Publication

Learning priors of human motion with vision transformers

Conference Article

Conference

IEEE International Conference on Computers, Software, and Applications (COMPSAC)

Edition

48th

Pages

382-389

Doc link

http://dx.doi.org/10.1109/COMPSAC61105.2024.00060

File

Download the digital copy of the doc pdf document

Abstract

A clear understanding of where humans move in a scenario, their usual paths and speeds, and where they stop, is very important for different applications, such as mobility studies in urban areas or robot navigation tasks within human- populated environments. We propose in this article, a neural architecture based on Vision Transformers (ViTs) to provide this information. This solution can arguably capture spatial correlations more effectively than Convolutional Neural Networks (CNNs). In the paper, we describe the methodology and proposed neural architecture and show the experiments’ results with a standard dataset. We show that the proposed ViT architecture improves the metrics compared to a method based on a CNN.

Categories

automation.

Author keywords

vision transformers, human motion prediction, semantic scene understanding, masked autoencoders, occupancy priors

Scientific reference

P. Falqueto, A. Sanfeliu, L. Palopoli and D. Fontanelli. Learning priors of human motion with vision transformers, 48th IEEE International Conference on Computers, Software, and Applications , 2024, Osaka, Japan, pp. 382-389.