KR20210071454A - Vehicle and control method thereof - Google Patents

Abstract

The present invention provides a vehicle capable of driving comfortably by preventing erroneous braking in a situation in which the vehicle can be driven by determining the height of an object around the vehicle, and a control method thereof.
A vehicle according to an embodiment includes a first camera configured to acquire an image of a first area around the vehicle; a second camera provided at a location different from that of the first camera and configured to acquire an image of a second area around the vehicle; and identifying at least two points of the object based on the image of the object acquired by the first camera and the second camera, and determining a reference area based on the viewing angle of the first camera, wherein the object is the reference and a controller configured to determine whether to brake the vehicle based on the height of the object determined based on the image of the first region and the image of the second region when included in the region.

Description

Vehicle and control method {VEHICLE AND CONTROL METHOD THEREOF}

The present technology relates to a vehicle for detecting an obstacle and a method for controlling the same.

Autonomous vehicle technology is a technology that enables the vehicle to automatically drive by understanding the road conditions without the driver controlling the brake, steering wheel, or accelerator pedal.

Autonomous driving technology is a key technology for the realization of smart cars. For autonomous vehicles, highway driving assistance system (HDA, technology that automatically maintains the distance between cars) and rear-side warning system (BSD, detecting surrounding vehicles while reversing) , warning system), automatic emergency braking system (AEB, technology that activates the brake when the vehicle in front is not recognized), lane departure warning system (LDWS), lane keeping assist system (LKAS, lane departure without a turn signal) Complementary technology), Advanced Smart Cruise Control (ASCC, technology that maintains a constant speed while maintaining the distance between vehicles at a set speed), Congested Section Driving Assist System (TJA), Parking Collision-Avoidance Assist (PCA) consists of, etc.

In particular, in a Parking Collision-Avoidance Assist (PCA), a camera may be used to obtain information on an object on the main surface of a vehicle.

In addition, the Rear Parking Collision Assist (PCA-R) system can use a rear camera/ultrasonic sensor to warn the driver of danger and control the vehicle's braking in the event of a collision with a rear pedestrian or obstacle. However, in the case of the Forward Parking Collision Assist System (PCA-F), it is difficult to identify low obstacles during operation, so incorrect braking is applied, which may make smooth driving difficult. Therefore, research to solve these problems is being actively conducted.

The present invention provides a vehicle capable of driving comfortably by preventing erroneous braking in a situation in which the vehicle can be driven by determining the height of an object around the vehicle, and a control method thereof.

A vehicle according to an embodiment includes a first camera configured to acquire an image of a first area around the vehicle; a second camera provided at a location different from that of the first camera and configured to acquire an image of a second area around the vehicle; and identifying at least two points of the object based on the image of the object acquired by the first camera and the second camera, and determining a reference area based on the viewing angle of the first camera, wherein the object is the reference and a controller configured to determine whether to brake the vehicle based on the height of the object determined based on the image of the first region and the image of the second region when included in the region.

The at least two points of the object may include a reference point at which the object is in contact with a road and a feature point corresponding to the highest point of the object determined based on the image of the first area and the image of the second area.

If the reference point and the feature point are not included in the reference region, the controller may track the reference point and the feature point based on the image of the first region and the image of the second region.

The controller may calculate the moving distance of the vehicle from a point in time when the reference point is excluded from the first region.

The controller may determine the height of the object based on the moving distance of the vehicle, the height of the vehicle, and the reference area from a point in time when the feature point is excluded from the first area.

The controller may determine the height of the object by applying a ratio of a distance of the reference area to the vehicle to a moving distance of the vehicle to the height of the vehicle.

The controller may determine whether the feature point is at least one point on a straight line perpendicular to the ground, and determine whether the object is an obstacle.

The controller may determine a region of interest (ROI) included in the reference region, and when the object is included in the region of interest, determine the height of the object.

The first camera may be provided as a windshield camera, and the second camera may be provided as an SVM camera provided in front of the vehicle.

When the height of the object exceeds a predetermined height, the controller may brake the vehicle based on a distance between the object and the vehicle.

