Abstract We address the problem of recognition of natural motions such as water, smoke and wind-blown vegetation. Such dynamic scenes exhibit characteristic stochastic motions, and we ask whether the scene contents can be recognized using motion information alone. Previous work on this problem has considered only the case where the texture samples have sufficient overlap to allow registration, so that the visual content of the scene is very similar between examples. In this paper we investigate the recognition of entirely non-overlapping views of the same underlying motion, specifically excluding appearance-based cues. We describe the scenes with time-series models—specifically multivariate autoregressive (AR) models—so the recognition problem becomes one of measuring distances between AR models. We show that existing techniques, when applied to non-overlapping sequences, have significantly lower performance than on static-camera data. We propose several new schemes, and show that some outperform the existing methods.
Shift-Invariant Dynamic Texture Recognition
Computer Vision – ECCV 2006 ; 9 ; 549-562
Lecture Notes in Computer Science ; 3952 , 9
2006-01-01
14 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Shift-Invariant Dynamic Texture Recognition
British Library Conference Proceedings | 2006
|The Illumination-Invariant Recognition of Texture in Color Texture
British Library Conference Proceedings | 1995
|British Library Conference Proceedings | 2001
|IEEE | 2001
|Affine-Invariant Local Descriptors and Neighborhood Statistics for Texture Recognition
British Library Conference Proceedings | 2003
|