Trajectory representation of dynamic texture via manifold learning

This paper proposes a novel framework to explore the motion trajectories of dynamic texture videos via manifold learning. First, we partition the high-dimensional dataset into a set of data clusters. Second, we construct intra-cluster neighborhood graphs using visible neighbors based on the individual character of each data cluster. Third, we construct the inter-cluster graph by analyzing the interrelation among these isolated data clusters. Then we compute the shortest paths according to the whole graph of the dataset. Finally, we embed the dataset to a unique low-dimensional space, trying to maintain the pairwise distances of all pairs of high-dimensional data points. Experiments on standard dynamic texture database show that the proposed framework can represent motion characters of dynamic textures very well. Index Terms—Dimensionality reduction, dynamic textures, manifold learning, trajectory representation