] The objectives, features, and advantages of the present invention are further illustrated by the following description of embodiments in conjunction with the accompanying drawings.

[0009] Figure 1This is a diagram showing the vehicle having the slope recognition device according to an embodiment of the present invention, viewed from the side.

[0010] Figure 2 This is a diagram illustrating an example of a driving scenario using a slope recognition device according to an embodiment of the present invention.

[0011] Figure 3 This is a block diagram illustrating the main components of a slope recognition device according to an embodiment of the present invention.

[0012] Figure 4 It is shown by Figure 3 A flowchart of an example of the processing performed by the controller.

[0013] Figure 5 It is shown Figure 1 A diagram of a variation. Detailed Implementation

[0014] The following is for reference Figures 1-5 Embodiments of the present invention will now be described. The slope recognition device of the present invention is configured to recognize the slope of the road surface in front of the vehicle based on images from a camera mounted at the front of the vehicle that captures images in the direction of the vehicle's travel.

[0015] Figure 1 This is a side view of the vehicle 100 equipped with the slope recognition device according to an embodiment of the present invention. (See figure) Figure 1 As shown, a camera 1 is installed at the front of the vehicle 100, more specifically near the front windshield in the upper part of the vehicle interior. The camera 1 is a single-lens reflex camera with imaging elements (image sensors) such as CCD (charge-coupled device) and CMOS (complementary metal-oxide-semiconductor). The camera 1 continuously captures images of the space in front of the vehicle 100, obtaining images of objects (camera images).

[0016] exist Figure 1 The vertical field of view θ of camera 1 and the shooting area AR are shown. The shooting area AR includes the preceding vehicles 101 (101_1, 101_2) traveling in front of this vehicle 100 as the subject of camera 1's shooting. The preceding vehicles 101_1 and 101_2 illustrate the case where they are traveling on different road surfaces. That is, the preceding vehicle 101_1 is traveling on the same road surface 200 (the road surface on the same horizontal plane) as the road surface 200 that this vehicle 100 is traveling on, and is at the same height as this vehicle 100. On the other hand, the preceding vehicle 101_2 is traveling forward on a road surface 201 with an uphill slope, and is positioned above this vehicle 100.

[0017] Figure 2This is a diagram illustrating an example of a driving scenario using the slope recognition device of this embodiment. The diagram shows a view (camera image) as observed from camera 1 of the vehicle 100. Figure 2 The image includes a vehicle image 100a showing the front end of the engine hood of the vehicle 100, a front vehicle image 101a showing the vehicle in front 101, road images 200a and 201a showing road surfaces 200 and 201 respectively, road marking images 211a and 212a showing the left and right road markings 211 and 212 respectively, and a lane image 210a showing the driving lane 210.

[0018] like Figure 2 As shown, vehicle 100 is traveling in lane 210 defined by a pair of road markings 211 and 212 extending along the direction of travel of vehicle 100. Ahead of the road surface 200 on which vehicle 100 is traveling, there is a road surface 201 with an uphill slope. Ahead of vehicle 100, there is another vehicle 101 traveling on road surface 200 (equivalent to...) Figure 1 (Vehicle 101_1 in front). Points P1 and P2 in the figure are vanishing points.

[0019] Vanishing points P1 and P2 are the intersection points (points at infinity) obtained by extending the left and right road lines 211 and 212, the sidewalk area, and the guardrails into straight lines. When the road slope is constant, the vanishing points converge at a single point on the image. Figure 2 During the journey, the road gradient changes to an uphill gradient, resulting in multiple vanishing points P1 and P2. Specifically, there is a vanishing point P1 determined by road markings on the road surface 200 on which the vehicle 100 is currently traveling, and a vanishing point P2 determined by road markings on the road surface 201 ahead of the vehicle 100. It should be noted that if no vanishing point is found due to obstacles, forks in the road, etc., the most recently determined vanishing point can be used.

