Human Activities Recognisation System Using Knn Classification

Authors

  • Amandeep Kaur M.tech IT-Research Scholar, Guru Kashi University, Talwandi Sabo
  • Er. Jaspreet Kaur Assistant Professor Deptt. of CSE, Guru Kashi University, Talwandi Sabo

Keywords:

associations, human body, modeling, mental problems

Abstract

: Human action acknowledgment is an essential zone of PC vision exploration and applications. The objective of the action acknowledgment is a robotized investigation (or understanding) of progressing occasions and their connection from feature information. Its applications incorporate reconnaissance frameworks, patient observing frameworks, and a mixture of frameworks that include associations in the middle of persons and electronic gadgets, for example, human-PC interfaces. There are different problems that the previous work is only for 2D/3D pose estimation of the human body modeling. Another human activity of great interest to many researchers due to the fact that the loss of ability to walk correctly can be caused by a serious health problem, such as pain, injury, paralysis, muscle damage, or even mental problems. The video data set that we have to test and train and find the region of interest and Non-ROI part of the video and after that process the ROI part to detect the action of the human with SVM and K-NN classification and enhance the Non –ROI part of the video and find the accuracy of the detected part .

 

References

. Haoran Wang et.al “Action Recognition Using Nonnegative Action Component Representation and Sparse Basis Selection” IEEE transactions on image processing, vol. 23, no. 2, February 2014.

. Raviteja Vemulapalli et.al “Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group” IEEE -2014.

. Muhammad Shahzad Cheema et. al “Efficient Human Activity Recognition in Large Image and Video Databases”2014.

. Shian-Ru Ke et. al “ A Review on Video-Based Human Activity Recognition” computers ,ISSN 2073-431X, www.mdpi.com/journal/computers Computers 2013.

. Duong et.al “ Activity Recognition and Abnormality Detection with the Switching Hidden Semi-Markov Model” . In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA, 20–25 June 2005.

. Gorelick et.al “ Actions as Space-time Shapes”In Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV), Beijing, China, 17–21 October 2005.

. Sukthankar et.al “Spatio-temporal Shape and Flow Correlation for Action Recognition”In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, MN, USA, 17–22 June 2007.

. Yamato et.al “ Recognizing Human Action in Time-sequential Images using Hidden Markov Model” In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Champaign, IL, USA, 15–18 June 1992.

. W. Brendel et. al. “Activities as time series of human postures,” in Proc. ECCV, 2010.

.Q. V. Le et. al “Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis,” in Proc. IEEE Int. Conf. Comput. Vis. Pattern Recognit., Jun. 2011 .

Downloads

Published

30-09-2015

How to Cite

Amandeep Kaur, & Er. Jaspreet Kaur. (2015). Human Activities Recognisation System Using Knn Classification. International Journal for Research Publication and Seminar, 6(3). Retrieved from https://jrps.shodhsagar.com/index.php/j/article/view/623

Issue

Vol. 6 No. 3 (2015): Volume 6 | Issue 3 | 2015

Section

Original Research Article

License

Copyright (c) 2015 International Journal for Research Publication and Seminar

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Re-users must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. This license allows for redistribution, commercial and non-commercial, as long as the original work is properly credited.