Behaviour Understanding in Video: A Combined Method Export

@inproceedings{citeulike:4716395, abstract = {In this paper we develop a system for human behaviour recognition in video sequences. Human behaviour is modelled as a stochastic sequence of actions. Actions are described by a feature vector comprising both trajectory information (position and velocity), and a set of local motion descriptors. Action recognition is achieved via probabilistic search of image feature databases representing previously seen actions. A HMM which encodes the rules of the scene is used to smooth sequences of actions. High-level behaviour recognition is achieved by computing the likelihood that a set of predefined Hidden Markov Models explains the current action sequence. Thus, human actions and behaviour are represented using a hierarchy of abstraction: from simple actions, to actions with spatio-temporal context, to action sequences and finally general behaviours. While the upper levels all use (parametric) Bayes networks and belief propagation, the lowest level uses non-parametric sampling from a previously learned database of actions. The combined method represents a general framework for human behaviour modelling. In this paper we demonstrate the results chiefly on broadcast tennis sequences for automated video annotation.}, address = {Washington, DC, USA}, author = {Robertson, Neil and Reid, Ian}, booktitle = {ICCV '05: Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1}, citeulike-article-id = {4716395}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1097727}, citeulike-linkout-1 = {http://dx.doi.org/10.1109/ICCV.2005.47}, doi = {10.1109/ICCV.2005.47}, isbn = {0-7695-2334-X-01}, keywords = {aal}, pages = {808--815}, posted-at = {2009-06-02 09:45:24}, priority = {2}, publisher = {IEEE Computer Society}, title = {Behaviour Understanding in Video: A Combined Method}, url = {http://dx.doi.org/10.1109/ICCV.2005.47}, year = {2005} }

TY - CONF ID - citeulike:4716395 L3 - citeulike-article-id:4716395 N2 - In this paper we develop a system for human behaviour recognition in video sequences. Human behaviour is modelled as a stochastic sequence of actions. Actions are described by a feature vector comprising both trajectory information (position and velocity), and a set of local motion descriptors. Action recognition is achieved via probabilistic search of image feature databases representing previously seen actions. A HMM which encodes the rules of the scene is used to smooth sequences of actions. High-level behaviour recognition is achieved by computing the likelihood that a set of predefined Hidden Markov Models explains the current action sequence. Thus, human actions and behaviour are represented using a hierarchy of abstraction: from simple actions, to actions with spatio-temporal context, to action sequences and finally general behaviours. While the upper levels all use (parametric) Bayes networks and belief propagation, the lowest level uses non-parametric sampling from a previously learned database of actions. The combined method represents a general framework for human behaviour modelling. In this paper we demonstrate the results chiefly on broadcast tennis sequences for automated video annotation. SN - 0-7695-2334-X-01 AD - Washington, DC, USA EP - 815 TI - Behaviour Understanding in Video: A Combined Method PB - IEEE Computer Society T2 - ICCV '05: Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 SP - 808 KW - aal AU - Robertson, Neil AU - Reid, Ian PY - 2005/// UR - http://dx.doi.org/10.1109/ICCV.2005.47 ER -