View alignment with dynamically updated affine tracking

Author

De la Torre, Fernando ; Gong, Shaogang ; McKenna, Stephen

Author_Institution

Dept. of Signal Theory, Univ. Ramon Llull, Spain

fYear

1998

fDate

14-16 Apr 1998

Firstpage

510

Lastpage

515

Abstract

The authors propose a framework for fast view alignment using adaptive affine tracking. They address the issue of modelling both shape and texture information in eigenspace for view alignment. They present an effective bootstrapping process based on colour segmentation and selective attention. They recover affine parameters with dynamic updates to the eigenspace using most recent history and perform predictions in parameter space. Experimental results are given to illustrate their approach

Keywords

image colour analysis; image representation; image segmentation; image texture; object recognition; statistical analysis; tracking; adaptive affine tracking; affine parameter recovery; bootstrapping process; colour segmentation; dynamically updated affine tracking; eigenspace; selective attention; shape information modelling; texture information modelling; view alignment; Computer science; Covariance matrix; Electrical capacitance tomography; Electronic switching systems; History; Matrix decomposition; Object recognition; Piecewise linear techniques; Shape; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Automatic Face and Gesture Recognition, 1998. Proceedings. Third IEEE International Conference on

Conference_Location

Nara

Print_ISBN

0-8186-8344-9

Type

conf

DOI

10.1109/AFGR.1998.670999

Filename

670999