In a vehicle control method according to an embodiment, a first camera acquires an image of a first area around the vehicle, a second camera is provided at a different location from the first camera, and the image of a second area around the vehicle obtain, identify at least two points of the object based on the image of the object acquired by the first camera and the second camera, and determine a reference area based on the viewing angle of the first camera,

and determining whether to brake the vehicle based on the height of the object determined based on the image of the first area and the image of the second area when the object is included in the reference area.

The at least two points of the object may include a reference point at which the object is in contact with a road and a feature point corresponding to the highest point of the object determined based on the image of the first area and the image of the second area.

When the first camera and the second camera identify at least two points of the object based on the image of the object acquired, if the reference point and the feature point are not included in the reference area, the image of the first area and tracking the reference point and the feature point based on the image of the second region.

Determining whether to brake the vehicle may include calculating a moving distance of the vehicle from a point in time when the reference point is excluded from the first region.

Determining the height of the object may include determining the height of the object based on a moving distance of the vehicle, the height of the vehicle, and the reference area from a point in time when the feature point is excluded from the first area.

Determining the height of the object may include determining the height of the object by applying a ratio of a distance of the reference area with respect to the vehicle to a moving distance of the vehicle to the height of the vehicle.

The vehicle control method according to an embodiment may further include determining whether the object is an obstacle by determining whether the feature point is at least one point on a straight line perpendicular to the ground.

The vehicle control method according to an embodiment may further include determining a region of interest (ROI) included in the reference region, and determining a height of the object when the object is included in the region of interest.

The first camera may be provided as a windshield camera, and the second camera may be provided as an SVM camera provided in front of the vehicle.

Determining whether to brake the vehicle may include braking the vehicle based on a distance between the object and the vehicle when the height of the object exceeds a predetermined height.

A vehicle and a method for controlling the same according to an embodiment determine the height of an object around the vehicle to prevent erroneous braking in a situation in which the vehicle is drivable, thereby enabling comfortable driving.

1 is a control block diagram of a vehicle according to an exemplary embodiment.
2A and 2B are diagrams for explaining that a vehicle determines a height of an object according to an exemplary embodiment.
3A to 3D are diagrams illustrating examples of objects according to an embodiment of the present invention.
4A to 4C are diagrams illustrating a relationship between an ROI and an object according to an exemplary embodiment.
5 is a flowchart according to an embodiment.

Like reference numerals refer to like elements throughout the specification. This specification does not describe all elements of the embodiments, and general content in the technical field to which the present invention pertains or content that overlaps between embodiments is omitted. The term 'part, module, member, block' used in the specification may be implemented in software or hardware, and according to embodiments, a plurality of 'part, module, member, block' may be implemented as one component, It is also possible for one 'part, module, member, block' to include a plurality of components.

Throughout the specification, when a part is "connected" with another part, it includes not only direct connection but also indirect connection, and indirect connection includes connection through a wireless communication network. do.

In addition, when a part "includes" a certain component, this means that other components may be further included rather than excluding other components unless otherwise stated.

Throughout the specification, when a member is said to be located “on” another member, this includes not only a case in which a member is in contact with another member but also a case in which another member is present between the two members.

Terms such as first, second, etc. are used to distinguish one component from another, and the component is not limited by the above-mentioned terms.

The singular expression includes the plural expression unless the context clearly dictates otherwise.

In each step, the identification code is used for convenience of description, and the identification code does not describe the order of each step, and each step may be performed differently from the specified order unless the specific order is clearly stated in the context. have.

Hereinafter, the working principle and embodiments of the present invention will be described with reference to the accompanying drawings.

1 is a control block diagram of a vehicle 1 according to an embodiment.

Referring to FIG. 1 , a vehicle 1 according to an exemplary embodiment may include a first camera 110 , a second camera 120 , a controller 200 , and a braking unit 300 .

