Mixed Features Based Improved Human Action Recognition Algorithm

Abstract:

The choice of the motion features affects the result of the human action recognition method directly. Many factors often influence the single feature differently, such as appearance of human body, environment and video camera. So the accuracy of action recognition is limited. On the basis of studying the representation and recognition of human actions, and giving full consideration to the advantages and disadvantages of different features, this paper proposes a mixed feature which combines global silhouette feature and local optical flow feature. This combined representation is used for human action recognition.

• Periodical: Advanced Materials Research (Volumes 989-994)
• Pages: 2731-2734
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.989-994.2731
• Online since: July 2014
• Authors: Hai Long Jia*, Kun Cao
• Keywords: Action Recognition, Improved Algorithm, Leave One out, Mixed Characteristics, Optical Flows, Silhouette

References

[1] ZHU G, XU C. Action recognition in broadcast tennis video[C] Proceedings of the 18th International Conference on Pattern Recognition, Hong Kong, China, NJ: IEEE, Press, 2006: 251-254.

DOI: 10.1109/icpr.2006.205

[2] Yi yang, Jianguo Xing. Human Action Recognition Algorithm based on Minimum Spanning Tree of CPA Models [J]. Journal of Software, 2010, 7(7): 1577–1584.

DOI: 10.4304/jsw.7.7.1577-1584

[3] Ling Gan, Fu Chen. Human Action Recognition using APJ3D and Random Forests [J]. Journal of Software, 2013, 8(9): 2238–2245.

DOI: 10.4304/jsw.8.9.2238-2245

[4] WANG L, SUTER D. Recognizing human activities from silhouettes: motion subspace and factorial discriminative graphical model[C]Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Minnesota, USA, NJ: IEEE, Press, 2007: 1−8.R. Nicole, Title of paper with only first word capitalized, J. Name Stand. Abbrev., in press.

DOI: 10.1109/cvpr.2007.383298

[5] Dedeoğlu Y, A Silhouette-based method for object classification and human action recognition in video[C]Proceedings of the European Conference on Computer Vision, Graz, Austria, N J: IEEE, Press, 2006: 64- 77.

DOI: 10.1007/11754336_7

[6] GRITAI A, SHEIKH Y, SHAH M．On the use of anthropometry in the invariant analysis of human actions[C] Proceedings of the 17th International IEEE Conference on Pattern Recognition (ICPR) , Cambridge , UK, NJ: IEEE, Press, 2004, Ⅱ: 923－926.

DOI: 10.1109/icpr.2004.1334410