On the spatial statistics of optical flow
- 1 January 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15505499) , 42-49 Vol. 1
- https://doi.org/10.1109/iccv.2005.180
Abstract
We develop a method for learning the spatial statistics of optical flow fields from a novel training database. Training flow fields are constructed using range images of natural scenes and 3D camera motions recovered from handheld and car-mounted video sequences. A detailed analysis of optical flow statistics in natural scenes is presented and machine learning methods are developed to learn a Markov random field model of optical flow. The prior probability of a flow field is formulated as a field-of-experts model that captures the higher order spatial statistics in overlapping patches and is trained using contrastive divergence. This new optical flow prior is compared with previous robust priors and is incorporated into a recent, accurate algorithm for dense optical flow computation. Experiments with natural and synthetic sequences illustrate how the learned optical flow prior quantitatively improves flow accuracy and how it captures the rich spatial structure found in natural scene motion.Keywords
This publication has 19 references indexed in Scilit:
- Fields of Experts: A Framework for Learning Image PriorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Probability distributions of optical flowPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statisticsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Training Products of Experts by Minimizing Contrastive DivergenceNeural Computation, 2002
- 10.1162/jmlr.2003.4.7-8.1235Applied Physics Letters, 2000
- Design and Use of Linear Models for Image Motion AnalysisInternational Journal of Computer Vision, 2000
- Multi-frame optical flow estimation using subspace constraintsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Multimodal estimation of discontinuous optical flow using Markov random fieldsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Scene Segmentation from Visual Motion Using Global OptimizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1987
- Determining optical flowArtificial Intelligence, 1981