A Caltech Library Service

Motion from fixation

Soatto, Stefano and Perona, Pietro (1996) Motion from fixation. In: 1996 IEEE computer society conference on computer vision and pattern recognition: proceedings. IEEE Computer Society , Los Alamitos, CA, pp. 817-824. ISBN 0-8186-7258-7.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


We study the problem of estimating rigid motion from a sequence of monocular perspective images obtained by navigating around an object while fixating a particular feature point. We cast the problem in the framework of “epipolar geometry”, and propose a filter based upon implicit dynamical model for recursively estimating motion under the fixation constraint. This allows us to compare the quality of the estimates directly against the ones obtained assuming a general rigid motion simply by changing the geometry of the parameter space, while maintaining the same structure of the recursive estimator. We also present a closed-form static solution from two views, and a recursive estimator of the relative pose between the viewer and the scene.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Perona, Pietro0000-0002-7583-5809
Additional Information:© 1996 IEEE. Date of Current Version: 06 August 2002. Research sponsored by NSF NYI Award, NSF ERC in Neuromorphic Systems Engineering, ONR grant N00014-93-1-0990.
Funding AgencyGrant Number
NSF ERC in Neuromorphic Systems EngineeringUNSPECIFIED
Office of Naval Research (ONR)N00014-93-1-0990
Other Numbering System:
Other Numbering System NameOther Numbering System ID
INSPEC Accession Number5329360
Record Number:CaltechAUTHORS:20120131-140550430
Persistent URL:
Official Citation:Soatto, S.; Perona, P.; , "Motion from fixation," Computer Vision and Pattern Recognition, 1996. Proceedings CVPR '96, 1996 IEEE Computer Society Conference on , vol., no., pp.817-824, 18-20 Jun 1996 doi: 10.1109/CVPR.1996.517166 URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:29050
Deposited By: Tony Diaz
Deposited On:08 Feb 2012 23:53
Last Modified:09 Nov 2021 17:03

Repository Staff Only: item control page