A template matching and ellipse modeling approach to detecting lane markers
2010 (English)In: Advanced Concepts for Intelligent Vision Systems: 12th International Conference, ACIVS 2010, Sydney, Australia, December 13-16, 2010, Proceedings, Part II, Springer, 2010, no PART 2, 179-190 p.Conference paper (Refereed)
Lane detection is an important element of most driver assistance applications. A new lane detection technique that is able to withstand some of the common issues like illumination changes, surface irregularities, scattered shadows, and presence of neighboring vehicles is presented in this paper. At first, inverse perspective mapping and color space conversion is performed on the input image. Then, the images are cross-correlated with a collection of predefined templates to find candidate lane regions. These regions then undergo connected components analysis, morphological operations, and elliptical projections to approximate positions of the lane markers. The implementation of the Kalman filter enables tracking lane markers on curved roads while RANSAC helps improve estimates by eliminating outliers. Finally, a new method for calculating errors between the detected lane markers and ground truth is presented. The developed system showed good performance when tested with real-world driving videos containing variations in illumination, road surface, and traffic conditions.
Place, publisher, year, edition, pages
Springer, 2010. no PART 2, 179-190 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 6475
Advanced Vehicle Safety Systems, Driver Assistance Systems, Lane Detection and Lane Keeping, Template Matching, Color space conversion, Connected component, Driver assistance, Driver assistance system, Ground truth, Illumination changes, Input image, Inverse perspective mappings, Lane detection, Lane marker, Modeling approach, Morphological operations, Real-world, Road surfaces, Surface irregularities, Traffic conditions, Astatine, Automobile drivers, Computer vision, Image enhancement, Mathematical morphology, Roads and streets, Security systems, Image matching
Other Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-150025DOI: 10.1007/978-3-642-17691-3_17ISI: 000287941500017ScopusID: 2-s2.0-78650854637ISBN: 3642176909ISBN: 978-3-642-17690-6OAI: oai:DiVA.org:kth-150025DiVA: diva2:742279
12th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2010; Sydney, NSW; Australia; 13 December 2010 through 16 December 2010
QC 201409012014-09-012014-08-292014-09-01Bibliographically approved