Article: Multimodal pose estimation and simulation modelling for real-time human motion analysis Journal: International Journal of Simulation and Process Modelling (IJSPM) 2025 Vol.22 No.5 pp.1 - 10 Abstract: To ensure safe and effective campus physical activities, this pioneering study proposes an innovative real-time sports pose recognition framework integrated with simulation-oriented process modelling, aligning with the core scope of dynamic motion analysis. The framework features a sophisticated multimodal architecture that fuses visual and inertial data across four interconnected layers, while embedding simulation-driven process modelling to capture the spatiotemporal dynamics of human motion. Enhanced spatiotemporal alignment mechanisms enable precise extraction of key biomechanical features, which are further refined through optimised Relief F algorithm for critical motion feature selection. A particle swarm-optimised graph convolutional network (PSO-AGCN) leverages simulated motion topology variations to process these features efficiently for pose classification. Evaluations on Human3.6M and a college sports dataset show 96.7% accuracy, 42.3% reduced occlusion errors, and 38 FPS operation, highlighting robustness and real-time performance, with simulation enhancing analysis interpretability. Inderscience Publishers - linking academia, business and industry through research

Title: Multimodal pose estimation and simulation modelling for real-time human motion analysis

Authors: Dongsheng Chen; Zhen Ni; Wei Huang

Addresses: School of Sports and Health, Guangxi College for Preschool Education, Guangxi 530022, China ' School of Physical Education and Health, Nanning Normal University, Nanning 530001, China ' School of Sports and Health, Guangxi College for Preschool Education, Guangxi 530022, China

Abstract: To ensure safe and effective campus physical activities, this pioneering study proposes an innovative real-time sports pose recognition framework integrated with simulation-oriented process modelling, aligning with the core scope of dynamic motion analysis. The framework features a sophisticated multimodal architecture that fuses visual and inertial data across four interconnected layers, while embedding simulation-driven process modelling to capture the spatiotemporal dynamics of human motion. Enhanced spatiotemporal alignment mechanisms enable precise extraction of key biomechanical features, which are further refined through optimised Relief F algorithm for critical motion feature selection. A particle swarm-optimised graph convolutional network (PSO-AGCN) leverages simulated motion topology variations to process these features efficiently for pose classification. Evaluations on Human3.6M and a college sports dataset show 96.7% accuracy, 42.3% reduced occlusion errors, and 38 FPS operation, highlighting robustness and real-time performance, with simulation enhancing analysis interpretability.

Keywords: multimodal pose estimation; simulation modelling; real-time motion analysis; graph convolutional networks; sports simulation; campus sports analytics.

DOI: 10.1504/IJSPM.2025.149326

International Journal of Simulation and Process Modelling, 2025 Vol.22 No.5, pp.1 - 10

Received: 03 Jul 2025
Accepted: 28 Aug 2025
Published online: 24 Oct 2025 *

Title: Multimodal pose estimation and simulation modelling for real-time human motion analysis

Keep up-to-date