Epitomic Representation of Human Activities

TitleEpitomic Representation of Human Activities
Publication TypeConference Papers
Year of Publication2007
AuthorsCuntoor NP, Chellappa R
Conference NameComputer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on
Date Published2007/06//
Keywordsaction, activities, airport, dataset;epitomic, dataset;UCF, decomposition;modelling;statistics;video, decomposition;TSA, dynamical, human, indoor, Iwasawa, matrix, matrix;human, modeling;input, processing;, representation;estimated, sequences;image, sequences;matrix, signal, statistics;linear, Surveillance, system, systems;video

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.