General Road Detection From a Single Image

• Published in: IEEE transactions on image processing Vol. 19; no. 8; pp. 2211 - 2220
• Main Authors: Hui Kong, Audibert, Jean-Yves, Ponce, Jean
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.08.2010; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied sciences; Boundaries; Color; Computer Science; Computer Vision and Pattern Recognition; Detection algorithms; Detection, estimation, filtering, equalization, prediction; Distributed computing; Dominant edge detection; Exact sciences and technology; Gabor filters; Image edge detection; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image processing; Image segmentation; Information, signal and communications theory; Optical character recognition software; Pattern recognition; Pattern Recognition, Automated - methods; Pixel; Remotely operated vehicles; Reproducibility of Results; road detection; Roads; Segmentation; Sensitivity and Specificity; Signal and communications theory; Signal processing; Signal, noise; soft voting; Surface layer; Telecommunications and information theory; Texture; Transportation; vanishing point detection; Voting; Gabor filter; Dominant edge detection; Segmentation; road detection; soft voting; Shape detection; Adaptive method; Texture; vanishing point detection; Implementation; Voting; A priori estimation; Edge detection; dominant edge detection
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2010.2045715

Given a single image of an arbitrary road, that may not be well-paved, or have clearly delineated edges, or some a priori known color or texture distribution, is it possible for a computer to find this road? This paper addresses this question by decomposing the road detection process into two steps: the estimation of the vanishing point associated with the main (straight) part of the road, followed by the segmentation of the corresponding road area based upon the detected vanishing point. The main technical contributions of the proposed approach are a novel adaptive soft voting scheme based upon a local voting region using high-confidence voters, whose texture orientations are computed using Gabor filters, and a new vanishing-point-constrained edge detection technique for detecting road boundaries. The proposed method has been implemented, and experiments with 1003 general road images demonstrate that it is effective at detecting road regions in challenging conditions.