Large displacement optical flow
Authors:
- 1 June 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 41-48
Abstract
The literature currently provides two ways to establish point correspondences between images with moving objects. On one side, there are energy minimization methods that yield very accurate, dense flow fields, but fail as displacements get too large. On the other side, there is descriptor matching that allows for large displacements, but correspondences are very sparse, have limited accuracy, and due to missing regularity constraints there are many outliers. In this paper we propose a method that can combine the advantages of both matching strategies. A region hierarchy is established for both images. Descriptor matching on these regions provides a sparse set of hypotheses for correspondences. These are integrated into a variational approach and guide the local optimization to large displacement solutions. The variational optimization selects among the hypotheses and provides dense and subpixel accurate estimates, making use of geometric constraints and all available image information.Keywords
This publication has 14 references indexed in Scilit:
- Local Invariant Feature Detectors: A SurveyFoundations and Trends in Computer Graphics and Vision, 2008
- Using contours to detect and localize junctions in natural images2008
- A Duality Based Approach for Realtime TV-L 1 Optical Flow2007
- Efficient MRF Deformation Model for Non-Rigid Image Matching2007
- Consistent segmentation for optical flow estimation2005
- Robust wide-baseline stereo from maximally stable extremal regionsImage and Vision Computing, 2004
- Learning to detect natural image boundaries using local brightness, color, and texture cuesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- A Probabilistic Approach to Large Displacement Optical Flow and Occlusion Detection2004
- Dense estimation and object-based segmentation of the optical flow with robust techniquesIEEE Transactions on Image Processing, 1998
- The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow FieldsComputer Vision and Image Understanding, 1996