Structure and Motion Toolkit in Matlab
 
P.H.S. Torr

Languages: Matlab

From 1992 to date I have been involved in work on estimation of structure and motion from images. This has lead to the formation of the company 2d3 and product boujou, and to the Marr Prize, the highest honour in computer vision. A lot of my work from this time appears in the excellent book by Hartley and Zisserman. As a lot of the problems got solved I rarely work on Fundamental and Trifocal stuff nowadays, a summary of some simple algorithms and Matlab code can be found in my Structure and motion toolkit in Matlab the Torr tool! Also on the Matlab file exchange see here.

I have a fair few papers on this topic a few journal papers are given here, more papers can be found here.

 

P.H.S. Torr and A. Fitzgibbon. Invariant Fitting of Two View Geometry or “In Defiance of the eight point algorithm”, In IEEE Trans Pattern Analysis and Machine Intelligence, 26(5), pages 648-651, 2004.

P.H.S. Torr. Bayesian Model Estimation and Selection for Epipolar Geometry and Generic Manifold Fitting. In International Journal of Computer Vision, 50(1), pages 27—45, 2002.

P.H.S. Torr and A. Zisserman. MLESAC: A New Robust Estimator with Application to Estimating Image Geometry. In Journal of Computer Vision and Image Understanding, pages 138—156, 78(1), 2000.

P.H.S. Torr, A. Fitzgibbon and A. Zisserman. The Problem of Degeneracy in Structure and Motion Recovery from Uncalibrated Image Sequences. In International Journal of Computer Vision, 32(1), pages 27—45, 1999. Marr Prize Paper.

P.H.S. Torr, A. Zisserman. Robust Parameterization and Computation of the Trifocal Tensor. Image and Vision Computing, pages 591—607, v 15, 1997.

P.H.S. Torr, A. Zisserman. Performance Characterisation of Fundamental Matrix Estimation Under Image Degradation. In Machine Vision and Applications, pages 321—333, v 9, 1997.