Citation

Keller CG, Enzweiler M, Rohrbach M, Llorca DF, Schnorr C, Gavrila DM. IEEE Trans. Intel. Transp. Syst. 2011; 12(4): 1096-1106.

Copyright

(Copyright © 2011, IEEE (Institute of Electrical and Electronics Engineers))

DOI

10.1109/TITS.2011.2143410

PMID

unavailable

Abstract

This paper presents a novel pedestrian detection sys- tem for intelligent vehicles. We propose the use of dense stereo for both the generation of regions of interest and pedestrian classi- fication. Dense stereo allows the dynamic estimation of camera parameters and the road profile, which, in turn, provides strong scene constraints on possible pedestrian locations. For classifica- tion, we extract spatial features (gradient orientation histograms) directly from dense depth and intensity images. Both modalities are represented in terms of individual feature spaces, in which discriminative classifiers (linear support vector machines) are learned. We refrain from the construction of a joint feature space but instead employ a fusion of depth and intensity on the classifier level. Our experiments involve challenging image data captured in complex urban environments (i.e., undulating roads and speed bumps). Our results show a performance improvement by up to a factor of 7.5 at the classification level and up to a factor of 5 at the tracking level (reduction in false alarms at constant detection rates) over a system with static scene constraints and intensity-only classification.