The camera installed in the vehicle 1 may include a charge-coupled device (CCD) camera 120 or a CMOS color image sensor. Here, both CCD and CMOS refer to a sensor that converts and stores the light entered through the lens of the camera 120 into an electric signal. Specifically, a charge-coupled device (CCD) camera is a device that converts an image into an electrical signal using a charge-coupled device. In addition, CIS (CMOS Image Sensor) refers to a low-consumption, low-power type imaging device having a CMOS structure, and serves as an electronic film of a digital device. In general, CCD is more sensitive than CIS, so it is often used for vehicles (1) and (1), but it is not necessarily limited thereto.

The first camera 110 may acquire an image of a first area around the vehicle 1 . Meanwhile, the first camera 110 may be provided as a windshield camera provided in the vehicle 1 . The first area image may mean an area of an image that the windshield camera can acquire.

Meanwhile, the first camera 110 is a camera located in the interior space behind the windshield of the vehicle 1 , and may correspond to an MFC camera for driving assistance or a DVRS camera for image recording.

The second camera 120 may be provided at a location different from that of the first camera 110 , and may acquire an image of a second area around the vehicle 1 . Meanwhile, the second camera 120 may be provided as an SVM camera. The second camera 120 according to an embodiment is a camera located in the radiator grill of the vehicle 1 and may provide an image of the front proximity of the vehicle 1 for parking convenience.

The braking unit 300 may brake the vehicle 1 based on a command from the control unit 200 . A signal for braking the vehicle 1 and a configuration involved in actual braking may be included in the braking unit 300 , and the embodiment is not limited thereto.

The controller 200 may identify at least two points of the object based on the image of the object acquired by the first camera 110 and the second camera 120 . The two points of the object may be composed of a reference point at which the object is in contact with the floor and a feature point corresponding to the height of the object, as will be described later.

The controller 200 may determine the reference area based on the viewing angle of the first camera 110 . The reference area does not correspond to the viewing angle of the first camera 110 , but may be determined as a portion corresponding to the viewing angle of the second camera 120 .

When the object is included in the reference area, the controller 200 may determine whether to brake the vehicle 1 based on the height of the object determined based on the image of the first area and the image of the second area. A detailed description related thereto will be provided later.

Meanwhile, at least two points of the object identified by the controller 200 may include a reference point at which the object is in contact with the road, and a feature point corresponding to the highest point of the object determined based on the image of the first area and the image of the second area.

If the reference point and the feature point of the object are not included in the reference region, the controller 200 may track the reference point and the feature point based on the image of the first region and the image of the second region. That is, if the object is not included in the reference area, the controller 200 may continue to track the object.

The controller 200 may calculate the moving distance of the vehicle 1 from a point in time when the reference point is excluded from the first region.

The control unit 200 may determine the height of the object based on the moving distance of the vehicle 1 , the height of the vehicle 1 , and the reference region from a time point when the feature point is excluded from the first region. A detailed description related thereto will be provided later.

The controller 200 may determine the height of the object by applying the ratio of the distance of the reference region with respect to the vehicle 1 to the moving distance of the vehicle 1 to the height of the vehicle 1 .

The controller 200 may determine whether the object is an obstacle by determining whether the feature point is at least one point on a straight line perpendicular to the ground. Specifically, the controller 200 may determine as an obstacle only when there is an edge component perpendicular to the ground among the feature points, and when there is no vertical edge of the identified object, it may be determined as the floor pattern of the road surface.

The controller 200 may determine a region of interest (ROI) included in the reference region and, when the object is included in the region of interest, determine the height of the object. That is, the first region and the second region may be wider than the region required for driving of the vehicle 1 , and it is inefficient to determine the height of the object in the part necessary for driving. In determining the region of interest, the object corresponds to the region of interest. Only in this case, the height of the object can be determined.

The controller 200 may brake the vehicle 1 when the height of the object exceeds a predetermined height.

The controller 200 performs the above-described operation using a memory (not shown) that stores data for an algorithm for controlling the operation of components in the vehicle 1 or a program reproducing the algorithm, and the data stored in the memory. may be implemented by a processor (not shown). In this case, the memory and the processor may be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip.

