Feature Interaction Descriptor for Pedestrian Detection
Hui Ying Cao, Koichiro Yamaguchi, Mitsuhiko Ohta, Takashi Naito, Yoshiki Ninomiya · IEICE Transactions on Information and Systems · 2010
We propose a novel representation called Feature Interaction Descriptor (FIND) to capture high-level properties of object appearance by computing pairwise interactions of adjacent region-level features. In order to deal with pedestrian detection task, we employ localized oriented gradient histograms as region-level features and measure interactions between adjacent histogram elements with a suitable histogram-similarity function. The experimental results show that our descriptor improves upon HOG significantly and outperforms related high-level features such as GLAC and CoHOG.