3D Human Pose Estimation for Martial Arts Analysis through Graph Convolutional Networks

Victor H. Giron, Juan M. Chau, Anali Alfaro, Elizabeth R. Villota

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents a human pose estimation method for martial arts video analysis using a Semantic Graph Convolutional Network (SemGCN) instead of an ordinary convolutional neural network (CNN). The inputs for the model are videos from the Human3.6M dataset, in addition to the ones from Martial Arts, Dancing and Sports (MADS) dataset. A data unification process is described so that MADS joints can be adapted to the Human3.6M base setting. The performance of the model when only uses Human3.6M for training is compared to training with both Human3.6M and MADS datasets, resulting in a lower mean per-joint position error (MPJPE) for the latter. Finally, performance indicators such as the vertical position of the center of mass, balance and stability, are calculated for the MADS sequences in order to provide insights regarding martial arts execution.

Original languageEnglish
Title of host publicationFourteenth International Conference on Machine Vision, ICMV 2021
EditorsWolfgang Osten, Dmitry Nikolaev, Jianhong Zhou
PublisherSPIE
ISBN (Electronic)9781510650442
DOIs
StatePublished - 2022
Event14th International Conference on Machine Vision, ICMV 2021 - Rome, Italy
Duration: 8 Nov 202112 Nov 2021

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume12084
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference14th International Conference on Machine Vision, ICMV 2021
Country/TerritoryItaly
CityRome
Period8/11/2112/11/21

Keywords

  • dataset unification
  • graph convolutional networks
  • martial arts
  • pose estimation
  • sports performance analysis

Fingerprint

Dive into the research topics of '3D Human Pose Estimation for Martial Arts Analysis through Graph Convolutional Networks'. Together they form a unique fingerprint.

Cite this