A Combined Approach to Single-Camera-Based Lane Detection in Driverless Navigation

Xin Zhang, Maolin Chen, Xingqun Zhan

Abstract: A combined approach is presented with real-world examples to illustrate how to detect lane lines under several road conditions in driverless navigation. This approach is designed for single-camera perception and is achieved using camera calibration, un-distortion, color thresholding, perspective transformation, pixel identification and ployfitting. Limiting factors such as illumination and radius of curvature of the testing road is considered. The results show that the method is effective in normal conditions but needs further improvement in extremely challenging environments.
Published in: 2018 IEEE/ION Position, Location and Navigation Symposium (PLANS)
April 23 - 26, 2018
Hyatt Regency Hotel
Monterey, CA
Pages: 1042 - 1046
Cite this article: Zhang, Xin, Chen, Maolin, Zhan, Xingqun, "A Combined Approach to Single-Camera-Based Lane Detection in Driverless Navigation," 2018 IEEE/ION Position, Location and Navigation Symposium (PLANS), Monterey, CA, April 2018, pp. 1042-1046.
Full Paper: ION Members/Non-Members: 1 Download Credit
Sign In