Scene Flow Estimation using Intelligent Cost Functions
In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.108
Abstract
Motion estimation algorithms are typically based upon the assumption of brightness constancy or related assumptions such as gradient constancy. This manuscript evaluates several common cost functions from the motion estimation literature, which embody these assumptions. We demonstrate that such assumptions break for real world data, and the functions are therefore unsuitable. We propose a simple solution, which significantly increases the discriminatory ability of the metric, by learning a nonlinear relationship using techniques from machine learning. Furthermore, we demonstrate how context and a nonlinear combination of metrics, can provide additional gains, and demonstrating a 65% improvement in the performance of a state of the art scene flow estimation technique. In addition, smaller gains of 20% are demonstrated in optical flow estimation tasks.
Session
Poster Session
Files
Extended Abstract (PDF, 1 page, 658K)Paper (PDF, 14 pages, 2.3M)
Bibtex File
Citation
Simon Hadfield, and Richard Bowden. Scene Flow Estimation using Intelligent Cost Functions. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.
BibTex
@inproceedings{BMVC.28.108 title = {Scene Flow Estimation using Intelligent Cost Functions}, author = {Hadfield, Simon and Bowden, Richard}, year = {2014}, booktitle = {Proceedings of the British Machine Vision Conference}, publisher = {BMVA Press}, editors = {Valstar, Michel and French, Andrew and Pridmore, Tony} doi = { http://dx.doi.org/10.5244/C.28.108 } }