AUTHOR=Usman Muhammad , Zhong Jianqi 

TITLE=Skeleton-based motion prediction: A survey

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 16 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2022.1051222

DOI=10.3389/fncom.2022.1051222

ISSN=1662-5188

ABSTRACT=Human motion prediction based on 3D skeleton data is an active research topic in computer vision and multimedia analysis, which involves many disciplines, such as image processing, pattern recognition, and artificial intelligence. As an effective representation of human motion, human 3D skeleton data is favored by researchers because it is not easily affected by light, scene changes, etc. Previous research on human motion prediction mainly focused on RGB data-based methods. In recent years, researchers have proposed the fusion of human skeleton data and depth learning methods for human motion prediction and achieved good results. We first introduced human motion prediction's research background and significance in this survey. We then summarized the latest deep learning-based methods for human motion prediction in recent years. Finally, a detailed paper review and future development discussion are provided.