Presentation 2007-12-14
Obstacle detection based on Eigenvector approach in Stereo Image
Hiroaki KAWAE, Yuta SHUNMORI, Junpei NOMURA, Masayuki OKADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This article describes technique to use for obstacle detection of the autonomous navigation system with an eigenvector approach. A manner of making feature points of two figures correspond has been published already. However, using this manner for check in a stereo image engenders pixel deficits by the occlusion or change of the reflection amount of light, and making them correspond might be difficult. Therefore, we sorted them in distance between feature points, and we solved the problem of pixel deficits by making feature points correspond in an eigenvector approach. And also, we inspected that accurate obstacle detection is possible hereby.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) eigenvector approach / harris operator / epipolar constraint / distance image
Paper # CS2007-49,IE2007-132
Date of Issue

Conference Information
Committee CS
Conference Date 2007/12/6(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 Systems (CS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Obstacle detection based on Eigenvector approach in Stereo Image
Sub Title (in English)
Keyword(1) eigenvector approach
Keyword(2) harris operator
Keyword(3) epipolar constraint
Keyword(4) distance image
1st Author's Name Hiroaki KAWAE
1st Author's Affiliation Kyushu Polytechnic College()
2nd Author's Name Yuta SHUNMORI
2nd Author's Affiliation Kyushu Polytechnic College
3rd Author's Name Junpei NOMURA
3rd Author's Affiliation Kyushu Polytechnic College
4th Author's Name Masayuki OKADA
4th Author's Affiliation Kyushu Polytechnic College
Date 2007-12-14
Paper # CS2007-49,IE2007-132
Volume (vol) vol.107
Number (no) 379
Page pp.pp.-
#Pages 6
Date of Issue