[0020] The slope recognition device of this embodiment has the function of calculating the distance from the current vehicle 100 to the vehicle 101 ahead, i.e., the inter-vehicle distance, based on a camera image. The inter-vehicle distance is calculated as follows. First, the vanishing point P1 is determined by extending the road markings or other markings on the road surface where the current vehicle 100 is traveling. Next, the length y1 from the vanishing point P1 to the ground contact point of the vehicle 101 ahead is calculated in the camera image. That is, in an XY coordinate system with the horizontal axis of the camera image as the X-axis and the vertical axis as the Y-axis, the length y1 is calculated by subtracting the y-coordinate of the ground contact point from the y-coordinate of the vanishing point P1.

[0021] The length y1 on the camera image is related to the vehicle-to-vehicle distance. That is, the shorter the length y1 is, the longer the vehicle-to-vehicle distance, as the ground plane is below the vanishing point P1. Therefore, the vehicle-to-vehicle distance can be calculated by substituting the length y1 into the formula showing the relationship between the length y1 and the vehicle-to-vehicle distance. The calculated vehicle-to-vehicle distance is treated as the actual vehicle-to-vehicle distance, for example, when following a vehicle ahead while keeping the vehicle-to-vehicle distance constant at a target vehicle-to-vehicle distance.

[0022] However, when the vehicle 101 ahead is traveling on road 201, which has an uphill slope relative to road surface 200, the contact surface area moves upwards relative to the vanishing point P1. As a result, if the inter-vehicle distance is calculated based on distance y1, the inter-vehicle distance cannot be calculated correctly, making it difficult to follow the vehicle 101 ahead effectively. It should be noted that when the slope in front of the vehicle 100 is not uphill but downhill, the inter-vehicle distance also cannot be calculated correctly. Therefore, in this embodiment, the change in slope in front of the vehicle 100 is identified as follows, and the inter-vehicle distance is calculated taking into account the change in slope.

[0023] Figure 3 This is a block diagram illustrating the main components of a slope recognition device 10 according to an embodiment of the present invention. Figure 3 As shown, the slope recognition device 10 includes a camera 1, a controller 20, and a driving actuator 2.

[0024] The driving actuator 2 is an actuator that controls the drive of the vehicle 100 when it is moving, especially when the vehicle 100 follows the vehicle 101 ahead at a predetermined distance corresponding to its speed. When the driving source is an engine, the driving actuator 2 includes a throttle actuator for adjusting the opening of the engine's throttle valve. When the driving source is a drive motor, the drive motor is included in the driving actuator 2. A brake actuator that operates the vehicle 100's braking system is also included in the driving actuator 2. A steering actuator that drives the steering system can also be included in the driving actuator 2.

[0025] The controller 20 is configured as a computer with a CPU (Central Processing Unit), ROM (Read-Only Memory), RAM (Random Access Memory), and other peripheral circuits such as I / O interfaces. The controller 20 performs prescribed processing based on image signals from the camera 1, determines whether the slope of the road surface in front of the vehicle 100 has changed, and controls the driving actuator 2 based on the determination result. The controller 20 has a functional structure including a calculation unit 21, a storage unit 22, a determination unit 23, and a driving control unit 24.

[0026] The calculation unit 21 calculates the vanishing points P1 and P2, the inter-vehicle distance D between the current vehicle 100 and the vehicle 101 in front, and the area A of the rear surface of the vehicle 101 in front, based on the camera images. That is, the calculation unit 21 functions as a vanishing point calculation unit, a distance calculation unit, and an area calculation unit.

[0027] More specifically, the vanishing point calculation unit will be as follows: Figure 2 The vanishing point P1 is the intersection of straight lines extending from the left and right sides of the vehicle 100 towards the upper side of the camera image (the side of the vehicle 100's direction of travel). The coordinates (x and y coordinates) of the vanishing point P1 on the camera image are calculated. The vanishing point P1 can be calculated using Hough transform or similar methods. It should be noted that when the road gradient changes along the way, the vanishing point calculation unit calculates multiple vanishing points P1 and P2.

