Title :
A robust lane detection and departure warning system
Author :
Haloi, Mrinal ; Jayagopi, Dinesh Babu
Author_Institution :
Dept. Electron. & Commun. Enginering, IIT Guwahati, Guwahati, India
fDate :
June 28 2015-July 1 2015
Abstract :
In this work, we have developed a robust lane detection and departure warning technique. Our system is based on single camera sensor. For lane detection a modified Inverse Perspective Mapping using only a few extrinsic camera parameters and illuminant Invariant techniques is used. Lane markings are represented using a combination of 2nd and 4th order steerable filters, robust to shadowing. Effect of shadowing and extra sun light are removed using Lab color space, and illuminant invariant representation. Lanes are assumed to be cubic curves and fitted using robust RANSAC. This method can reliably detect lanes of the road and its boundary. This method has been experimented in Indian road conditions under different challenging situations and the result obtained were very good. For lane departure angle an optical flow based method were used.
Keywords :
alarm systems; cameras; image colour analysis; object detection; traffic engineering computing; Lab color space; RANSAC; departure warning system; illuminant invariant representation; illuminant invariant techniques; lane markings; modified inverse perspective mapping; robust lane detection; single camera sensor; steerable filters; Alarm systems; Cameras; Feature extraction; Optical imaging; Roads; Robustness; Vehicles;
Conference_Titel :
Intelligent Vehicles Symposium (IV), 2015 IEEE
Conference_Location :
Seoul
DOI :
10.1109/IVS.2015.7225674