Automatic Detection and Tracking of Pedestrians from a Moving Stereo Rig

Konrad Schindler, Andreas Ess, Bastian Leibe, Luc Van Gool
International Journal of Photogrammetry and Remote Sensing, Vol. 65(6), pp. 523-537 (ISPRS'2010)

We report on a stereo system for 3D detection and tracking of pedestrians in urban traffic scenes. The system is built around a probabilistic environment model which fuses evidence from dense 3D reconstruction and image-based pedestrian detection into a consistent interpretation of the observed scene, and a multi-hypothesis tracker to reconstruct the pedestrians’ trajectories in 3D coordinates over time. Experiments on real stereo sequences recorded in busy inner-city scenarios are presented, in which the system achieves promising results.

» Show BibTeX

@article{schindler2010automatic,
title={Automatic detection and tracking of pedestrians from a moving stereo rig},
author={Schindler, Konrad and Ess, Andreas and Leibe, Bastian and Van Gool, Luc},
journal={ISPRS Journal of Photogrammetry and Remote Sensing},
volume={65},
number={6},
pages={523--537},
year={2010},
}




Disclaimer Home Visual Computing institute RWTH Aachen University