At least one component may be added or deleted according to the performance of the components of the vehicle 1 illustrated in FIG. 1 . In addition, it will be readily understood by those skilled in the art that the mutual positions of the components may be changed corresponding to the performance or structure of the system.

Meanwhile, each component shown in FIG. 1 means a hardware component such as software and/or a Field Programmable Gate Array (FPGA) and an Application Specific Integrated Circuit (ASIC).

2A and 2B are diagrams for explaining that a vehicle determines a height of an object according to an exemplary embodiment.

Referring to FIG. 2A , a first camera 110 , a second camera 120 , and a first region Z1 and a second region Z2 corresponding to each are shown.

The first camera 110 may be provided as a windshield camera.

The first camera 110 is difficult to obtain image information of a front near-low obstacle because the angle of view is obscured by the vehicle hood contact point.

On the other hand, the second camera 120 may be provided as a Surround View Monitor (SVM) camera. The second camera 120 may acquire an image of a low obstacle in a short distance in front of the vehicle, but it is difficult to acquire information on the height and distance of the obstacle.

Accordingly, the controller 200 may acquire image information of an object with the first camera 110 and the second camera 120 at a long distance in front of the vehicle in which the first region Z1 and the second region Z2 are common.

However, when the object leaves the first area Z1 and is included in the second area Z2 and approaches the vehicle, the first camera 110, that is, to obtain an image of a partial area of the object by covering the hood of the windshield camera. It is difficult.

Based on these characteristics, the control unit 200 can determine a low obstacle. A detailed description related thereto will be described with reference to FIG. 2B .

Meanwhile, referring to FIG. 2B , an operation of determining the height of an object in front while the vehicle is driving is described.

Referring to FIG. 2B , it is shown that the object exists and the height of the object is determined as the vehicle approaches.

When the object is located outside the reference area (M1), the first camera 110 and the second camera 120 may track the reference point MR and the feature point MF of the object. Meanwhile, the reference point MR may mean a contact point or an edge line where the ground and the object come into contact with each other based on the angle of view of the image of the first camera 110 . In addition, the feature point MF may mean an obstacle-specific pattern or edge line in front of the reference point MR.

On the other hand, when the object is located at the boundary of the reference area, it can be confirmed that the reference point of the first camera 110 is covered. That is, when the object enters the reference area, it may mean that the reference point MF of the object is excluded from the first area Z1. From this point on, the moving distance DL of the vehicle can be calculated based on the inside of the wheel of the vehicle. Specifically, the moving distance of the vehicle may be determined by the following equation.

DL denotes a moving distance of the vehicle, t1 denotes a time at which the object reached the reference region, and t2 denotes a time when a feature point of the object deviates from the first region, as will be described later.

Meanwhile, at a time point M3 when the object is included in the reference area and the feature point of the object leaves the first area Z1, the controller may calculate the height MH and the distance ML of the object.

The height of the object may be determined by Equation 2 below.

Referring to Equation 2, MH is the height of the object, DL is the moving distance of the vehicle, VL is the installation height of the first camera, and RL is the distance from the front of the vehicle to the reference area.

VL and RL may be predetermined.

Meanwhile, as shown in Equation 2, the height of the object may be determined by applying the ratio of the distance of the reference area with respect to the vehicle to the moving distance of the vehicle to the height of the vehicle, as shown in Equation 2 above.

Meanwhile, in this case, the distance ML between the vehicle and the obstacle may be determined by excluding the moving distance DL of the vehicle from the distance RL from the vehicle to the reference area.

Meanwhile, when the height of the object exceeds a predetermined height and it is determined as an obstacle, the controller may control the vehicle to be braked in consideration of the distance ML between the object and the vehicle.

On the other hand, when the height of the object is less than a predetermined height and is a specific pattern of a road or a structure such as a bump, the controller may control the vehicle to run without braking.

On the other hand, the operation described in FIGS. 2A and 2B is an operation of determining the height of an object by using the first camera and the second camera, despite an embodiment of determining the height of the object in the present invention, there is no limitation on the operation. .