[0028] The distance calculation unit calculates the Y-axis length y1 from the position of the vanishing point P1 calculated by the vanishing point calculation unit to the ground plane of the preceding vehicle 101 in the camera image. The distance calculation unit also uses the relationship between the Y-axis length y1 of the camera image and the inter-vehicle distance D stored in the storage unit 22 to calculate the inter-vehicle distance D from the current vehicle 100 to the preceding vehicle 101 corresponding to the length y1.

[0029] The area calculation unit calculates the area A of the rear surface of the vehicle 101 in the camera image. For example, Figure 2 As shown, a rectangular shape F is defined by the ground contact surface, upper surface, and left and right side surfaces of the front vehicle 101. The area calculation unit calculates the area (area in the image) of shape F by multiplying the length in the Y-axis direction (length in the image) from the ground contact surface of the front vehicle 101 to the upper surface and the length in the X-axis direction (length in the image) from the left surface to the right surface. This area of ​​shape F is then processed as the area A of the rear surface of the front vehicle 101.

[0030] Storage unit 22 stores, in chronological order, the workshop distance D calculated by the workshop distance calculation unit and the area A calculated by the area calculation unit, from the current time point to the specified time. The specified time is equivalent to the vehicle arriving at, for example, 100... Figure 1 The specified time is the time required for the vehicle ahead 101 to start traveling on a road surface 201 with a different gradient than the road surface 200 on which the vehicle 100 is traveling (the point of gradient change) from its initial position Pa. In other words, it is the time until the vehicle 100 and the vehicle ahead 101 are traveling on the same gradient road surface 201. Therefore, the longer the distance D between the two vehicles and the slower the speed, the longer the specified time. It should be noted that a constant time can also be used as the specified time, regardless of the distance D between the two vehicles and the speed. Alternatively, the time required for the vehicle 100 to travel a specified distance towards the vehicle ahead 101 can also be used as the specified time.

[0031] The determination unit 23 determines whether there is a slope in front of the vehicle 100 based on the workshop distance D calculated by the distance calculation unit and the area A calculated by the area calculation unit. Specifically, the determination unit 23 first determines whether the area A calculated by the area calculation unit is greater than or equal to a predetermined value A1. This determination is to prevent the possibility of mistakenly determining that the change in area A or the rate of change has increased when the change in area A is calculated from a state where area A is less than the predetermined value A1, that is, a state where the area is relatively small.

[0032] When the determination unit 23 determines that the area A is above a specified value, it determines whether the change in workshop distance D within a specified time, calculated by the distance calculation unit and stored in the storage unit 22, is above a specified value ΔD1, and whether the change in area A within a specified time, calculated by the area calculation unit and stored in the storage unit 22, is below a specified value ΔA1. This is the determination of whether the slope condition is met. When the slope condition is met, it is determined that the slope has changed.

[0033] That is, for example, Figure 2 As shown, when the vehicle 100 is traveling on a level road surface 200, and the vehicle in front 101 is also traveling on a level road surface 200, the change in length y1 from the vanishing point P1 to the ground surface Δy is relatively small, less than the specified value Δy1. On the other hand, when the vehicle 100 is traveling on a level road surface 200, and the vehicle in front 101 is traveling on an uphill road surface 201, the ground surface of the vehicle in front 101 in the camera image moves upward, the change in length y1 Δy becomes more than the specified value Δy1, and the change in inter-vehicle distance D ΔD also becomes more than the specified value ΔD1. At this time, as Figure 1 As shown, even if the vehicle 101 in front is traveling on the road 201 with an uphill slope, as long as the actual inter-vehicle distance does not change much, the change in the area A of the rear surface of the vehicle 101 in front, ΔA, is small and below the specified value ΔA1.

[0034] Taking this into consideration, the determination unit 23 determines whether ΔD ≥ D1 and ΔA ≤ ΔA1 are true, i.e., whether the slope condition is true. Then, when the slope condition is determined to be true, the determination unit 23 determines that the slope has changed in the direction of travel of the vehicle 100. It should be noted that the determination unit 23 can also determine whether the rate of change of the workshop distance D calculated by the distance calculation unit within a specified time is above a specified value and whether the rate of change of the area A calculated by the area calculation unit within a specified time is below a specified value, thereby determining whether the slope condition is true. Alternatively, the changes in workshop distance D and area A, ΔD and ΔA, can be calculated without using a specified time as a condition, and the slope condition is determined to be true when ΔD ≥ D1 and ΔA ≤ ΔA1 are true.

