Simplifying multiple motion and structure analysis using planar parallax and image warping

Author

Sawhney, Harpreet S.

Author_Institution

Machine Vision Group, IBM Almaden Res. Center, San Jose, CA, USA

fYear

1994

fDate

11-12 Nov 1994

Firstpage

104

Lastpage

109

Abstract

Presents a formulation for 3D motion and structure analysis using motion parallax defined with respect to an arbitrary plane in the environment. It is shown that if an image coordinate system is warped using plane projective transformation with respect to a reference view, the residual image motion is dependent only on the epipoles and has a simple relation to the 3D structure. Our computational scheme avoids point/line correspondence and is based on hierarchical estimation and image warping working directly with spatiotemporal image intensities. Results on real images demonstrate how this analysis can be used to simplify ego and object motion segmentation

Keywords

motion estimation; 3D motion analysis; 3D structure analysis; computational scheme; ego motion; epipoles; hierarchical estimation; image coordinate system; image warping; motion parallax; motion segmentation; multiple motion analysis; object motion; planar parallax; plane projective transformation; reference view; residual image motion; spatiotemporal image intensities; Cameras; Computer vision; Image analysis; Image motion analysis; Image reconstruction; Image segmentation; Linear approximation; Machine vision; Motion analysis; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Motion of Non-Rigid and Articulated Objects, 1994., Proceedings of the 1994 IEEE Workshop on

Conference_Location

Austin, TX

Print_ISBN

0-8186-6435-5

Type

conf

DOI

10.1109/MNRAO.1994.346248

Filename

346248