International Journal of Computer Vision

, Volume 103, Issue 1, pp 60–79

Dense Trajectories and Motion Boundary Descriptors for Action Recognition

  • Heng Wang
  • Alexander Kläser
  • Cordelia Schmid
  • Cheng-Lin Liu
Article

DOI: 10.1007/s11263-012-0594-8

Cite this article as:
Wang, H., Kläser, A., Schmid, C. et al. Int J Comput Vis (2013) 103: 60. doi:10.1007/s11263-012-0594-8

Abstract

This paper introduces a video representation based on dense trajectories and motion boundary descriptors. Trajectories capture the local motion information of the video. A dense representation guarantees a good coverage of foreground motion as well as of the surrounding context. A state-of-the-art optical flow algorithm enables a robust and efficient extraction of dense trajectories. As descriptors we extract features aligned with the trajectories to characterize shape (point coordinates), appearance (histograms of oriented gradients) and motion (histograms of optical flow). Additionally, we introduce a descriptor based on motion boundary histograms (MBH) which rely on differential optical flow. The MBH descriptor shows to consistently outperform other state-of-the-art descriptors, in particular on real-world videos that contain a significant amount of camera motion. We evaluate our video representation in the context of action classification on nine datasets, namely KTH, YouTube, Hollywood2, UCF sports, IXMAS, UIUC, Olympic Sports, UCF50 and HMDB51. On all datasets our approach outperforms current state-of-the-art results.

Keywords

Action recognition Dense trajectories Motion boundary histograms 

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Heng Wang
    • 1
  • Alexander Kläser
    • 2
  • Cordelia Schmid
    • 2
  • Cheng-Lin Liu
    • 1
  1. 1.National Laboratory of Pattern Recognition, Institute of AutomationChinese Academy of SciencesBeijingChina
  2. 2.LEAR TeamINRIA Grenoble Rhône-AlpesMontbonnotFrance

Personalised recommendations