[1]GUO Li,CAO Jiangtao,LI Ping,et al.Human action recognition based on accumulated orientation-magnitude histograms of optical flow[J].CAAI Transactions on Intelligent Systems,2014,9(1):104-108.[doi:10.3969/j.issn.1673-4785.201305001]
Copy
Human action recognition based on accumulated orientation-magnitude histograms of optical flow
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
9
Number of periods:
2014 1
Page number:
104-108
Column:
学术论文—机器学习
Public date:
2014-02-25
- Title:
- Human action recognition based on accumulated orientation-magnitude histograms of optical flow
- Keywords:
- human action recognition; Horn-Schunck optical flow; orientation-magnitude histograms; gradient histograms
- CLC:
- TP391.41
- DOI:
- 10.3969/j.issn.1673-4785.201305001
- Abstract:
- In order to improve the recognition rate and efficiency of optical flow in the human action recognition system, a novel method for human action representation based on the accumulated orientation-magnitude gradient histograms of the optical flow is proposed in this paper. First the image optical flow is computed, and then every flow vector is counted according to the orientation-magnitude to obtain orientation-magnitude histograms of single frame image. Finally information of the video sequence can be represented by accumulating orientation-magnitude histograms in time dimension. The proposed feature is evaluated on a standard database of human actions: KTH. The experiment conducted on the four scenes demonstrates that this algorithm is effective and achieves a correct recognition rate of 87.5% with the KTH dataset.
- References:
-
[1] BLANK M, GORELICK L, SHECHTMAN E, et al. Actions as space-time shapes[C]//Proceedings of the International Conference on Computer Vision. Beijing, China, 2005: 1395-1402.
[2] GORELICK L, BLANK M, SHECHTMAN E, et al. Actions as space-time shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(12): 2247-2253.
[3] YILMAZ A, SHAH M. A differential geometric approach to representing the human actions[J]. Computer Vision and Image Understanding, 2008, 119(3): 335-351.
[4] LAPTEV I, LINDEBERG T. Space-time interest points[C]//Proceedings of the International Conference on Computer Vision. Nice, France, 2003: 432-439.
[5] LAPTEV I, CAPUTO B, SCHVLDT C, et al. Local velocity-adapted motion events for spatio-temporal recognition[J]. Computer Vision and Image Understanding, 2007, 108(3): 207-229.
[6] OIKONOMOPOULOS A, PATRAS I, PANTIC M. Spatiotemporal salient points for visual recognition of human actions[J]. IEEE Transactions on Systems Man and Cybernetics-Part B: Cybernetics, 2006, 36(3): 710-719.
[7] DANAFAR S, GHEISSARI N. Action recognition for surveillance applications using optic flow and SVM[C]//Proceedings of the Asian Conference on Computer Vision. Tokyo, Japan, 2007: 457-466.
[8] TRAN D, SOROKIN A. Human activity recognition with metric learning[C]//Proceedings of the European Conference on Computer Vision. Marseille, France, 2008: 61-66.
[9] ZHANG Ziming, HU Yiqun, CHAN Syin, et al. Motion context: a new representation for human action recognition[C]//Proceedings of the European Conference on Computer Vision. Marseille, France, 2008: 817-829.
[10] FAN Rongen, CHEN Paihsuen, LIN Chihjen. Working set selection using second order information for training SVM[J]. Journal of Machine Learning Research, 2005, 6: 1889-1918.
[11] LIU Jingen, LUO Jiebo, SHAN M. Recognizing realistic actions from videos "in the wild"[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA, 2009: 1996-2003.
[12] QIN Yaohui, LI Hongliang, LIU Guanghui, et al. Human action recognition using PEM histogram[C]//IEEE International Conference on Computational Problem Solving. Singapore, 2010: 323-325.
- Similar References:
Memo
-
Last Update:
1900-01-01