Lane recognition apparatus for vehicle

• US 20020042668A1
• Filed: 09/14/2001
• Published: 04/11/2002
• Est. Priority Date: 10/02/2000
• Status: Active Grant

• Current Assignee: Nissan Motor Co., Ltd.
• Original Assignee: Nissan Motor Co., Ltd.
• Inventors: Mouri, Hiroshi, Shirato, Ryota
• Granted Patent: US 6,823,241 B2
• Time in Patent Office: Days
• US Class Current: 701/1
• CPC Class Codes: B60T 2201/08 Lane monitoring; Lane Keeping Systems
• CPC Class Codes: B60T 2201/089 using optical detection
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 10/443 by matching or filtering
• 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 lane recognition apparatus for a vehicle is comprised of an image picking-up section which picks up a road image in front of the vehicle, a lane-marker candidate-point detecting section which detects coordinate values of a plurality of lane marker candidate points from the road image, and a road model parameter calculating section which estimates a road model parameter representative of a road shape in front of the vehicle and a vehicle state quantity of the vehicle using an extended Kalman filter, on the basis of the coordinate values of the lane marker candidate points.

Claims

1. A lane recognition apparatus for a vehicle, comprising:

an image picking-up section picking up a road image in front of the vehicle;

a lane-marker candidate-point detecting section detecting coordinate values of a plurality of lane marker candidate points from the road image; and

a road model parameter calculating section estimating a road model parameter representative of a road shape in front of the vehicle and a vehicle state quantity of the vehicle using an extended Kalman filter, on the basis of the coordinate values of the lane marker candidate points.

2. The lane recognition apparatus as claimed in claim 1, wherein the vehicle state quantity and the road model parameter comprises a lateral displacement of the vehicle with respect to a lane maker, a road curvature of a road to be traveled, a yaw angle of the vehicle with respect to the lane marker, a pitch angle of the vehicle, and a height of the image picking-up section above a ground.

3. The lane recognition apparatus as claimed in claim 1, wherein the vehicle state quantity and the road model parameter comprises a lateral displacement of the vehicle with respect to a lane maker, a road curvature of a road to be traveled, a yaw angle of the vehicle with respect to the lane marker, a pitch angle of the vehicle and a lane width of the road.

4. The lane recognition apparatus as claimed in claim 1, further comprising a steering angle detecting section which detects a steering angle of the vehicle, wherein a state equation of the extended Kalman filter uses a change of the vehicle state quantity caused by the steering angle and a vehicle speed.

5. The lane recognition apparatus as claimed in claim 1, wherein a state equation of the extended Kalman filter is defined as a random walk model in a discrete system.

6. The lane recognition apparatus as claimed in claim 1, wherein a state equation of the extended Kalman filter is represented as a first-order lag in a continuous system.

7. The lane recognition apparatus as claimed in claim 4, wherein the road model parameter calculating section estimates the state quantity of disturbance so as to maintain preferable properties of following up a quick behavior of the vehicle at the input of the steering angle.

8. The lane recognition apparatus as claimed in claim 4, wherein the road model parameter estimates the state quantity of disturbance so as to prevent the steering angle from generating an error.

9. A lane recognition apparatus for a vehicle, comprising:

a camera picking up a road image in front of the vehicle; and

a processor coupled to the camera, the processor being arranged,

to calculate coordinate values of a plurality of lane marker candidate points from the road image,

to estimate a road model parameter representative of a road shape in front of the vehicle and a vehicle state quantity from an extended Kalman filter and the coordinate values of the lane marker candidate points.

10. A method for recognizing a lane in front of a vehicle, comprising:

picking up a road image in front of the vehicle;

calculating coordinate values of a plurality of candidate points of a lane marker from the road image; and

estimating a road model parameter representative of a road shape in front of the vehicle and a vehicle state quantity from an extended Kalman filter and the coordinate values of the lane marker candidate points.

11. A lane recognition apparatus for a vehicle, comprising:

image picking-up means for picking up a road image in front of the vehicle;

lane-marker candidate-point detecting means for detecting coordinate values of a plurality of lane marker candidate points from the road image; and

road model parameter calculating means for estimating a road model parameter representative of a road shape in front of the vehicle and a vehicle state quantity of the vehicle using an extended Kalman filter, on the basis of the coordinate values of the lane marker candidate points.