Statistical analysis of dynamic actions
- 24 July 2006
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 28 (9), 1530-1535
- https://doi.org/10.1109/tpami.2006.194
Abstract
Real-world action recognition applications require the development of systems which are fast, can handle a large variety of actions without a priori knowledge of the type of actions, need a minimal number of parameters, and necessitate as short as possible learning stage. In this paper, we suggest such an approach. We regard dynamic activities as long-term temporal objects, which are characterized by spatio-temporal features at multiple temporal scales. Based on this, we design a simple statistical distance measure between video sequences which captures the similarities in their behavioral content. This measure is nonparametric and can thus handle a wide range of complex dynamic actions. Having a behavior-based distance measure between sequences, we use it for a variety of tasks, including: video indexing, temporal segmentation, and action-based video clustering. These tasks are performed without prior knowledge of the types of actions, their models, or their temporal extentsKeywords
This publication has 23 references indexed in Scilit:
- Probabilistic recognition of activity using local appearancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Recognizing action at a distancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Cardboard people: a parameterized model of articulated image motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Motion segmentation and pose recognition with motion history gradientsMachine Vision and Applications, 2002
- The recognition of human movement using temporal templatesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- Texture mixing and texture movie synthesis using statistical learningIEEE Transactions on Visualization and Computer Graphics, 2001
- Robust real-time periodic motion detection, analysis, and applicationsIeee Transactions On Pattern Analysis and Machine Intelligence, 2000
- Recognizing Facial Expressions in Image Sequences Using Local Parameterized Models of Image MotionInternational Journal of Computer Vision, 1997
- 3-D model-based tracking of humans in action: a multi-view approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Computing occluding and transparent motionsInternational Journal of Computer Vision, 1994