AI-driven Human Motion Classification and Analysis using Laban Movement System
Table of Contents
Introduction
Human movement study:
- Health sciences (biomechanics, kinesiology, neurology, sports medicine)
- Arts (theater and dance, cultural studies)
- Intersection (arts in medicine, dance therapy)
Multi-modal datasets:
- Video
- Skeletal motion capture
- Manual annotations
- Clinical metadata
Problem Statement
Traditional Laban movement analysis (LMA):
- 4-dimensional features (shape, effort, space, body)
- Manual input from professionals
- Time-consuming
- Human errors
Objective
Creating automated Laban movement annotation:
- Training four different machine learning algorithms through supervised learning on existing human motion datasets of video and skeletal sequences
- Test feature extraction methods (within and across frames) to improve the annotation accuracy
- Input raw videos and export Laban annotated videos
Check code file AI-HumanMotionAnalysis-Test.ipynb
Acknowledgements
This project was supported by the 2020 UF AI Catalyst grant from the UF Office of Research. The authors acknowledge the University of Florida HiPerGator Research Computing for providing computational resources and support that have contributed to the research results reported in this publication.
Presentation Video
AI Research Catalyst Fund Awardees Virtual Seminar Series
Presentation Video
Cite this paper
Guo, Wenbin, Osubi Craig, Timothy Difato, James Oliverio, Markus Santoso, Jill Sonke, and Angelos Barmpoutis. (2022). AI-Driven Human Motion Classification and Analysis Using Laban Movement System. In: Duffy, V.G. (eds) Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management. Anthropometry, Human Behavior, and Communication. HCII 2022. Lecture Notes in Computer Science, vol 13319. Springer, Cham. https://doi.org/10.1007/978-3-031-05890-5_16