Presentation 2005-06-17
Epipolar geometry for spherical camera and its calculations
Jun FUJIKI, Shotaro AKAHO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recovering the camera motion and the object shape from the sequence of images is the fundamental and important problem in computer vision. Especially, epipolar geometry, which is the geometrical relation between two images, is quite important to understand the theoretical view of computer vision. On the other hand, computer vision under omnidirectional views, which applicable to suveyrance and/or robot navigation system, is in the spotlight recently and the geometry among multiple omnidirectional views is getting significant. In this paper, we highlight the spherical camera, which is one of the omnidirectional camera, and propose new method to compute epipolar geometry between two spherical images. We also evaluate the methods by synthesized data.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) epipolar geometry / omnidiretional camera / spherical fish-eye camera / parabolic catadioptric camera / essential matrix
Paper # DE2005-20,PRMU2005-41
Date of Issue

Conference Information
Committee PRMU
Conference Date 2005/6/10(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) Epipolar geometry for spherical camera and its calculations
Sub Title (in English)
Keyword(1) epipolar geometry
Keyword(2) omnidiretional camera
Keyword(3) spherical fish-eye camera
Keyword(4) parabolic catadioptric camera
Keyword(5) essential matrix
1st Author's Name Jun FUJIKI
1st Author's Affiliation National Institute of Advanced Industrial Science and Technology()
2nd Author's Name Shotaro AKAHO
2nd Author's Affiliation National Institute of Advanced Industrial Science and Technology
Date 2005-06-17
Paper # DE2005-20,PRMU2005-41
Volume (vol) vol.105
Number (no) 119
Page pp.pp.-
#Pages 6
Date of Issue