2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1 2005
DOI: 10.1109/acvmot.2005.44
|View full text |Cite
|
Sign up to set email alerts
|

Dynamic Texture Recognition by Spatio-Temporal Multiresolution Histograms

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
44
0

Year Published

2006
2006
2011
2011

Publication Types

Select...
4
2
2

Relationship

0
8

Authors

Journals

citations
Cited by 60 publications
(44 citation statements)
references
References 25 publications
0
44
0
Order By: Relevance
“…But they did not consider the multi-scale properties of DT. Lu et al proposed a new method using spatiotemporal multi-resolution histograms based on velocity and acceleration fields [21]. Velocity and acceleration fields of different spatiotemporal resolution image sequences were accurately estimated by the structure tensor method.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…But they did not consider the multi-scale properties of DT. Lu et al proposed a new method using spatiotemporal multi-resolution histograms based on velocity and acceleration fields [21]. Velocity and acceleration fields of different spatiotemporal resolution image sequences were accurately estimated by the structure tensor method.…”
Section: Related Workmentioning
confidence: 99%
“…The methods based on optic flow [3], [4], [17], [18], [19], [20], [21], [22], [23], [24] are currently the most popular ones [5], because optic flow estimation is a computationally efficient and natural way to characterize the local dynamics of a temporal texture. Péteri and Chetverikov [3] proposed a method that combines normal flow features with periodicity features, in an attempt to explicitly characterize motion magnitude, directionality and periodicity.…”
Section: Related Workmentioning
confidence: 99%
“…In recent years, recognizing dynamic textures has drawn increasing interests [1,2,3,4,5,6]. Dynamic texture recognition aims at finding dynamic visual patterns with repetitive motion, such as waving trees, flame, water waves, and traffic flow, in video.…”
Section: Introductionmentioning
confidence: 99%
“…The first category focuses on extracting local features, such as optical flow [2], local binary pattern (LBP) [5], and histogram [6], for recognition. Other information, such as temporal periodicity, can be jointly used for recognition.…”
Section: Introductionmentioning
confidence: 99%
“…The recent survey [6] mentions just a few methods that keep track of DT 'history' to a certain, limited temporal depth [3,11,21,22]. With small depth, one can only estimate short-term temporal variations such as acceleration [19]; no periodicity estimation is possible. Global spatiotemporal transforms like spatiotemporal wavelets [25] may become useful in multiscale periodicity analysis when motion periodicity appears at different scales (e.g., trunk, branches, leaves of a tree in the wind).…”
Section: Introductionmentioning
confidence: 99%