Lane boundary detector

• US 20050270374A1
• Filed: 05/24/2005
• Published: 12/08/2005
• Est. Priority Date: 06/02/2004
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Inventors: Nishida, Makoto, Watanabe, Akihiro
• Granted Patent: US 7,808,523 B2
• Time in Patent Office: Days
• US Class Current: 348/148
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• 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 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• 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

Abstract

A boundary detector includes a candidate line detecting unit that detects a candidate line of a lane boundary position drawn on a road surface based on image data of a predetermined detection time period acquired from a camera. The detector also includes a lane boundary position selecting unit that selects a lane boundary position based on the candidate line; a branch lane boundary position selecting unit that selects a lane boundary position of a branch lane that diverts from a main lane based on the candidate line; and a branch processing unit that sets a branch process mode in which the detection time period is short without using the selected lane boundary position of the branch lane when the branch lane boundary position selecting unit selects the lane boundary position of the branch lane.

Claims

1. A boundary detector comprising:

a camera that is mounted on a vehicle and picks up an image of a road surface;

a candidate line detecting unit that detects a candidate line of a lane boundary position drawn on the road surface based on image data of a predetermined detection time period acquired from the image supplied from the camera;

a lane boundary position selecting unit that selects a lane boundary position based on the candidate line of the lane boundary position detected by the candidate line detecting unit;

a branch lane boundary position selecting unit that selects a lane boundary position of a branch lane that diverts from a main lane based on the candidate line of the lane boundary position detected by the candidate line detecting unit; and

a branch processing unit that sets a branch process mode in which the detection time period is short without adopting the selected lane boundary position of the branch lane when the branch lane boundary position selecting unit selects the lane boundary position of the branch lane.

2. The boundary detector according to claim 1, wherein the branch processing unit adopts a lane boundary position which is selected before the currently selected lane boundary position of the branch lane when the branch lane boundary position selecting unit selects the lane boundary position of the branch lane.

3. The boundary detector according to claim 1, wherein the branch lane boundary position selecting unit recognizes the detected lane boundary position as the lane boundary position of the branch lane when one of a curvature and a pitch angle of the road calculated based on the lane boundary position are larger than predetermined values.

4. The boundary detector according to claim 1, wherein

the candidate line detecting unit detects a candidate line of the lane boundary position based on a number of pieces of data of a candidate line which is continuously detected in a predetermined detection time, and

the branch processing unit sets a shorter detection time in the branch process mode.

5. The boundary detector according to claim 1, wherein the candidate line detecting unit detects a candidate line of the lane boundary position based on a predetermined number of pieces of data of a candidate line, and

the branch processing unit sets a smaller number of pieces of data of the candidate line.

6. The boundary detector according to claim 1, wherein the branch processing unit cancels the branch process mode when one of the short detection time period and a predetermined branch mode cancel time period elapses after the branch process mode is set.

7. A boundary detecting method comprising:

detecting a candidate line of a lane boundary position drawn on a road surface based on image data of a predetermined detection time period acquired from an image supplied from a camera that is mounted on a vehicle and that picks up the image of the road surface;

selecting a lane boundary position based on the candidate line of the detected lane boundary position;

selecting a lane boundary position of a branch lane that diverts from a main lane based on the candidate line of the detected lane boundary position; and

setting a branch process mode in which the detection time period is short without adopting the selected lane boundary position of the branch lane when the lane boundary position of the branch lane is selected.

8. The boundary detecting method according to claim 7, wherein setting of the branch process mode includes adopting a lane boundary position which is selected before the currently selected lane boundary position of the branch lane when the lane boundary position of the branch lane is selected.

9. The boundary detecting method according to claim 7, wherein selecting of the lane boundary position of the branch lane includes recognizing the detected lane boundary position as the lane boundary position of the branch lane when one of a curvature and a pitch angle of the road calculated based on the lane boundary position are larger than predetermined values.

10. The boundary detecting method according to claim 7, wherein

detecting of the candidate line includes detecting a candidate line of the lane boundary position based on a number of pieces of data of a candidate line which is continuously detected in a predetermined detection time, and

setting of the branch process mode includes setting a shorter detection time in the branch process mode.

11. The boundary detecting method according to claim 7, wherein detecting of the lane boundary position includes detecting a candidate line of the lane boundary position based on a predetermined number of pieces of data of a candidate line, and

setting of the branch process includes setting a smaller number of pieces of data of the candidate line.

12. The boundary detecting method according to claim 7, wherein setting of the branch process includes canceling the branch process mode when one of the short detection time period and a predetermined branch mode cancel time period elapses after the branch process mode is set.