Coarse-to-Fine Event Model for Human Activities

TitleCoarse-to-Fine Event Model for Human Activities
Publication TypeConference Papers
Year of Publication2007
AuthorsCuntoor NP, Chellappa R
Conference NameAcoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on
Date Published2007/04//
Keywordsaction, activities;spatial, airport, browsing;video, dataset;activity, dataset;UCF, event, framework;human, human, indoor, Markov, model, model;event, models;image, probabilities;hidden, processing;, recognition;coarse-to-fine, reduction;video, representation;image, resolution, resolution;image, sequences;hidden, sequences;stability;video, signal, Surveillance, tarmac, TSA

We analyze coarse-to-fine hierarchical representation of human activities in video sequences. It can be used for efficient video browsing and activity recognition. Activities are modeled using a sequence of instantaneous events. Events in activities can be represented in a coarse-to-fine hierarchy in several ways, i.e., there may not be a unique hierarchical structure. We present five criteria and quantitative measures for evaluating their effectiveness. The criteria are minimalism, stability, consistency, accessibility and applicability. It is desirable to develop activity models that rank highly on these criteria at all levels of hierarchy. In this paper, activities are represented as sequence of event probabilities computed using the hidden Markov model framework. Two aspects of hierarchies are analyzed: the effect of reduced frame rate on the accuracy of events detected at a finer scale; and the effect of reduced spatial resolution on activity recognition. Experiments using the UCF indoor human action dataset and the TSA airport tarmac surveillance dataset show encouraging results