Human Action prediction based on skeleton data

Abstract

Human behavior prediction is an interdisciplinary research direction, involving image processing, computer vision, pattern recognition, machine learning, and artificial intelligence, which is one of the important research topics in the field of computer vision. This paper introduces a model for predicting human skeletal motion sequence, which is composed of LSTM main network and structured prediction layer. We have verified its performance on h3.6m dataset, and this structure has achieved good results in the short-term prediction of human motion.