Human action detection using PNF propagation of temporal constraints

@inproceedings{Pinhanez1998-HAD, abstract = {In this paper we develop a representation for the temporal structure inherent in human actions and demonstrate an effective method for using that representation to detect the occurrence of actions. The temporal structure of the action, sub-actions, events, and sensor information is described using a constraint network based on Allen's interval algebra. We map these networks onto a simpler, S-valued domain (past, now, fut) network-a PNF-network-to allow fast detection of actions and sub-actions. The occurrence of an action is computed by considering the minimal domain of its PNF-network, under constraints imposed by the current state of the sensors and the previous states of the network. We illustrate the approach with examples, showing that a major advantage of PNF propagation is the detection and removal of in-consistent situations}, author = {Pinhanez, C. S. and Bobick, A. F. }, booktitle = {Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on}, citeulike-article-id = {2308456}, doi = {http://dx.doi.org/10.1109/CVPR.1998.698711}, journal = {Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on}, keywords = {action, constraint, events, networks, vision}, pages = {898--904}, posted-at = {2008-01-30 20:45:02}, priority = {2}, title = {Human action detection using PNF propagation of temporal constraints}, url = {http://dx.doi.org/10.1109/CVPR.1998.698711}, year = {1998} }

TY - CONF ID - Pinhanez1998-HAD L3 - citeulike-article-id:2308456 TI - Human action detection using PNF propagation of temporal constraints T2 - Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on JF - Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on SP - 898 EP - 904 N2 - In this paper we develop a representation for the temporal structure inherent in human actions and demonstrate an effective method for using that representation to detect the occurrence of actions. The temporal structure of the action, sub-actions, events, and sensor information is described using a constraint network based on Allen's interval algebra. We map these networks onto a simpler, S-valued domain (past, now, fut) network-a PNF-network-to allow fast detection of actions and sub-actions. The occurrence of an action is computed by considering the minimal domain of its PNF-network, under constraints imposed by the current state of the sensors and the previous states of the network. We illustrate the approach with examples, showing that a major advantage of PNF propagation is the detection and removal of in-consistent situations KW - action KW - constraint KW - events KW - networks KW - vision AU - Pinhanez, CS AU - Bobick, AF PY - 1998/// UR - http://dx.doi.org/10.1109/CVPR.1998.698711 ER -