1Center for Machine Perception (Czech Technical University in Prague Faculty of Electrical Engineering Department of Cybernetics Technicka 2 166 27 Prague 6 Czech republic - Czech Republic)
Abstract : A new learning method for motion estimation of objects with significantly varying appearance is proposed. Varying object appearance is represented by a low dimensional space of appearance parameters. The appearance mapping and motion estimation method are optimized simultaneously. Appearance parameters are estimated by unsupervised learning. The method is experimentally verified by a tracking application on sequences which exhibit strong variable illumination, non-rigid deformations and self-occlusions.
https://hal.inria.fr/inria-00326712 Contributor : Peter SturmConnect in order to contact the contributor Submitted on : Sunday, October 5, 2008 - 12:23:12 PM Last modification on : Tuesday, January 19, 2021 - 10:16:02 AM Long-term archiving on: : Monday, October 8, 2012 - 1:56:12 PM
Karel Zimmermann, Tomas Svoboda, Jiri Matas. Simultaneous learning of motion and appearance. The 1st International Workshop on Machine Learning for Vision-based Motion Analysis - MLVMA'08, Oct 2008, Marseille, France. ⟨inria-00326712⟩