Journal of Korea Multimedia Society (한국멀티미디어학회논문지)

Korea Multimedia Society (한국멀티미디어학회)
권호 표지
DOI QR코드

DOI QR Code

Improved DT Algorithm Based Human Action Features Detection

  • Hu, Zeyuan (Dept. of Information Communication Engineering, Tongmyong University) ;
  • Lee, Suk-Hwan (Dept. of Information Security Engineering, Tongmyong University) ;
  • Lee, Eung-Joo (Dept. of Information Communication Engineering, Tongmyong University)
  • Received : 2018.03.08
  • Accepted : 2018.04.10
  • Published : 2018.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

The choice of the motion features influences the result of the human action recognition method directly. Many factors often influence the single feature differently, such as appearance of the human body, environment and video camera. So the accuracy of action recognition is restricted. On the bases of studying the representation and recognition of human actions, and giving fully consideration to the advantages and disadvantages of different features, the Dense Trajectories(DT) algorithm is a very classic algorithm in the field of behavior recognition feature extraction, but there are some defects in the use of optical flow images. In this paper, we will use the improved Dense Trajectories(iDT) algorithm to optimize and extract the optical flow features in the movement of human action, then we will combined with Support Vector Machine methods to identify human behavior, and use the image in the KTH database for training and testing.

Keywords

References

  1. J.K. Aggarwal, and M.S. Ryoo, "Human Activity Analysis: A Review," Journal of Association for Computing Machinery(ACM) Computing Surveys, Vol. 43, No. 3, pp. 102-145, 2011.
  2. H. Wang, and C. Schmid, "Action Recognition with Improved Trajectories," Proceeding of IEEE International Conference on Computer Vision, pp. 3551-3558, 2013.
  3. I. Laptev, M. Marszalek, C. Schmid, and B. Rozenfeld, "Learning Realistic Human Actions from Movies," Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2008.
  4. H. Kuehne, H. Jhuang, E. Garrote, T. Poggio, and T. Serre, "HMDB: A Large Video Database for Human Motion Recognition," Proceeding of International Conference on Computer Vision, pp. 2556-2563, 2011.
  5. K. Soomro, A.R. Zamir, and M. Shah, UFC101: A Dataset of 101 Human Actions Classes From Videos in The Wild, Master's Thesis of Cornell University, 2012.
  6. K.G. Cho, "A Human Action Recognition Scheme in Temporal Spatial Data for Intelligent Web Browser," Journal of Korea Multimedia Society, Vol. 8, No. 6, pp. 844-855, 2005.
  7. A. Patron-Perez, M. Marszalek, I. Reid, and A. Zisserman, "Structured Learning of Human Interactions in TV Shows," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 2441-2453, 2012.
  8. L.B. Truong, S.H. Kim, and G.M. Jeong, "Pattern Recognition with feature feedback: Feature Mask By Using PCA," Proceeding of Conference on Korea Multimedia Society, pp. 14-16, 2010.
  9. Z. Guangyu, X. Changsheng, H. Qingming, and G. Wen, "Action Recognition in Broadcast Tennis Video," Proceeding of the 18th International IEEE Conference on Pattern Recognition, pp. 251-254, 2006.
  10. A. Gritai, Y. Sheikh, and M. Shah, "On the Use of Anthropometry in the Invariant Analysis of Human Actions," Proceeding of the 17th International IEEE Conference on Pattern Recognition, pp. 923-926, 2004.
  11. W. Liang, and D. Suter, "Recognizing Human Activities from Silhouette: Motion Subspace and Factorial Discriminative Graphical Model," Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2007.
  12. M. Ahmad, and S.W. Lee, "Human Action Recognition Using Shape and CLG-motion Flow from Multi-view Image Sequences," Journal of Pattern Recognition, Vol. 41, No. 7, pp. 2237-2252, 2008. https://doi.org/10.1016/j.patcog.2007.12.008
  13. N. Sawant, and K.K. Biswa, "Human Action Recognition Based on Spatio-temporal Feature," Proceeding of International Conference on Pattern Recognition and Machine Intelligence, pp. 357-362, 2009.