Recovering the Basic Structure of Human Activities from a Video-Based Symbol String

Authors:
Kris M. Kitani;Yoichi Sato;Akihiro Sugimoto
Affiliations:
University of Tokyo;University of Tokyo;National Institute of Informatics, Japan
Venue:
WMVC '07 Proceedings of the IEEE Workshop on Motion and Video Computing
Year:
2007

Citing 0
Cited 4

Understanding video events: a survey of methods for automatic interpretation of semantic occurrences in video

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Human activity analysis: A review

ACM Computing Surveys (CSUR)
Survey on classifying human actions through visual sensors

Artificial Intelligence Review
Recognition of long-term behaviors by parsing sequences of short-term actions with a stochastic regular grammar

SSPR'12/SPR'12 Proceedings of the 2012 Joint IAPR international conference on Structural, Syntactic, and Statistical Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In recent years stochastic context-free grammars have been shown to be effective in modeling human activities because of the hierarchical structures they represent. However, most of the research in this area has yet to address the issue of learning the activity grammars from a noisy input source, namely, video. In this paper, we present a framework for identifying noise and recovering the basic activity grammar from a noisy symbol string produced by video. We identify the noise symbols by finding the set of non-noise symbols that optimally compresses the training data, where the optimality of compression is measured using an MDL criterion. We show the robustness of our system to noise and its effectiveness in learning the basic structure of human activity, through an experiment with real video from a local convenience store.