Outlier Correction in Image Sequences for the Affine Camera

Speaker:          Dr. Du Huynh   
                  School of Computer Science and Software Engineering 
                  The University of Western Australia, Australia   

Title:            Outlier Correction in Image Sequences for the Affine Camera 

Date:             Monday, 23 Feb 2004 

Time:             4:00pm - 5:00pm 

Venure:           Lecture Theatre F (Leung Yat Seng Lecture Theatre) 
                  (near lift nos. 25/26)   


ABSTRACT: 

It is widely known that, for the affine camera model, both shape and
motion can be factorized directly from the so-called image measurement
matrix constructed from image point coordinates. The ability to extract
both shape and motion from this matrix by a single SVD operation makes
this shape-from-motion approach attractive; however, it can not deal with
missing feature points and, in the presence of outliers, a direct SVD to
the matrix would yield highly unreliable shape and motion components. In
this talk, I will present an outlier correction scheme that iteratively
updates the elements of the image measurement matrix.  The magnitude and
sign of the update to each element is dependent upon the residual robustly
estimated in each iteration. The result is that outliers are corrected and
retained, giving improved reconstruction and smaller reprojection errors.  
This iterative outlier correction scheme has been applied to both
synthesized and real video sequences.  The results obtained are remarkably
good.


BIOGRAPHY: 

Dr Du Huynh completed her PhD in Computer Science at The University of
Western Australia (UWA) in 1994.  She then joined the Cooperative Research
Centre on Sensor, Signal, and Information Processing in South Australia as
a postdoc.  In 1998, she returned to Western Australia to take up the post
of a Lecturer at Murdoch University and moved back to UWA, as a Senior
Lecturer in the School of Computer Science and Software Engineering in
2003.

Dr Huynh is an active researcher in the computer vision and image
processing area.  She has published many papers in international and
national journals and conferences, including the European Conference on
Computer Vision, International Conference on Computer Vision, and
International Journal of Computer Vision.  She has been
involved in reviewing technical papers for ECCV2002, Image and Vision
Computing journal, IEEE PAMI, SPIE Optical Engineering, etc.  She was on
the Program Committee of Australian Pattern Recognition Society (APRS) and
IEEE NSW Section Workshop on Stereo Image and Video Processing in 2000.