3A to 3D are diagrams illustrating examples of objects according to an embodiment of the present invention.

Specifically, Fig. 3a shows a stopper used for parking a vehicle, Fig. 3b shows a parking pole, Fig. 3c shows a speed bump, and Fig. 3d shows a crosswalk.

The controller may acquire the reference point MR and the feature point MF.

Meanwhile, when the object has an edge component perpendicular to the ground, such as a stopper or a parking pillar, the controller may determine the object as an obstacle. On the other hand, even if the reference point and feature point of the object exist, if there is no edge component perpendicular to the ground, such as a speed bump or a crosswalk, the controller may not determine the object as an obstacle.

In addition, the control unit detects a reference point and a feature point for each front obstacle, and it is possible to calculate the obstacle distance when the intersection or orthogonal point of the feature line enters the inside of the hood line. Since a detailed description related to this has been described above, a detailed description thereof will be omitted.

In addition, low obstacles that the controller must distinguish in the image acquired from the camera have short vertical components, so various obstacles can be recognized through learning.

On the other hand, the obstacles shown in FIGS. 3A to 3D are merely an example for explaining the operation of the present invention, and there is no limitation on the type of obstacle for which the controller determines the height.

4A to 4C are diagrams illustrating a relationship between a region of interest (ZI) and an object according to an exemplary embodiment.

4A to 4C , FIG. 4A shows a case in which a straight obstacle is positioned, FIG. 4B shows a case in which an oblique obstacle is positioned, and FIG. 4C shows a case in which an external obstacle is positioned.

The aforementioned reference region ZR is a region determined by the angles of view of the first camera 110 and the second camera 120, and according to an embodiment, the distance from the vehicle to the reference region ZR is 3.0 m to 3.5 m. m can be determined. Meanwhile, the controller may determine the region of interest ZI from the reference region for efficient operation. When the object is included in the ROI ZI, the controller may determine whether to brake the vehicle by determining the height of the object and the distance between the vehicle and the object.

Meanwhile, it is shown that the object of FIG. 4B is positioned in an oblique line of the ROI ZI. In this case, the controller may determine the height of the obstacle based on a feature point of an object close to the vehicle in the region of interest ZI.

However, when the object is included in the reference region but not in the region of interest as shown in FIG. 4C , the presence of the object does not become a problem for the vehicle to proceed, so the controller may not determine the height of the object for optimization of calculation. .

Meanwhile, the operation of the present invention described with reference to FIGS. 4A to 4C is only an exemplary embodiment for explaining the region of interest, and there is no limitation on the shape of the region of interest or the positional relationship between the region of interest and the object.

5 is a flowchart according to an embodiment.

Referring to FIG. 5 , when the vehicle is driven ( 1001 ), the first camera and the second camera may acquire images ( 1002 ). Meanwhile, when the object is outside the reference area, the controller may track the object ( 1003 ). If the vehicle continues to move and the object is included in the reference area ( 1004 ), the controller may determine the height of the object ( 1005 ). When the height of the object exceeds a predetermined value and it is difficult for the vehicle to pass, the vehicle may perform braking control ( 1006 ). However, if the height of the object is less than a predetermined reference value, the vehicle may continue to drive ( 1001 ). As described above, this is also the case when the feature points of the object do not form an edge.

Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing instructions executable by a computer. Instructions may be stored in the form of program code, and when executed by a processor, may generate program modules to perform operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

The computer-readable recording medium includes any type of recording medium in which instructions readable by the computer are stored. For example, there may be a read only memory (ROM), a random access memory (RAM), a magnetic tape, a magnetic disk, a flash memory, an optical data storage device, and the like.

The disclosed embodiments have been described with reference to the accompanying drawings as described above. Those of ordinary skill in the art to which the present invention pertains, without changing the technical spirit or essential features of the present invention, have different forms from the disclosed embodiments. It will be understood that the present invention may be practiced with The disclosed embodiments are illustrative and should not be construed as limiting.

