Action Recognition using Motion Primitives

Thomas B. Moeslund, Preben Fihl, Michael Boelstoft Holte

Research output: Contribution to conference without publisher/journalPaper without publisher/journalResearch

394 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.

Original languageEnglish
Publication date2006
Number of pages10
Publication statusPublished - 2006
EventThe 15th Danish conference on pattern recognition and image analysis - Copenhagen, Denmark
Duration: 24 Aug 200625 Aug 2006
Conference number: 15


ConferenceThe 15th Danish conference on pattern recognition and image analysis


  • Human motion
  • Gesture recognition
  • Motion primitives

Fingerprint Dive into the research topics of 'Action Recognition using Motion Primitives'. Together they form a unique fingerprint.

  • Cite this

    Moeslund, T. B., Fihl, P., & Holte, M. B. (2006). Action Recognition using Motion Primitives. Paper presented at The 15th Danish conference on pattern recognition and image analysis, Copenhagen, Denmark.