Image processing method for preventing lane deviation

• US 6,850,629 B2
• Filed: 11/26/2001
• Issued: 02/01/2005
• Est. Priority Date: 12/27/2000
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Original Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Inventors: Jeon, Yong-Won
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): Choobin, Barry
• Application Number:
  US09/991,738
• Publication Number:
  US 20020080235A1
• Time in Patent Office: 1,163 Days
• Field of Search: 382/104, 382/107, 382/168, 382/260, 382/272, 382/298, 377/9, 348/113, 348/116, 180/168, 340/934, 340/907, 701/41, 701/301
• US Class Current: 382/104
• CPC Class Codes: B60T 2201/08 Lane monitoring; Lane Keeping Systems
• CPC Class Codes: B60T 2201/089 using optical detection
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20068 Projection on vertical or horizontal image axis
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/64 of convexity or concavity
• CPC Class Codes: G06T 7/73 using feature-based methods

Abstract

An image processing method comprises the steps of generating a road image by photographing a road on which a vehicle is traveling; performing a brightness averaging process of the road image; filtering the road image having undergone the brightness averaging process to detect lane markers; performing an inverse perspective process on the filtered road image; compressing the road image having undergone the inverse perspective process; determining slope in the lane markers from the compressed road image; determining a curvature in the road from the determined slope in the lane markers; and determining a drive direction and a lane deviation of the vehicle.

Claims

1. An image processing method comprising the steps of:

generating a road image by photographing a road on which a vehicle is traveling;

performing a brightness averaging process of the road image;

filtering the road image having undergone the brightness averaging process to detect lane markers;

performing an inverse perspective process on the filtered road image;

compressing the road image having undergone the inverse perspective process in a vertical direction;

determining slope in the lane markers from the compressed road image;

determining a curvature in the road from the determined slope in the lane markers; and

determining a drive direction and a lateral lane deviation of the vehicle.

2. The method of claim 1 wherein the brightness averaging process is realized by exchanging a brightness of portions having a value less than an average brightness value of a photographed road image with the average brightness value.

3. The method of claim 1 further comprising the steps of:

determining vehicle speed and driver intentions; and

controlling steering of the vehicle based on vehicle speed, driver intentions, and an amount of lane deviation of the vehicle.