A Level Set Approach on Human Action Prediction

A Level Set Approach on Human Action Prediction

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2017 by IJETT Journal
Volume-47 Number-1
Year of Publication : 2017
Authors : M. Sushma Sri
DOI :  10.14445/22315381/IJETT-V47P204

Citation 

M. Sushma Sri "A Level Set Approach on Human Action Prediction", International Journal of Engineering Trends and Technology (IJETT), V47(1),32-35 May 2017. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group

Abstract
Human activity prediction is a challenging task. The aim of this paper is to track the human motion and probabilistically predict the future action of the target. This is done in three ways detect the target, estimate the direction and then predict the future action. We employ K-means algorithm which results were not very encouraged hence we shifted to level sets for better target localization. A probabilistic approach is used to estimate the direction of motion. MAP estimator is implemented to estimate the direction of the object motion. The results of estimated directions are used to predict the position of the object in future frames.

 References

[1] Adnan khashman, “ Automatic detection, extraction and recognition of moving objects”. International journal of systems applications, engineering & development . Issue 1, volume 2, 2008.
[2] Anil Z Chitade, “colour based image segmentation using kmeans Clustering”. International Journal of Engineering Science and Technology Vol. 2(10), 2010, 5319-5325.
[3] Chan Tony F, Vese Lumanita A, “Active contours without edge”, IEEE Trans. “On Image processing”, 10(2): 266-277, 2001.
[4] D.Waltisberg, A. Yao, J. Gall, and L.V.Gool, “Variations of a Hough- voting action recognition system”. In ICPR Contest on Semantic Sescription of Human Activities (SDHA), in Proceedings of ICPR Contests, 2010.
[5] F. Yuan, V. Prinet, and J. Yuan, “Middle-level representation for human activities recognition: the role of spatio-temporal relationships”. In ECCV Workshop on Human Motion: Understanding, Modeling, Capture and Animation, 2010.
[6] Mario F. Triola, Bayes` Theorem.
[7] M. Airouche, L. Bentabet and M. Zelmat, “Image Segmentation Using Active Contour Model and Level Set Method Applied to Detect Oil Spills”,Proceedings of the World Congress on Engineering 2009 Vol I WCE 2009, July 1 - 3, 2009, London, U.K.
[8] M.S. Ryoo and J.K. Aggarwal, “UT-Interaction Dataset”, ICPR Contest on semantic Description of Human Activities (SDHA), 2010.
[9] M. S. Ryoo, C.C. Chen, J. K. Aggarwal, and A. Roy- Chowdhury, “An overview of contest on semantic description of human activities (SDHA)”. in Proceedings of ICPR Contests, 2010.
[10]Tapas Kanungo, David M. Mount, Nathan S. Netanyahu, Christine D. Piatko, Ruth Silverman, and Angela Y. Wu, “An Efficient k- Means Clustering Algorithm: Analysis and Implementation”. IEEE transactions on pattern analysis and machine intelligence, vol. 24, no. 7, July 2002.
[11] Thomas Brox and Joachim Weickert, “Level Set Based Image Segmentation with Multiple Regions”. In Pattern Recognition, Springer LNCS 3175, C.E. Rasmussen, H. Bulthoff, M. Giese, and BScholkopf (Eds.), pp. 415-423, Tubingen, Germany, Aug. 2004.
[12] Yonggang Shi, W.Clem Karl, “Real-time Tracking Using Level Sets”. CVPR`05.

Keywords
Direction estimation, K-mean clustering, Level sets, Prediction, Target localization.