Vehicle and Lane Mark Detection Device

• US 20090167864A1
• Filed: 11/14/2006
• Published: 07/02/2009
• Est. Priority Date: 12/28/2005
• Status: Active Grant

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Unoura, Kiyozumi
• Granted Patent: US 8,208,021 B2
• Time in Patent Office: Days
• US Class Current: 348/148
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2420/42 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 30/12 Lane keeping
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20061 Hough transform
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

A vehicle includes: an image acquisition means (4) which acquires a road image via an imaging means (3); an edge extraction means (5) which extracts edge points from the acquired image; a line search means (6) which searches the extracted edge points for line components; an evaluation value calculation means (7) which calculates an evaluation value indicating the degree that each line component approximates a linear lane mark on the road for the line components searched for; a lane mark candidate selection means (8) which selects line components each having an evaluation value greater than a predetermined threshold value as candidates for a line component corresponding to the lane mark from the line components searched for; and a lane mark detection means (9) which detects the lane mark by determining the line component corresponding to the lane mark from the selected candidates for the line component. This allows the detection accuracy to be increased by preventing an object other than a lane mark on the road from being incorrectly detected as a linear lane mark such as a white line when detecting a linear lane mark such as a white line from the road image.

Claims

1. A vehicle comprising:

an imaging means;

an image acquisition means which acquires an image of a road via the imaging means;

an edge extraction means which extracts edge points by performing edge extraction for the image acquired by the image acquisition means;

a line search means which searches the edge points extracted by the edge extraction means for line components each of which is point sequence data of a plurality of linearly located edge points;

an evaluation value calculation means which calculates an evaluation value indicating the degree that each line component approximates a linear lane mark on the road for the line components searched for by the line search means;

a lane mark candidate selection means which selects line components each having an evaluation value or a value obtained by filtering the time series of the evaluation value greater than a predetermined threshold value as candidates for a line component corresponding to the lane mark from the line components searched for by the line search means; and

a lane mark detection means which detects the lane mark by determining the line component corresponding to the lane mark from the candidates for the line component selected by the lane mark candidate selection means.

2. The vehicle according to claim 1, wherein the evaluation value calculation means calculates the evaluation value by using a ratio between the number of edge points constituting the line component and the number of continuous edge points among the edge points.

3. The vehicle according to claim 2, wherein the evaluation value calculation means calculates the evaluation value by performing correction based on a distance between the position of the line component in the real space and the vehicle for the ratio between the number of edge points constituting the line component and the number of continuous edge points among the edge points.

4. The vehicle according to claim 3, wherein the evaluation value calculation means performs the correction by multiplying the ratio between the number of edge points constituting the line component and the number of continuous edge points among the edge points by a correction factor set so as to decrease as the distance between the position of the line component in the real space and the vehicle increases.

5. The vehicle according to claim 4, wherein the evaluation value calculation means sets the correction factor to a predetermined upper limit in the case where the distance between the position of the line component in the real space and the vehicle is less than a first predetermined distance.

6. The vehicle according to claim 4, wherein the evaluation value calculation means sets the correction factor to a predetermined lower limit in the case where the distance between the position of the line component in the real space and the vehicle is greater than a second predetermined distance.

7. The vehicle according to claim 5, wherein the evaluation value calculation means sets the correction factor to a predetermined lower limit in the case where the distance between the position of the line component in the real space and the vehicle is greater than the second predetermined distance.

8. The vehicle according to claim 1, wherein the lane mark candidate selection means includes a means which specifies a range corresponding to an area apart from the vehicle by a predetermined distance or more in the real space within the image and a means which sets the threshold value for selecting a line component included in the range to a greater value than the threshold value for selecting a line component not included in the range.

9. A lane mark detection device comprising:

an image acquisition means which acquires an image of a road via an imaging means mounted on a vehicle;

an edge extraction means which extracts edge points by performing edge extraction for the image acquired by the image acquisition means;

a line search means which searches the edge points extracted by the edge extraction means for line components each of which is point sequence data of a plurality of linearly located edge points;

an evaluation value calculation means which calculates an evaluation value indicating the degree that each line component approximates a linear lane mark on the road for the line components searched for by the line search means;

a lane mark candidate selection means which selects line components each having an evaluation value or a value obtained by filtering the time series of the evaluation value greater than a predetermined threshold value as candidates for a line component corresponding to the lane mark from the line components searched for by the line search means; and

a lane mark detection means which detects the lane mark by determining the line component corresponding to the lane mark from the candidates for the line component selected by the lane mark candidate selection means.

10. The lane mark detection device according to claim 9, wherein the evaluation value calculation means calculates the evaluation value by using a ratio between the number of edge points constituting the line component and the number of continuous edge points among the edge points.

11. The lane mark detection device according to claim 10, wherein the evaluation value calculation means calculates the evaluation value by performing correction based on a distance between the position of the line component in the real space and the vehicle for the ratio between the number of edge points constituting the line component and the number of continuous edge points among the edge points.

12. The lane mark detection device according to claim 11, wherein the evaluation value calculation means performs the correction by multiplying the ratio between the number of edge points constituting the line component and the number of continuous edge points among the edge points by a correction factor set so as to decrease as the distance between the position of the line component in the real space and the vehicle increases.

13. The lane mark detection device according to claim 12, wherein the evaluation value calculation means sets the correction factor to a predetermined upper limit in the case where the distance between the position of the line component in the real space and the vehicle is less than a first predetermined distance.

14. The lane mark detection device according to claim 12, wherein the evaluation value calculation means sets the correction factor to a predetermined lower limit in the case where the distance between the position of the line component in the real space and the vehicle is greater than a second predetermined distance.

15. The lane mark detection device according to claim 13, wherein the evaluation value calculation means sets the correction factor to a predetermined lower limit in the case where the distance between the position of the line component in the real space and the vehicle is greater than the second predetermined distance.

16. The lane mark detection device according to claim 9, wherein the lane mark candidate selection means includes a means which specifies a range corresponding to an area apart from the vehicle by a predetermined distance or more in the real space within the image and a means which sets the threshold value for selecting a line component included in the range to a greater value than the threshold value for selecting a line component not included in the range.