Browse > Article

Spatial-Temporal Scale-Invariant Human Action Recognition using Motion Gradient Histogram  

Kim, Kwang-Soo (현대자동차 CL사업부)
Kim, Tae-Hyoung (LG전자 MC사업부)
Kwak, Soo-Yeong (연세대학교 컴퓨터과학과)
Byun, Hye-Ran (연세대학교 컴퓨터과학과)
Publication Information
Journal of KIISE:Software and Applications / v.34, no.12, 2007 , pp. 1075-1082 More about this Journal
Abstract
In this paper, we propose the method of multiple human action recognition on video clip. For being invariant to the change of speed or size of actions, Spatial-Temporal Pyramid method is applied. Proposed method can minimize the complexity of the procedures owing to select Motion Gradient Histogram (MGH) based on statistical approach for action representation feature. For multiple action detection, Motion Energy Image (MEI) of binary frame difference accumulations is adapted and then we detect each action of which area is represented by MGH. The action MGH should be compared with pre-learning MGH having pyramid method. As a result, recognition can be done by the analyze between action MGH and pre-learning MGH. Ten video clips are used for evaluating the proposed method. We have various experiments such as mono action, multiple action, speed and site scale-changes, comparison with previous method. As a result, we can see that proposed method is simple and efficient to recognize multiple human action with stale variations.
Keywords
Action recognition; Multiple action detection; Motion gradient histogram; Motion energy image;
Citations & Related Records
연도 인용수 순위
  • Reference
1 I.Haritaoglu, D.Harwood, L.S.Davis, 'W4:real-time surveillance of people and their activities,' IEEE Trans. on Pattern Analysis and Machine Intelligence, 22(8), 2000, pp. 809-830   DOI   ScienceOn
2 A.Efros, A.Berg, G.Mori and J.Malik, 'Recognizing action at a distance,' IEEE International Conference on Computer Vision, Vol.2, pp. 726-733, 2003
3 Y.Yacoob and M.J.Black, 'Parameterized modeling and recognition of activities,' Journal of Computer Vision and Image Understanding 73(2):pp. 232-247, 1999   DOI   ScienceOn
4 A.Bobick and J.Davis, 'The recognition of human movement using temporal templates,' IEEE Pattern Analysis and Machine Intelligence, 23(3):pp. 257-267, 2001   DOI   ScienceOn
5 Alex Pentland, 'Looking at people: sensing for ubiquitous and wearable computing,' IEEE Trans. on Pattern Analysis and Machine Intelligence, 22(1), 2000, pp. 107-119   DOI   ScienceOn
6 Shearer, Bunke., Venkatesh, 'Video indexing and similarity retrieval by largest common subgraph detection using decision trees,' Pattern Recognition 34, 2001, pp. 1075-1091   DOI   ScienceOn
7 M.Yang, N.Ahuja, and M.Tabb, 'Extraction of 2D motion trajectories and its application to hand gesture recognition,' IEEE Trans. on Pattern Analysis and Machine Intelligence, 24(8):pp. 1061-1074, 2002   DOI   ScienceOn
8 S.X.Ju, M.J.Black, and Y.Yacoob, 'Cardboard people: A parameterized model of articulated image motion,' In 2nd Int. Conf. On Automatic Face and Gesture Recognition, pp. 38-44, Oct. 1996
9 M.Blank, L,Gorelick, E,Shechtman, M.Irani and R. Basri, 'Actions as Space-Time Shapes,' IEEE International Conference on Computer Vision, pp. 1395-1402, 2005
10 E. Shechtman and M. Irani, 'Space-Time Behavioral Correlation,' IEEE Conference on Computer Vision and Pattern Recognition, Vol.1, pp. 405-412, 2005
11 L.Zelnik Manor and M.Irani, 'Event-based analysis of video,' IEEE Conference on Computer Vision and Pattern Recognition, Vol.2, pp. 123-130, 2001