TechRxiv
Joint Selection using Deep Reinforcement Learning for Skeleton-based activity recognition.pdf (506.61 kB)

Joint Selection using Deep Reinforcement Learning for Skeleton-based Activity Recognition

Download (506.61 kB)
preprint
posted on 07.07.2021, 08:24 by Bahareh Nikpour, Narges Armanfard
Skeleton based human activity recognition has attracted lots of attention due to its wide range of applications. Skeleton data includes two or three dimensional coordinates of body joints. All of the body joints are not effective in recognizing different activities, so finding key joints within a video and across different activities has a significant role in improving the performance. In this paper we propose a novel framework that performs joint selection in skeleton video frames for the purpose of human activity recognition. To this end, we formulate the joint selection problem as a Markov Decision Process (MDP) where we employ deep reinforcement learning to find the most informative joints per frame. The proposed joint selection method is a general framework that can be employed to improve human activity classification methods. Experimental results on two benchmark activity recognition data sets using three different classifiers demonstrate effectiveness of the proposed joint selection method.

History

Email Address of Submitting Author

Bahareh.nikpour@mail.mcgill.ca

Submitting Author's Institution

McGill university

Submitting Author's Country

Canada