Dynamic texture recognition using optical flow features and temporal periodicity

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 of different flow features for normal and complete optical flows.