REAL-TIME LANE DETECTION FOR AUTONOMOUS VEHICLE
This paper describes two search ranges for detecting a lane in a road. The searching mode searches the lane with out any prior information. The recognition mode reduces the size and changes the position of a searching range by predicting lane position. It can also extract the edge candidate points of a lane without any unneeded searching. Additional steps include transform the edge candidate information into a plane-view image, defining a linear approximation filter, and removing faulty edge candidate points. The lane of an actual road is approximated by applying a least-mean square method with the fault- removed edge information for curve fitting.
-
Supplemental Notes:
- Publication Date: 2001. IEEE Service Center, Piscataway NJ
-
Corporate Authors:
Kungmin Taehakkyo (Korea)
,Pusan Taehakkyo
,Tonga Taehakkyo
,Kyungnam Taehakkyo
, -
Authors:
- Jeong, Seun Gweon
- Kim, Chang Sup
- Lee, Dong Youp
- Ha, Sung Ki
-
Conference:
- IEEE International Symposium on Industrial Electronics (2001). ISIE 2001 : proceedings
- Location: Pusan Korea
- Publication Date: 2001
Language
- English
Media Info
- Pagination: p. 1466-1471
-
Serial:
- Volume: 3
Subject/Index Terms
- TRT Terms: Advanced vehicle control systems; Image processing; Road markings
- Subject Areas: Operations and Traffic Management;
Filing Info
- Accession Number: 00926720
- Record Type: Publication
- Source Agency: UC Berkeley Transportation Library
- Files: PATH
- Created Date: Jul 3 2002 12:00AM