ABSTRACT
In this paper, we propose a novel dynamic texture description method base on spatiotemporal context phrase for general dynamic texture. Different with the existing methods, we consider the spatiotemporal context both in the feature extraction phase and in the feature description phase. We present a space time constraint and salience rank strategies to extract the representative interest points. Then, we propose a novel space time context phrase method to mining and describe the semantic and spatiotemporal correlation of interest points. Finally, the space time context phrase is used in the nearest neighbor classifier to classify dynamic texture scene. We test our algorithm on the dynamic texture classification and human action classification tasks on the Dyntex dataset and the KTH dataset, respectively. The results show that our proposed method outperforms the state-of-the-art methods on the tasks.
- G. Doretto, A. Chiuso, Y. N. Wu, and S. Soatto, "Dynamic textures," IJCV, 51(2):91--109, 2003. Google ScholarDigital Library
- C. Schuldt, I. Laptev, and B. Caputo, "Recognizing human actions: a local SVM approach", IEEE ICPR, 32--36, 2004 Google ScholarDigital Library
- I. Laptev, M. Marszalek, C. Schmid, and B. Rozenfeld, "Learning realistic human actions from movies", CVPR, 2008Google ScholarCross Ref
- J. C. Niebles, C. W. Chen, and L. Fei-Fei, "Modeling temporal structure of decomposable motion segments for activity classification", ECCV, 2010. Google ScholarDigital Library
- G. Zhao, and M. Pietikinen, "Dynamic texture recognition using local binary patterns with an application to facial expressions", IEEE TPAMI, 29(6):915--928, 2007 Google ScholarDigital Library
- Z. Lu, W. Xie, J. Pei, and J. Huang, "Dynamic Texture Recognition by Spatiotemporal Multiresolution Histogram", IEEE Workshop on Motion and Video Computing, 2005 Google ScholarDigital Library
- G. Zhao, and M. Pietikäinen, "Dynamic texture recognition using volume local binary patterns", Dynamical Vision, 2007 Google ScholarDigital Library
- K. G. Derpanis, and R. P. Wildes, "Dynamic Texture Recognition Based on Distributions of Spacetime Oriented Structure", CVPR, 2010Google Scholar
- I. Laptev, "On Space-Time Interest Points", IJCV, 2005 Google ScholarDigital Library
- R. Péteri, S. Fazekas, and M. J. Huiskes, "DynTex: A Comprehensive Database of Dynamic Textures", PRL, 2010 Google ScholarDigital Library
- S. Dubois, R. Péteri, and M. Ménard, "A Comparison of Wavelet Based Spatio-temporal Decomposition Methods for Dynamic Texture Recognition", Pattern Recognition and Image Analysis, 314--321, 2009 Google ScholarDigital Library
- S. Wong, T. Kim, R. Cipolla, Learning Motion Categories using Both Semantic and Structural Information, CVPR, 2007Google Scholar
Index Terms
- A spatiotemporal context phrase description for general dynamic texture
Recommendations
Dynamic texture recognition with video set based collaborative representation
Efficient feature description and classification of dynamic texture (DT) is an important problem in computer vision and pattern recognition. Recently, the local binary pattern (LBP) based dynamic texture descriptor has been proposed to classify DTs by ...
Spatiotemporal lacunarity spectrum for dynamic texture classification
A descriptor for dynamic texture (DT) is proposed.The descriptor is constructed by lacunarity analysis on local binary patterns.The proposed descriptor encodes the spatio-temporal distribution details of DT patterns in a multi-scale manner.The proposed ...
Dynamic texture video classification using extreme learning machine
Recognition of complex dynamic texture is a difficult task and captures the attention of the computer vision community for several decades. Essentially the dynamic texture recognition is a multi-class classification problem that has become a real ...
Comments