Motion Models that Only Work Sometimes

Abstract : It is too often that tracking algorithms lose track of interest points in image sequences. This persistent problem is difficult because the pixels around an interest point change in appearance or move in unpredictable ways. In this paper we explore how classifying videos into categories of camera motion improves the tracking of interest points, by selecting the right specialist motion model for each video. As a proof of concept, we enumerate a small set of simple categories of camera motion and implement their corresponding specialized motion models. We evaluate the strategy of predicting the most appropriate motion model for each test sequence. Within the framework of a standard Bayesian tracking formulation, we compare this strategy to two standard motion models. Our tests on challenging real-world sequences show a significant improvement in tracking robustness, achieved with different kinds of supervision at training time.
Complete list of metadatas

Cited literature [32 references]  Display  Hide  Download
Contributor : Yvain Queau <>
Submitted on : Friday, March 29, 2013 - 2:27:30 PM
Last modification on : Thursday, February 7, 2019 - 5:47:15 PM
Long-term archiving on : Sunday, April 2, 2017 - 10:40:16 PM


Files produced by the author(s)


  • HAL Id : hal-00806098, version 1


Cristina Garcia Cifuentes, Marc Sturzel, Frédéric Jurie, Gabriel J. Brostow. Motion Models that Only Work Sometimes. British Machive Vision Conference, Sep 2012, Guildford, United Kingdom. 12 p. ⟨hal-00806098⟩



Record views


Files downloads