Machine Learning based 2D Pose Estimation Model for Human Action Recognition using Geometrical Maps
M.V.D. Prasad1, K. Durga Bhavani2, S. M. Tharun Kumar3, P.V.V. Kishore4, M. Teja Kiran Kumar5, E. Kiran Kumar6, D. Anil Kumar7
1M.V.D. Prasad, Department Name, University/ College/ Organization Name, City Name, Country Name.
2K. Durga Bhavani, Department Name, University/ College/ Organization Name, City Name, Country Name.
3S. M. Tharun Kumar, Department Name, University/ College/ Organization Name, City Name, Country Name.
4P.V.V. Kishore, Department Name, University/ College/ Organization Name, City Name, Country Name.
5M. Teja Kiran Kumar, Department Name, University/ College/ Organization Name, City Name, Country Name.
6E. Kiran Kumar, Department Name, University/ College/ Organization Name, City Name, Country Name.
7D. Anil Kumar, Department Name, University/ College/ Organization Name, City Name, Country Name.
Manuscript received on 02 June 2019 | Revised Manuscript received on 10 June 2019 | Manuscript published on 30 June 2019 | PP: 1127-1130 | Volume-8 Issue-8, June 2019 | Retrieval Number: H6594068819/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Human action recognition has been a most emerging topic in computer vision because of its several applications like surveillance cameras, human machine interaction and video retrieval. Later human action recognition got better results using machine learning algorithms when compared to computer vision algorithms. In next level pose estimation technique has been introduced and it has drawn more attention for its ability to segment a human body and for detection of joints. Now, in this paper we are developing a human action recognition framework using pose estimation to extract geometrical features and these features are inputted to a sequential convolution neural network for recognizing action performed by the subjects.
Keyword: Human action recognition, machine learning algorithms, pose estimation, sequential convolution neural network.
Scope of the Article: Machine Learning.