[0035] When instructed to follow the vehicle 101 ahead, the driving control unit 24 controls the driving actuator 2 to make the actual distance between vehicles the target distance corresponding to the vehicle speed. At this time, if the gradient condition is not met, the driving control unit 24 uses the distance D calculated by the distance calculation unit as the actual distance between vehicles. On the other hand, when the determination unit 23 determines that the gradient condition is met, the distance D calculated before the gradient condition is determined (e.g., just before the determination) and stored in the storage unit 22 is used as the actual distance between vehicles. This prevents incorrect calculation of the actual distance between vehicles and enables accurate following.

[0036] Figure 4 This is a flowchart illustrating an example of a process executed by the controller 20 according to a predetermined procedure. The process shown in the flowchart begins, for example, when a vehicle 101 ahead is identified in a camera image through processes such as template matching, and is repeatedly executed at a predetermined cycle.

[0037] First, in step S1 (S: processing step), the image signal from camera 1 is read in. Next, in step S2, the vanishing point P1 is calculated based on the camera image. Next, in step S3, the length y1 from the vanishing point P1 to the contact surface of the preceding vehicle 101 is calculated, and the vehicle distance D corresponding to the length y1 is calculated using the relationship between the length y1 and the vehicle distance D pre-stored in storage unit 22. Next, in step S4, the area A of the rear surface (graphic F) of the preceding vehicle 101 is calculated based on the camera image. Next, in step S5, the vehicle distance D calculated in step S3 and the area A calculated in step S4 are stored in storage unit 22. In this case, the vehicle distance D and area A from the current time point to a predetermined time are stored, and data before the predetermined time are deleted sequentially.

[0038] Next, in S6, it is determined whether the area A calculated in S4 is greater than or equal to the specified value A1. If S6 is affirmative (S6: Yes), proceed to S7; otherwise, end the process. In S7, it is determined whether the change in the workshop distance D stored in the storage unit 22 within a specified time, ΔD, is greater than or equal to the specified value ΔD1, and whether the change in the area A within the specified time, ΔA, is less than or equal to the specified value ΔA1. If S7 is affirmative (S7: Yes), proceed to S8; otherwise, end the process. In S8, it is determined that the slope has changed in front of the vehicle 100, and the process ends.

[0039] The following summarizes the operation of the slope recognition device 10 in this embodiment. When the vehicle 100 is following the vehicle 101 ahead, the vanishing point P1 is calculated based on the camera image. Figure 2The distance between vehicles is calculated using the following method: The distance between vehicles is calculated based on the length y1 of the contact surface from the vanishing point P1 to the preceding vehicle 101. Thus, the distance between vehicles is calculated using a low-cost device employing a single-lens camera 1. At this time, the driving actuator 2 is controlled to make the distance between vehicles D a target distance corresponding to the vehicle speed.

[0040] When following another vehicle, when the preceding vehicle 101 begins to travel on the uphill slope of the road surface 201, the length y1 of the contact surface with the preceding vehicle 101 changes, and the change in the inter-vehicle distance D, ΔD, becomes a predetermined value ΔD1 or more. Conversely, because the actual change in inter-vehicle distance is smaller, the change in the area A of the rear surface of the preceding vehicle 101 is either a predetermined value A1 or less, or the change in the area A of the rear surface of the preceding vehicle 101, ΔA, is less than the predetermined value ΔA1. Thus, the change in the slope in front of this vehicle 100 (S7→S8) is identified.

