22 June 2015 Stereo sequences analysis for dynamic scene understanding in a driver assistance system
Author Affiliations +
Abstract
The improved stereo-based approach for dynamic road scene understanding in a Driver Assistance System (DAS) is presented. System calibration is addressed. Algorithms for road lane detection, road 3D model generation, obstacle predetection and object (vehicle) detection are described. Lane detection is based on the evidence analysis. Obstacle predetection procedure performs the comparison of radial ortophotos, obtained by left and right stereo images. Object detection algorithm is based on recognition of back part of cars by histograms of oriented gradients. Car Stereo Sequences (CSS) Dataset captured by vehicle-based laboratory and published for DAS algorithms testing.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Boris V. Vishnyakov, Boris V. Vishnyakov, Yuri V. Vizilter, Yuri V. Vizilter, Vladimir A. Knyaz, Vladimir A. Knyaz, Ivan K. Malin, Ivan K. Malin, Oleg V. Vygolov, Oleg V. Vygolov, Sergey Y. Zheltov, Sergey Y. Zheltov, } "Stereo sequences analysis for dynamic scene understanding in a driver assistance system", Proc. SPIE 9530, Automated Visual Inspection and Machine Vision, 95300P (22 June 2015); doi: 10.1117/12.2184849; https://doi.org/10.1117/12.2184849
PROCEEDINGS
9 PAGES


SHARE
RELATED CONTENT


Back to Top