Real-time coarse-to-fine topologically preserving segmentation
- 1 June 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2947-2955
- https://doi.org/10.1109/cvpr.2015.7298913
Abstract
In this paper, we tackle the problem of unsupervised segmentation in the form of superpixels. Our main emphasis is on speed and accuracy. We build on [31] to define the problem as a boundary and topology preserving Markov random field. We propose a coarse to fine optimization technique that speeds up inference in terms of the number of updates by an order of magnitude. Our approach is shown to outperform [31] while employing a single iteration. We evaluate and compare our approach to state-of-the-art superpixel algorithms on the BSD and KITTI benchmarks. Our approach significantly outperforms the baselines in the segmentation metrics and achieves the lowest error on the stereo task.Keywords
This publication has 23 references indexed in Scilit:
- Efficient Hierarchical Graph-Based Segmentation of RGBD VideosPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Fast and Accurate Large-Scale Stereo Reconstruction Using Variational MethodsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Robust Monocular Epipolar Flow EstimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Are we ready for autonomous driving? The KITTI vision benchmark suitePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Superpixels via pseudo-Boolean optimizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Entropy rate superpixel segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Efficient hierarchical graph-based video segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- TurboPixels: Fast Superpixels Using Geometric FlowsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual InformationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004