Dynamic Texture Recognition Using Optical Flow Features and Temporal Periodicity

@article{Fazekas2007DynamicTR,
  title={Dynamic Texture Recognition Using Optical Flow Features and Temporal Periodicity},
  author={S{\'a}ndor Fazekas and Dmitry Chetverikov},
  journal={2007 International Workshop on Content-Based Multimedia Indexing},
  year={2007},
  pages={25-32}
}
We address the problem of dynamic texture (DT) classification using optical flow features. Optical flow based approaches dominate among the currently available DT recognition methods. We introduce rotation-and scale-invariant DT features based on local image distortions computed via optical flow. Then we describe an SVD-based method for measuring the degree of temporal periodicity of a dynamic texture. Finally, we present the results of a DT classification study that compares the performances… CONTINUE READING