Feature interaction descriptor for pedestrian detection

Abstract

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 actions 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. Copyright © 2010 The Institute of Electronics, Information and Communication Engineers.