Dynamic programming and curve fitting based road boundary detection

Authors:
Shyam Prasad Adhikari;Hyongsuk Kim
Affiliations:
Division of Electronics and Information Engineering, Chonbuk National University, Jeonju-City, Jeonbuk, South-Korea;Division of Electronics and Information Engineering, Chonbuk National University, Jeonju-City, Jeonbuk, South-Korea
Venue:
CIMMACS '10 Proceedings of the 9th WSEAS international conference on computational intelligence, man-machine systems and cybernetics
Year:
2010

Citing 4
Cited 0

Lane detection using spline model

Pattern Recognition Letters
Road lane segmentation using dynamic programming for active safety vehicles

Pattern Recognition Letters
A Synchronous Detection of the Road Boundary and Lane Marking for Intelligent Vehicles

SNPD '07 Proceedings of the Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing - Volume 01
Road Boundary Detection Based on the Dynamic Programming and the Randomized Hough Transform

ISITC '07 Proceedings of the 2007 International Symposium on Information Technology Convergence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a vision based road boundary detection based on the combination of dynamic programming and 2nd order polynomial approximation. The initial estimate of the most likely road boundaries are obtained by a modified dynamic programming on a cost field defined on the edge image. A second order polynomial is fit to the initial coarse estimate of road boundaries to obtain a refined estimate of the road boundaries. The second order approximation of the road boundaries allows the estimation of the curved segments in addition to the straight segments of the road boundaries. Experiment results for road images taken under various non-ideal scenarios with shadow, unmarked lane segments and curvatures are presented.