CaltechAUTHORS
  A Caltech Library Service

Dynamic Rigid Motion Estimation From Weak Perspective

Soatto, Stefano and Perona, Pietro (1995) Dynamic Rigid Motion Estimation From Weak Perspective. In: Proceedings of the Fifth International Conference on Computer Vision. IEEE , pp. 321-328. ISBN 0-8186-7042-8 http://resolver.caltech.edu/CaltechAUTHORS:20120209-113251184

[img]
Preview
PDF - Published Version
See Usage Policy.

781Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20120209-113251184

Abstract

“Weak perspective” represents a simplified projection model that approximates the imaging process when the scene is viewed under a small viewing angle and its depth relief is small relative to its distance from the viewer. We study how to generate dynamic models for estimating rigid 3D motion from weak perspective. A crucial feature in dynamic visual motion estimation is to decouple structure from motion in the estimation model. The reasons are both geometric-to achieve global observability of the model-and practical, for a structure independent motion estimator allows us to deal with occlusions and appearance of new features in a principled way. It is also possible to push the decoupling even further, and isolate the motion parameters that are affected by the so called “bas relief ambiguity” from the ones that are not. We present a novel method for reducing the order of the estimator by decoupling portions of the state space from the time evolution of the measurement constraint. We use this method to construct an estimator of full rigid motion (modulo a scaling factor) on a six dimensional state space, an approximate estimator for a four dimensional subset of the motion space, and a reduced filter with only two states. The latter two are immune to the bas relief ambiguity. We compare strengths and weaknesses of each of the schemes on real and synthetic image sequences.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1109/ICCV.1995.466922DOIUNSPECIFIED
http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=466922PublisherUNSPECIFIED
Additional Information:© 1995 IEEE. Issue Date: 20-23 Jun 1995; Date of Current Version: 06 August 2002. This work was supported by a scholarship from the “Fondazione A. Gini” and a scholarship from the University of Padova - Italy (S. S.), the California Institute of Technology, the NSF ERC Center for Neuromorphic Systems Engineering, the NSF FYI Award (P. P.), and the Italian Space Agency ASI-RS-103.
Funders:
Funding AgencyGrant Number
Fondazione A. GiniUNSPECIFIED
University of Padova, ItalyUNSPECIFIED
CaltechUNSPECIFIED
NSF ERC Center for Neuromorphic Systems EngineeringUNSPECIFIED
NSF FYI AwardUNSPECIFIED
Italian Space AgencyASI-RS-103
Other Numbering System:
Other Numbering System NameOther Numbering System ID
INSPEC Accession Number5028029
Record Number:CaltechAUTHORS:20120209-113251184
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20120209-113251184
Official Citation:Soatto, S.; Perona, P.; , "Dynamic rigid motion estimation from weak perspective," Computer Vision, 1995. Proceedings., Fifth International Conference on , vol., no., pp.321-328, 20-23 Jun 1995 doi: 10.1109/ICCV.1995.466922
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:29228
Collection:CaltechAUTHORS
Deposited By: Jason Perez
Deposited On:09 Feb 2012 21:01
Last Modified:26 Dec 2012 14:49

Repository Staff Only: item control page