Abstract
Road detection is the basic component of many intelligent vehicle systems. In this paper, a robust multi-lane detection method based on binocular vision is proposed. First, a fast estimation technique of the Stixel World, which is the outside environment representation of stereo-vision, is developed. Taking advantage of the estimate for free space under the plane road hypothesis, the proposed method is robust against on-road obstacles when detecting lane markings. Then, the bird-view of the transitable area is obtained through Inverse Perspective Mapping (IPM) Transform; Steerable filter, parallel parabolas modal and RANdom SAmple Consensus (RANSAC) technique are introduced for multi-lane fitting. Experimental results in real urban driving situations indicate that our algorithm is robust under various conditions.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
