Abstract
Pedestrian protection is a crucial component of driver assistance systems. Considering all the available cues for predicting the possibility of collision is very important. The direction in which the pedestrian is facing is one of the most important cues predicting where the pedestrian may move in future. In this paper, we address the problem of single-frame pedestrian orientation estimation in real-world scenes with a single camera from a moving vehicle. We present a novel approach to determine the pedestrian' orientations using cascade orientation estimation, by exploiting the head orientation by a multi-Bayesian model.
Experiments on a large amount of real-world data show a significant performance improvement in octant orientation estimation of about 64% accuracy by head orientation consideration, compared to one vs. one and one vs. all multi-class classification methods.
