Learning and Recognizing Human Action from Skeleton Movement with Deep Residual Neural Networks

TL;DR

This paper introduces a deep residual neural network approach to recognize human actions from skeleton data transformed into images, achieving state-of-the-art results on public datasets.

Contribution

It proposes a novel method using ResNet models to learn from skeleton data converted into images, enhancing action recognition accuracy.

Findings

Achieved state-of-the-art performance on benchmark datasets.

Effectively transformed skeleton data into RGB image space for deep learning.

Demonstrated robustness across various challenging video datasets.

Abstract

Automatic human action recognition is indispensable for almost artificial intelligent systems such as video surveillance, human-computer interfaces, video retrieval, etc. Despite a lot of progress, recognizing actions in an unknown video is still a challenging task in computer vision. Recently, deep learning algorithms have proved its great potential in many vision-related recognition tasks. In this paper, we propose the use of Deep Residual Neural Networks (ResNets) to learn and recognize human action from skeleton data provided by Kinect sensor. Firstly, the body joint coordinates are transformed into 3D-arrays and saved in RGB images space. Five different deep learning models based on ResNet have been designed to extract image features and classify them into classes. Experiments are conducted on two public video datasets for human action recognition containing various challenges. The results show that our method achieves the state-of-the-art performance comparing with existing approaches.