Feature Interaction Descriptor for Pedestrian Detection

スポンサーリンク

概要

• 論文の詳細を見る

• 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.

• （社）電子情報通信学会の論文
• 2010-09-01

著者

• CAO Hui

  Road Environment Recognition Laboratory, Safety & Information Systems Division, Toyota Central R&D L

• NINOMIYA Yoshiki

  Safety & Information Systems Division, Toyota Central R&D LABS., INC.

• Yamaguchi Koichiro

  Road Environment Recognition Laboratory Safety & Information Systems Division Toyota Central R&a

• Ninomiya Yoshiki

  Safety & Information Systems Division Toyota Central R&d Labs. Inc.

• Ohta Mitsuhiko

  Road Environment Recognition Laboratory Safety & Information Systems Division Toyota Central R&a

• Naito Takashi

  Road Environment Recognition Laboratory Safety & Information Systems Division Toyota Central R&a

• Cao Hui

  Road Environment Recognition Laboratory Safety & Information Systems Division Toyota Central R&a

関連論文

• Feature Interaction Descriptor for Pedestrian Detection
• Feature Interaction Descriptor for Pedestrian Detection

スポンサーリンク