Adaptive Contour Features in Oriented Granular Space for Human Detection and Segmentation

In this paper, a novel feature named Adaptive Contour Feature (ACF) is proposed for human detection and segmentation. This feature consists of a chain of a number of granules in Oriented Granular Space (OGS) that is learnt via the AdaBoost algorithm. Three operations are defined on the OGS to mine object contour feature and feature cooccurrences automatically. A heuristic learning algorithm is proposed to generate an ACF that at the same time define a weak classifier for human detection or segmentation. Experiments on two open datasets show that the ACF outperform several well-known existing features due to its stronger discriminative power rooted in the nature of its flexibility and adaptability to describe an object contour element.

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Wei Gao (Tsinghua University), Haizhou Ai (Tsinghua University), Shihong Lao (Omron Corporation)
• Keywords: Adaptive Contour Features, Computer Vision, CVPR 2009, Human Detection, Human Segmentation