The Community for Technology Leaders
2008 IEEE Conference on Computer Vision and Pattern Recognition (2008)
Anchorage, AK, USA
June 23, 2008 to June 28, 2008
ISBN: 978-1-4244-2242-5
pp: 1-8
Shiv N. Vitaladevuni , Janelia Farm Research Campus, Howard Hughes Medical Institute, Ashburn VA 20147, U.S.A.
Vili Kellokumpu , Machine Vision Group, Univ. of Oulu, Finland
Larry S. Davis , Computer Vision Lab., Univ. of Maryland, College Park, U.S.A.
We present a Bayesian framework for action recognition through ballistic dynamics. Psycho-kinesiological studies indicate that ballistic movements form the natural units for human movement planning. The framework leads to an efficient and robust algorithm for temporally segmenting videos into atomic movements. Individual movements are annotated with person-centric morphological labels called ballistic verbs. This is tested on a dataset of interactive movements, achieving high recognition rates. The approach is also applied on a gesture recognition task, improving a previously reported recognition rate from 84% to 92%. Consideration of ballistic dynamics enhances the performance of the popular Motion History Image feature. We also illustrate the approach’s general utility on real-world videos. Experiments indicate that the method is robust to view, style and appearance variations.

L. S. Davis, S. N. Vitaladevuni and V. Kellokumpu, "Action recognition using ballistic dynamics," 2008 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Anchorage, AK, USA, 2008, pp. 1-8.
101 ms
(Ver 3.3 (11022016))