Presentation 2001/12/14
Improvement in Accuracy of reconstruction for Stereo Vision based on Color Segmentation
Hironao SAITO, Yuji WAKO, Masami IWATUKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have proposed a stereo vision method based on color segmentation. This method can acquire dense 3D maps by detecting feature points from the region contours given by color segmentation and matching the feature points on corresponding regions. However, the accuracy of reconstruction is sensitive to noise because the positions of feature points are detected by the degree of change of total curvature. Therefore, this paper proposes an approach to improve the accuracy of feature positions on contours by using subotimal line segmentation insensitive to noise.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Stereo Vision / Color Segmentation / 3D Reconstruction / Region Contour / Line Segmentation
Paper # PRMU2001-183
Date of Issue

Conference Information
Committee PRMU
Conference Date 2001/12/14(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Improvement in Accuracy of reconstruction for Stereo Vision based on Color Segmentation
Sub Title (in English)
Keyword(1) Stereo Vision
Keyword(2) Color Segmentation
Keyword(3) 3D Reconstruction
Keyword(4) Region Contour
Keyword(5) Line Segmentation
1st Author's Name Hironao SAITO
1st Author's Affiliation Faculty of Engineering, Hosei University()
2nd Author's Name Yuji WAKO
2nd Author's Affiliation Faculty of Engineering, Hosei University
3rd Author's Name Masami IWATUKI
3rd Author's Affiliation Faculty of Engineering, Hosei University
Date 2001/12/14
Paper # PRMU2001-183
Volume (vol) vol.101
Number (no) 525
Page pp.pp.-
#Pages 6
Date of Issue