We propose a new algorithm for dense optical flow computation. Dense optical flow schemes are challenged by the presence of motion discontinuities. In state of the art optical flow methods, over-smoothing of flow discontinuities accounts for most of the error. A breakthrough in the performance of optical flow computation has recently been achieved by Brox et al. Our algorithm embeds their functional within a contour-based segmentation framework. Piecewise-smooth flow fields are accommodated and flow boundaries are crisp. Experimental results show the superiority of our algorithm with respect to alternative techniques.
Dense discontinuous optical flow via contour-based segmentation
IEEE International Conference on Image Processing 2005 ; 3 ; III-1264
2005-01-01
176938 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Dense Discontinuous Optical Flowvia Contour-Based Segmentation
British Library Conference Proceedings | 2005
|Rigid Body Segmentation and Shape Description from Dense Optical Flow under Weak Perspective
British Library Conference Proceedings | 1995
|Transition region-based active contour model for image segmentation
British Library Online Contents | 2013
|A Contour Code Feature Based Segmentation for Handwriting Recognition
British Library Conference Proceedings | 2003
|