Presentation	2005-09-15 Real-Time Pedestrian Detection on Monitoring Lines by Machine Learning Chikahito Nakajima,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	This paper proposes a real-time detection method of intruders, who are walking or approaching to high voltage electric facilities, by existing surveillance cameras. The method uses monitoring lines that are settled around the facilities in advance instead of monitoring area to perform high-speed detection of intruders. To classify human-body and others, it uses Support Vector Machine as one of pattern recognition technique. In the experimental results, we describe that the system detects intruders on the monitoring lines in a video-rate.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Video Monitoring / Pedestrian Detection / Machine Learning / Monitoring Line
Paper #	CQ2005-44,OIS2005-29,IE2005-37
Date of Issue

Conference Information
Committee	CQ
Conference Date	2005/9/8(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Communication Quality (CQ)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Real-Time Pedestrian Detection on Monitoring Lines by Machine Learning
Sub Title (in English)
Keyword(1)	Video Monitoring
Keyword(2)	Pedestrian Detection
Keyword(3)	Machine Learning
Keyword(4)	Monitoring Line
1st Author's Name	Chikahito Nakajima
1st Author's Affiliation	Central Research Institute of Electric Power Industry()
Date	2005-09-15
Paper #	CQ2005-44,OIS2005-29,IE2005-37
Volume (vol)	vol.105
Number (no)	281
Page	pp.pp.-
#Pages	6
Date of Issue