1: vehicle
110: first camera
120: second camera
200: control unit
300: brake

Claims (20)

a first camera for acquiring an image of a first area around the vehicle;
a second camera provided at a location different from that of the first camera and configured to acquire an image of a second area around the vehicle; and
at least two points of the object are identified based on the image of the object acquired by the first camera and the second camera;
determining a reference area based on the viewing angle of the first camera;
When the object is included in the reference area,
and a controller configured to determine whether to brake the vehicle based on the height of the object determined based on the image of the first region and the image of the second region.
According to claim 1,
At least two points on the object,
a reference point at which the object is in contact with the road; and
and a feature point corresponding to the highest point of the object determined based on the image of the first area and the image of the second area.
3. The method of claim 2,
The control unit is
If the reference point and the feature point are not included in the reference region,
The vehicle tracks the reference point and the feature point based on the image of the first area and the image of the second area.
3. The method of claim 2,
The control unit is
a vehicle for calculating a moving distance of the vehicle from a point in time when the reference point is excluded from the first region.
5. The method of claim 4,
The control unit is
A vehicle for determining a height of the object based on a moving distance of the vehicle, a height of the vehicle, and the reference area from a point in time when the feature point is excluded from the first area.
6. The method of claim 5,
The control unit is
A vehicle for determining the height of the object by applying a ratio of a distance of the reference area with respect to the vehicle to a moving distance of the vehicle to the height of the vehicle.
3. The method of claim 2,
The control unit is
By determining whether the feature point is at least one point on a straight line perpendicular to the ground,
A vehicle that determines whether the object is an obstacle.
According to claim 1,
The control unit is
determining a region of interest (ROI) included in the reference region;
When the object is included in the region of interest,
A vehicle that determines the height of the object.
According to claim 1,
The first camera is provided as a windshield camera,
The second camera is a vehicle provided as a Surround View Monitor (SVM) camera provided in front of the vehicle.
According to claim 1,
The control unit is
If the height of the object exceeds a predetermined height,
A vehicle that brakes the vehicle based on a distance between the object and the vehicle.
The first camera acquires an image of a first area around the vehicle,
A second camera is provided in a position different from that of the first camera, and acquires an image of a second area around the vehicle,
at least two points of the object are identified based on the image of the object acquired by the first camera and the second camera;
determining a reference area based on the viewing angle of the first camera;
When the object is included in the reference area,
and determining whether to brake the vehicle based on the height of the object determined based on the image of the first area and the image of the second area.
12. The method of claim 11,
At least two points on the object,
a reference point where the object is in contact with the road; and
and a feature point corresponding to the highest point of the object determined based on the image of the first area and the image of the second area.
13. The method of claim 12,
Identifying at least two points of the object based on the image of the object acquired by the first camera and the second camera,
If the reference point and the feature point are not included in the reference region,
and tracking the reference point and the feature point based on the image of the first area and the image of the second area.
13. The method of claim 12,
Determining whether to brake the vehicle,
and calculating a moving distance of the vehicle from a point in time when the reference point is excluded from the first region.
15. The method of claim 14,
To determine the height of the object,
and determining the height of the object based on the moving distance of the vehicle, the height of the vehicle, and the reference area from a point in time when the feature point is excluded from the first area.
16. The method of claim 15,
To determine the height of the object,
and determining the height of the object by applying a ratio of a distance of the reference area with respect to the vehicle to a moving distance of the vehicle to the height of the vehicle.
13. The method of claim 12,
By determining whether the feature point is at least one point on a straight line perpendicular to the ground,
The vehicle control method further comprising determining whether the object is an obstacle.
12. The method of claim 11,
determining a region of interest (ROI) included in the reference region;
When the object is included in the region of interest, the vehicle control method further comprising determining a height of the object.
12. The method of claim 11,
The first camera is provided as a windshield camera,
The second camera is a vehicle control method provided with an SVM camera provided in front of the vehicle.
12. The method of claim 11,
Determining whether to brake the vehicle,
If the height of the object exceeds a predetermined height,
and braking the vehicle based on a distance between the object and the vehicle.

Images