Promoting excellence in mobility engineering

  1. FISITA Store
  2. Technical Papers

Detecting a Human Body Direction Using Multiple-HOG
FAST11/TS3-8-2-5

Authors

Yuuki Nakashima, Joo Kooi Tan, Seiji Ishikawa - Kyushu Institute of Technology
Takashi Morie - Kyushu Institute of Technology

Abstract

This paper describes a novel technique for detecting a human body direction using M-HOG feature. The HOG feature is a well-known feature for the detection of a pedestrian. Recently the HOG feature has been employed not only for detecting a human but also for recognizing a human pose or action. This paper proposes the employment of the HOG feature based on multiple bin histograms. We employ the feature for detecting a human body direction. Experimental results show effectiveness of the proposed technique compared to the conventional one.

Keywords: Body direction detection, HOG, Multiple-HOG

Add to basket