Action Recognition using Motion Primitives

Thomas B. Moeslund, Preben Fihl, Michael Boelstoft Holte

Publikation: Konferencebidrag uden forlag/tidsskriftPaper uden forlag/tidsskriftForskning

403 Downloads (Pure)


The number of potential applications has made automatic recognition of human actions a very active research area. Different approaches have been followed based on trajectories through some state space. In this paper we also model an action as a trajectory through a state space, but we represent the actions as a sequence of temporal isolated instances, denoted primitives. These primitives are each defined by four features extracted from motion images. The primitives are recognized in each frame based on a trained classifier resulting in a sequence of primitives. From this sequence we recognize different temporal actions using a probabilistic Edit Distance method. The method is tested on different actions with and without noise and the results show recognizing rates of 88.7% and 85.5%, respectively.

Antal sider10
StatusUdgivet - 2006
BegivenhedThe 15th Danish conference on pattern recognition and image analysis - Copenhagen, Danmark
Varighed: 24 aug. 200625 aug. 2006
Konferencens nummer: 15


KonferenceThe 15th Danish conference on pattern recognition and image analysis

Fingeraftryk Dyk ned i forskningsemnerne om 'Action Recognition using Motion Primitives'. Sammen danner de et unikt fingeraftryk.