Presentation 2003/2/14
Recover of the motion and the shape from sequences of scaled orthographic images via autoassociative learning
Jun FUJIKI, Takio KURITA,
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 multiple images with point correspondences is the fundamental and important problem in computer vision and many algorithms are presented. However, most algorithms do not work well when some data are missing. In this paper, we present a new algorithm which work well even if half of data are missing. The algorithm is based on autoassociative learning of multilayered neural network with their connecting coefficients constrained. The algorithm estimate missing data and recover the motion and the shape simultaneously. we evaluate the ability of the algorithm through experiment with synthesize data.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) structure from motion / sealed orthographic projection / Euclidean reconstruction / occlusion / autoassociative learning
Paper # PRMU2002-222
Date of Issue

Conference Information
Committee PRMU
Conference Date 2003/2/14(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) Recover of the motion and the shape from sequences of scaled orthographic images via autoassociative learning
Sub Title (in English)
Keyword(1) structure from motion
Keyword(2) sealed orthographic projection
Keyword(3) Euclidean reconstruction
Keyword(4) occlusion
Keyword(5) autoassociative learning
1st Author's Name Jun FUJIKI
1st Author's Affiliation National Institute of Advanced Industrial Science and Technology()
2nd Author's Name Takio KURITA
2nd Author's Affiliation National Institute of Advanced Industrial Science and Technology
Date 2003/2/14
Paper # PRMU2002-222
Volume (vol) vol.102
Number (no) 652
Page pp.pp.-
#Pages 4
Date of Issue