Spatio-Temporal Encoding and Decoding-Based Method for Future Human Activity Skeleton Synthesis

TL;DR

This paper introduces a spatio-temporal encoding-decoding approach for synthesizing future human activity skeletons, emphasizing efficiency and accuracy over traditional GAN-based methods.

Contribution

It presents a novel encoding-decoding framework that reduces computational costs and improves prediction accuracy for future skeleton sequences.

Findings

Outperforms existing algorithms in skeleton prediction accuracy

Generates sequences with smaller errors and fewer parameters

Enhances early activity prediction capabilities

Abstract

Inferring future activity information based on observed activity data is a crucial step to improve the accuracy of early activity prediction. Traditional methods based on generative adversarial networks(GAN) or joint learning frameworks can achieve good prediction accuracy under low observation ratios, but they usually have high computational costs. In view of this, this paper proposes a spatio-temporal encoding and decoding-based method for future human activity skeleton synthesis. Firstly, algorithms such as time control, discrete cosine transform, and low-pass filtering are used to cut or pad the skeleton sequences. Secondly, the encoder and decoder are responsible for extracting intermediate semantic encoding from observed skeleton sequences and inferring future sequences from the intermediate semantic encoding, respectively. Finally, joint displacement error, velocity error, and acceleration error, three higher-order kinematic features, are used as key components of the loss function to optimize model parameters. Experimental results show that the proposed future skeleton synthesis algorithm performs better than some existing algorithms. It generates skeleton sequences with smaller errors and fewer model parameters, effectively providing future information for early activity prediction.