[0041] When a change in gradient is detected, the vehicle following the vehicle 101 ahead is used as the actual following distance, calculated before the gradient change was detected. This prevents the use of an excessively long following distance D. As a result, traffic safety is improved without affecting surrounding traffic flow, while mitigating a decrease in traffic flow smoothness. When a change in gradient is detected, this information can also be communicated to the driver. This allows the driver to perform acceleration, braking, and other actions without delay.

[0042] The following effects can be achieved by adopting this implementation method.

[0043] (1) The slope recognition device 10 includes: a camera 1 mounted on the vehicle 100, which captures a predetermined shooting area AR including a vehicle 101 located in front of the vehicle 100; a vanishing point calculation unit (calculation unit 21) that calculates the position of the vanishing point P1 in the image captured by the camera 1; a distance calculation unit (calculation unit 21) that calculates the inter-vehicle distance D from the vehicle 100 to the vehicle 101 based on the position of the vanishing point P1 calculated by the vanishing point calculation unit and the position of the lower end of the vehicle 101 in the image captured by the camera 1; an area calculation unit (calculation unit 21) that calculates the area A of the vehicle 101 in the image captured by the camera 1; and a determination unit 23 that determines whether the slope of the road surface has changed in front of the vehicle 100 based on the inter-vehicle distance D calculated by the distance calculation unit and the area A calculated by the area calculation unit. Figure 3 When the change in the workshop distance D calculated by the distance calculation unit ΔD is greater than or equal to the predetermined value ΔD1 and the change in the area A calculated by the area calculation unit ΔA is less than or equal to the predetermined value ΔA1, the determination unit 23 determines that the slope of the road surface has changed in front of the vehicle 100. Figure 4 ).

[0044] Therefore, even when the position of the vanishing point P1 changes due to the vehicle's vertical movement, changes in road slope can be accurately determined. Furthermore, since slope changes are determined using only camera images, accurate slope determination is possible with minimal setup. Also, if the vehicle distance D obtained based on the vanishing point P changes, it can be determined that the vehicle distance D has not actually changed, but rather changed due to the slope, thus preventing the use of incorrect vehicle distance D for following maneuvers.

[0045] (2) The determination unit 23 further determines whether the area A calculated by the area calculation unit is a predetermined value A1 or higher. If the area A calculated by the area calculation unit is a predetermined value A1 or higher, it determines whether the slope of the road surface changes in front of the vehicle 100. Figure 4 Therefore, when the area A is large, it is possible to determine whether the slope condition of the change in area A ΔA is below the specified value ΔA1, thus accurately determining whether the slope of the road surface has changed.

[0046] The above-described embodiments can be modified in various ways. Several modifications are described below. In the above-described embodiments, the condition for determining whether the slope condition is met is that the area A is a predetermined value A1 or higher. However, the condition for determining whether the slope condition is met can also be that multiple vanishing points are calculated. That is, when there is a slope in front of the vehicle 100, such as Figure 2 As shown, multiple vanishing points P1 and P2 are calculated. Taking this into account, when the vanishing point calculation unit calculates multiple vanishing points P1 and P2, it can also determine whether the road surface slope changes in front of the vehicle 100. Therefore, it is possible to accurately determine whether a change in slope exists.

[0047] In the above embodiment, an example is shown where, when there is an uphill slope in front of the vehicle 100, the presence or absence of a change in slope (the presence or absence of a slope change point Pa) is determined based on the change in distance D calculated by the distance calculation unit ΔD and the change in area A calculated by the area calculation unit ΔA. However, even when there is a downhill slope in front of the vehicle 100, the presence or absence of a slope change can be determined in the same way. Figure 5 As shown, even when the vehicle 100 is traveling on a sloped road 201 while the vehicle in front of it is traveling on a level road 200, the presence or absence of a change in slope can be determined in the same way.

