Presentation 2010-12-03
Visual Odometry based on De-correlation of Color Components of Video
Yasuaki FUKUTANI, Katsuya AIHARA, Masahiro IWAHASHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The "odometry" based on GPS and IMU have been developed for various applications. Recently, the "visual odometry" has been developed to relax limitations on usage of the GPS and IMU. Most of the existing visual odometry are based on detecting feature points such as white lines or traffic signs on or along the road. This report introduces de-correlation of color components of a video signal before applying the phase only correlation (POC). Simulation results demonstrate that the proposed method increases recognition performance, even though any apparent feature points are not found in the video.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Mobile robot / Visual odometry / Motion estimation / Correlation / Principal component analysis
Paper # CS2010-64,IE2010-103
Date of Issue

Conference Information
Committee CS
Conference Date 2010/11/25(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) Visual Odometry based on De-correlation of Color Components of Video
Sub Title (in English)
Keyword(1) Mobile robot
Keyword(2) Visual odometry
Keyword(3) Motion estimation
Keyword(4) Correlation
Keyword(5) Principal component analysis
1st Author's Name Yasuaki FUKUTANI
1st Author's Affiliation Nagaoka University of Technology()
2nd Author's Name Katsuya AIHARA
2nd Author's Affiliation Nagaoka University of Technology
3rd Author's Name Masahiro IWAHASHI
3rd Author's Affiliation Nagaoka University of Technology
Date 2010-12-03
Paper # CS2010-64,IE2010-103
Volume (vol) vol.110
Number (no) 323
Page pp.pp.-
#Pages 6
Date of Issue