Summary: Y. Yagi et al. (Eds.): ACCV 2007, Part I, LNCS 4843, pp. 210219, 2007.
© Springer-Verlag Berlin Heidelberg 2007
Multiview Pedestrian Detection Based on Vector Boosting
, Haizhou Ai1
, and Shihong Lao2
Computer Science and Technology Department, Tsinghua University, Beijing 100084, China
Sensing and Control Technology Laboratory, Omron Corporation, Kyoto 619-0283, Japan
Abstract. In this paper, a multiview pedestrian detection method based on Vec-
tor Boosting algorithm is presented. The Extended Histograms of Oriented Gra-
dients (EHOG) features are formed via dominant orientations in which gradient
orientations are quantified into several angle scales that divide gradient orienta-
tion space into a number of dominant orientations. Blocks of combined rectan-
gles with their dominant orientations constitute the feature pool. The Vector
Boosting algorithm is used to learn a tree-structure detector for multiview
pedestrian detection based on EHOG features. Further a detector pyramid
framework over several pedestrian scales is proposed for better performance.