[0048] In the above embodiment, the camera, which serves as the capturing unit, is installed on the upper front side of the vehicle interior. However, as long as the area being captured includes the vehicle in front of the vehicle itself, the mounting position of the capturing unit is not limited to the above description. In the above embodiment, when the change in distance D ΔD calculated by the distance calculation unit within a specified time is a specified value (first specified value) or higher, and the change in area A ΔA calculated by the area calculation unit within a specified time is a specified value ΔA1 (second specified value) or lower, the determination unit 23 determines that the slope of the road surface has changed in front of the vehicle 100 (there is a slope change point Pa). However, the determination unit 23 can also determine that the slope of the road surface has changed in front of the vehicle 100 when the rate of change of distance D calculated by the distance calculation unit within a specified time is a first specified value or higher, and the rate of change of area A calculated by the area calculation unit within a specified time is a second specified value or lower. Therefore, the first specified value and the second specified value are not limited to the above description. In addition, the change in distance D and the rate of change of area A can be calculated without the condition of a specified time period.

[0049] In the above embodiment, when the vehicle 100 follows the vehicle 101 ahead, it is determined whether the slope of the road surface changes in front of the vehicle 100. However, even when following the vehicle, the presence or absence of a change in slope can be determined when there is a vehicle ahead. In the above embodiment, the vehicle-to-vehicle distance information stored in the storage unit 22 before the slope change is determined is used for following the vehicle. However, the vehicle-to-vehicle distance information can also be used for driving control other than following the vehicle.

[0050] It is possible to combine one or more of the above-described embodiments and variations, and to combine the variations with each other.

[0051] Using this invention, changes in slope can be accurately identified even when the location of the vanishing point changes.

[0052] The present invention has been described above in conjunction with preferred embodiments, but those skilled in the art should understand that various modifications and alterations can be made without departing from the scope of the following claims.

Claims

1. A slope recognition device, characterized in that, have: The camera unit (1) is installed on the vehicle (100) and takes pictures of a designated area including the vehicle (101) in front of the vehicle (100). The vanishing point calculation unit calculates the position of the vanishing point (P1) in the image acquired by the imaging unit (1); The distance calculation unit calculates the distance from the vehicle (100) to the vehicle (101) in front based on the longitudinal length (y1) in the image from the position of the vanishing point (P1) calculated by the vanishing point calculation unit to the position of the lower end of the vehicle (101) in front in the image acquired by the shooting unit (1). An area calculation unit calculates the area of ​​the vehicle (101) in front in the image acquired by the shooting unit (1); as well as The determination unit (23) determines, based on the distance calculated by the distance calculation unit and the area calculated by the area calculation unit, whether the slope of the road surface changes in front of the vehicle (100). When the determination unit (23) determines that the slope of the road surface changes in front of the vehicle (100) when the change in distance or rate of change calculated by the distance calculation unit is above a first predetermined value and the change in area or rate of change calculated by the area calculation unit is below a second predetermined value.

2. The slope recognition device according to claim 1, characterized in that, The determination unit (23) further determines whether the area calculated by the area calculation unit is a predetermined value (A1) or higher. If the area calculated by the area calculation unit is a predetermined value (A1) or higher, it determines whether the slope of the road surface changes in front of the vehicle (100).

3. The slope recognition device according to claim 1 or 2, characterized in that, The determination unit (23) further determines whether multiple vanishing points (P1, P2) are calculated by the vanishing point calculation unit. When multiple vanishing points (P1, P2) are calculated by the vanishing point calculation unit, it determines whether the slope of the road surface changes in front of the vehicle (100).

4. The slope recognition device according to claim 1 or 2, characterized in that, It also includes a storage unit (22) that stores, in chronological order, the distance calculated by the distance calculation unit and the area calculated by the area calculation unit from the current time point to a predetermined time point. The determination unit (23) determines whether the change in distance or rate of change of storage in storage unit (22) within the specified time period is greater than or equal to the first specified value and whether the change in area or rate of change of storage in storage unit (22) within the specified time period is less than or equal to the second specified value.

5. The slope recognition device according to claim 4, characterized in that, It also includes a driving control unit (24), which controls the driving actuator (2) based on the distance calculated by the distance calculation unit. When the determination unit (23) determines that the slope of the road surface changes in front of the vehicle (100), the driving control unit (24) controls the driving actuator (2) based on the distance stored in the storage unit (22) before the determination is about to be implemented.

Images