We propose a multi-layer, real-time vehicle detection and tracking system using stereo vision, multi-view AdaBoost detectors, and optical flow. By adopting a ground plane estimate extracted from stereo information, we generate a sparse set of hypotheses and apply trained AdaBoost classifiers in addition to fast disparity histogramming, for Hypothesis Verification (HV) purposes. Our tracking system employs one Kalman filter per detected vehicle and motion vectors from optical flow, as a means to increase its robustness. An acceptable detection rate with few false positives is obtained at 25 fps with generic hardware.
Real-time vehicle detection and tracking using stereo vision and multi-view AdaBoost
2011-10-01
1106365 byte
Conference paper
Electronic Resource
English
Video-based, real-time multi-view stereo
British Library Online Contents | 2011
|Performance Improvement of Vehicle Tracking Using Parts Features Adaboost
Springer Verlag | 2013
|Stereo Vision-based Vehicle Detection
British Library Conference Proceedings | 2000
|Stereo vision-based vehicle detection
IEEE | 2000
|Stereo vision based vehicle detection
Tema Archive | 2010
|