@article {12523, title = {Unsupervised view and rate invariant clustering of video sequences}, journal = {Computer Vision and Image Understanding}, volume = {113}, year = {2009}, month = {2009/03//}, pages = {353 - 371}, abstract = {Videos play an ever increasing role in our everyday lives with applications ranging from news, entertainment, scientific research, security and surveillance. Coupled with the fact that cameras and storage media are becoming less expensive, it has resulted in people producing more video content than ever before. This necessitates the development of efficient indexing and retrieval algorithms for video data. Most state-of-the-art techniques index videos according to the global content in the scene such as color, texture, brightness, etc. In this paper, we discuss the problem of activity-based indexing of videos. To address the problem, first we describe activities as a cascade of dynamical systems which significantly enhances the expressive power of the model while retaining many of the computational advantages of using dynamical models. Second, we also derive methods to incorporate view and rate-invariance into these models so that similar actions are clustered together irrespective of the viewpoint or the rate of execution of the activity. We also derive algorithms to learn the model parameters from a video stream and demonstrate how a single video sequence may be clustered into different clusters where each cluster represents an activity. Experimental results for five different databases show that the clusters found by the algorithm correspond to semantically meaningful activities.}, keywords = {Affine invariance, Cascade of linear dynamical systems, Rate invariance, Summarization, Surveillance, Video clustering, View invariance}, isbn = {1077-3142}, doi = {10.1016/j.cviu.2008.08.009}, url = {http://www.sciencedirect.com/science/article/pii/S1077314208001367}, author = {Turaga,Pavan and Veeraraghavan,Ashok and Chellapa, Rama} }