Feature Interaction Descriptor for Pedestrian Detection

Hui CAO  Koichiro YAMAGUCHI  Mitsuhiko OHTA  Takashi NAITO  Yoshiki NINOMIYA  

IEICE TRANSACTIONS on Information and Systems   Vol.E93-D   No.9   pp.2656-2659
Publication Date: 2010/09/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E93.D.2656
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
pedestrian detection,  feature interaction,  HOG,  co-occurrence,  

Full Text: PDF(319.1KB)>>
Buy this Article

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.