RESEARCH SPOTLIGHT
Biography - Naresh P. Cuntoor received the B.E. degree in electronics and communication engineering from the Karnataka Regional Engineering College (now renamed National Institute of Technology), Surathkal, India, in 2000, and the M.S. and Ph.D. degrees in electrical and computer engineering from the University of Maryland, College Park, in 2003 and 2007 respectively. His PhD thesis was on stochastic event detection and characterizing distance between activities in video sequences.
He is currently an engineer in the Signal Innovations Group, Durham, NC where he is working on event detection and behavior modeling. His broad interests are computer vision, statistical pattern recognition, image processing, differential geometry, and topology.
Dr. Cuntoor recently presented his paper on "Epitomic Representation of Human Activities" to the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
Abstract - We introduce an epitomic representation for modeling human activities in video sequences. A video sequence is divided into segments within which the dynamics of objects is assumed to be linear and modeled using linear dynamical systems. The tuple consisting of the estimated system matrix, statistics of the input signal and the initial state value is said to form an epitome. The system matrices are decomposed using the Iwasawa matrix decomposition to isolate the effect of rotation, scaling and projective action on the state vector. We demonstrate the usefulness of the proposed representation and decomposition for activity recognition using the TSA airport surveillance dataset and the UCF indoor human action dataset.