caa a22 4500 467915113 CHVBK 20180406152859.0 cr unu---uuuuu 170328e20060601xx s 000 0 eng 10.1007/s11263-006-6660-3 doi (NATIONALLICENCE)springer-10.1007/s11263-006-6660-3 A Feature-based Approach for Dense Segmentation and Estimation of Large Disparity Motion [Elektronische Daten] [Josh Wills, Sameer Agarwal, Serge Belongie] We present a novel framework for motion segmentation that combines the concepts of layer-based methods and feature-based motion estimation. We estimate the initial correspondences by comparing vectors of filter outputs at interest points, from which we compute candidate scene relations via random sampling of minimal subsets of correspondences. We achieve a dense, piecewise smooth assignment of pixels to motion layers using a fast approximate graphcut algorithm based on a Markov random field formulation. We demonstrate our approach on image pairs containing large inter-frame motion and partial occlusion. The approach is efficient and it successfully segments scenes with inter-frame disparities previously beyond the scope of layer-based motion segmentation methods. We also present an extension that accounts for the case of non-planar motion, in which we use our planar motion segmentation results as an initialization for a regularized Thin Plate Spline fit. In addition, we present applications of our method to automatic object removal and to structure from motion. Springer Science + Business Media, LLC, 2006 motion segmentation nationallicence RANSAC nationallicence Markov Random Field nationallicence layer-based motion nationallicence metric labeling problem nationallicence graph cuts nationallicence periodic motion nationallicence Wills Josh Department of Computer Science and Engineering, University of California, 92093, San Diego, La Jolla, CA, USA aut Agarwal Sameer Department of Computer Science and Engineering, University of California, 92093, San Diego, La Jolla, CA, USA aut Belongie Serge Department of Computer Science and Engineering, University of California, 92093, San Diego, La Jolla, CA, USA aut International Journal of Computer Vision Kluwer Academic Publishers 68/2(2006-06-01), 125-143 0920-5691 68:2<125 2006 68 11263 https://doi.org/10.1007/s11263-006-6660-3 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11263-006-6660-3 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Wills Josh Department of Computer Science and Engineering, University of California, 92093, San Diego, La Jolla, CA, USA aut NATIONALLICENCE 700 1- Agarwal Sameer Department of Computer Science and Engineering, University of California, 92093, San Diego, La Jolla, CA, USA aut NATIONALLICENCE 700 1- Belongie Serge Department of Computer Science and Engineering, University of California, 92093, San Diego, La Jolla, CA, USA aut NATIONALLICENCE 773 0- International Journal of Computer Vision Kluwer Academic Publishers 68/2(2006-06-01), 125-143 0920-5691 68:2<125 2006 68 11263 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer