Dense stereo matching in restricted disparity space
- 1 January 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19310587,p. 118-123
- https://doi.org/10.1109/ivs.2005.1505088
Abstract
We propose a new domain-specific area-based stereo method that is applicable to various tasks including safe navigation and pedestrian detection. Incorporating a spatial restriction in the height direction of road scenes into the recursive computation of correlation measures, the proposed method efficiently provides dense disparity measures. A pair of cameras just has to be weakly calibrated due to the non-metric formulation. We also implement our stereo method on a newly developed onboard LSI, which has a dedicated architecture for practical automotive use and realizes more than BOM disparity estimations per second. Furthermore, we apply our method to a side collision warning system, which detects approaching objects such as pedestrians and bicycles. Through experiments we demonstrate the efficiency of our stereo method in road environments.Keywords
This publication has 9 references indexed in Scilit:
- Rectifying transformations that minimize resampling effectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Visconti: multi-VLIW image recognition processor based on configurable processor [obstacle detection applications]Published by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- A practical stereo scheme for obstacle detection in automotive usePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Fast variable window for stereo correspondence using integral imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Obstacle detection using projective invariant and vanishing linesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- An integrated stereo-based approach to automatic vehicle guidancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Stereo without depth search and metric calibrationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence AlgorithmsInternational Journal of Computer Vision, 2002
- Fast Stereo Matching Using Rectangular Subregioning and 3D Maximum-Surface TechniquesInternational Journal of Computer Vision, 2002