Searching Video for Complex Activities with Finite State Models
- 1 June 2007
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
We describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our approach is based on units of activity at segments of the body, that can be composed across space and across the body to produce complex queries. The presence of search units is inferred automatically by tracking the body, lifting the tracks to 3D and comparing to models trained using motion capture data. We show results for a large range of queries applied to a collection of complex motion and activity. Our models of short time scale limb behaviour are built using labelled motion capture set. We compare with discriminative methods applied to tracker data; our method offers significantly improved performance. We show experimental evidence that our method is robust to view direction and is unaffected by the changes of clothing.Keywords
This publication has 27 references indexed in Scilit:
- Silhouette Lookup for Automatic Pose TrackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Pictorial Structures for Object RecognitionInternational Journal of Computer Vision, 2005
- Video-based event recognition: activity representation and probabilistic recognition methodsComputer Vision and Image Understanding, 2004
- Layered representations for learning and inferring office activity from multiple sensory channelsComputer Vision and Image Understanding, 2004
- A Survey on Visual Surveillance of Object Motion and BehaviorsIEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 2004
- Hierarchical recognition of daily human actions based on continuous Hidden Markov ModelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Human action recognition by sequence of movelet codewordsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Recognizing action at a distancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Gesture modeling and recognition using finite state machinesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The Visual Analysis of Human Movement: A SurveyComputer Vision and Image Understanding, 1999