For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Feature Interaction Descriptor for Pedestrian Detection
Hui CAO Koichiro YAMAGUCHI Mitsuhiko OHTA Takashi NAITO Yoshiki NINOMIYA
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/09/01
Online ISSN: 1745-1361
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)>>
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.