Skip to Main content Skip to Navigation
Conference papers

Simultaneous learning of motion and appearance

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.
Document type :
Conference papers
Complete list of metadata

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/inria-00326712
Contributor : Peter Sturm <>
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

File

mlvma08_submission_28.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00326712, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

158

Files downloads

406