Applying MSC-HOG feature to the detection of a human on a bicycle

Author

Heewook Jung ; Ehara, Yoshiyasu ; Joo Kooi Tan ; Hyoungseop Kim ; Ishikawa, Seiichiro

Author_Institution

Dept. of Mech. & Control Eng., Kyushu Inst. of Technol., Kitakyushu, Japan

fYear

2012

Firstpage

514

Lastpage

517

Abstract

Traffic accidents are decreasing under the influence of technology advancement. But the problems still remain that accidents occur due to carelessness of drivers. Therefore many researchers have been still studying to realize an advanced safety system. The Histograms of Oriented Gradients (HOG) feature is well known as a useful method of detecting a standing human in various kinds of the background. Unlike a human, a bicycle changes its appearance variously according to viewpoints. Hence, it is more difficult than detecting a human. In this paper, we propose a method of detecting a human on a bicycle using the Multiple-size Cell HOG (MSC-HOG) feature and the RealAdaboost algorithm. Experimental results and evaluation show satisfactory performance of the proposed method.

Keywords

computer vision; feature extraction; learning (artificial intelligence); object detection; object recognition; road accidents; road traffic; traffic engineering computing; MSC-HOG feature; advanced safety system; car vision; histograms-of-oriented gradients feature; human detection; multiple-size cell HOG feature; object recognition techniques; realAdaboost algorithm; technology advancement; traffic accidents; Accidents; Bicycles; Classification algorithms; Feature extraction; Histograms; Humans; Merging; MSC-HOG feature; advanced safety system; bicycle detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Control, Automation and Systems (ICCAS), 2012 12th International Conference on

Print_ISBN

978-1-4673-2247-8

Type

conf

Filename

6393499