A Method of Human Detection Employing Co-occurrence Information on Multiple-HOG Feature and Color Feature

DOI IR IR (HANDLE) Web Site
  • MORIE Takashi
    Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology
  • TAN Joo Kooi
    Department of Mechanical and Control Engineering, Kyushu Institute of Technology
  • ISHIKAWA Seiji
    Department of Mechanical and Control Engineering, Kyushu Institute of Technology
  • NAKASHIMA Yuuki
    Department of Mechanical and Control Engineering, Kyushu Institute of Technology
  • KIM Hyoungseop
    Department of Mechanical and Control Engineering, Kyushu Institute of Technology

Bibliographic Information

Other Title
  • M-HOG特徴量と色相の共起情報を用いた人検出法
  • M-HOG トクチョウリョウ ト シキソウ ノ キョウキジョウホウ オ モチイタ ヒト ケンシュツホウ
Published
2014
Resource Type
journal article
DOI
  • 10.24466/jbfsa.16.1_67
Publisher
Biomedical Fuzzy Systems Association

Search this article

Description

Recently, car vision technologies have been paid much attention in the field of ITS(Intelligent Transport System). In particular, techniques for automatic detection of humans (or pedestrians) from images have been studied enthusiastically. The HOG feature proposed by Dalal and Triggs is a well known feature for representing and recognizing a human image. This is the reason why the feature is improved by many researchers. However, none of the previous improved techniques are satisfactory in the detection rate and the processing time. In this paper, we propose a method of detecting a human based on the M-HOG (Multiple-HOG) feature and RealAdaBoost using 2D probability density function. The proposed method can optimize the number of histogram's bin and express feature co-occurrence. We also propose a method using Hue (HSV Transform) and M-HOG feature. Experimental results show effectiveness of the proposed method compared to previous ones.

Journal

Related Projects

See more

Keywords

Details 詳細情報について

Report a problem

Back to top