VAIR: Visual Analytics for Injury Risk Exploration in Sports

2025-12-19

AI Summary

This study addresses the challenge of identifying biomechanically high-risk movements from monocular sports videos for injury prevention. We propose the first framework integrating biomechanical modeling with interpretable visual analysis: 2D pose estimation is performed using YOLO and HRNet; 3D motion reconstruction is achieved via SMPL-X; and joint torques and internal forces are simulated using OpenSim. Crucially, we introduce a spatiotemporal alignment model that explicitly links video segments to quantitative biomechanical metrics—including joint angles, angular velocities, and torques—enabling multi-view synchronized visualization and collaborative exploration. Evaluated on anterior cruciate ligament (ACL) and Achilles tendon injury cases in basketball, our method significantly improves both the efficiency of high-risk movement identification and inter-expert diagnostic agreement. Clinical validation confirms its utility for retrospective biomechanical analysis and proactive intervention planning.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Injury prevention in sports requires understanding how bio-mechanical risks emerge from movement patterns captured in real-world scenarios. However, identifying and interpreting injury prone events from raw video remains difficult and time-consuming. We present VAIR, a visual analytics system that supports injury risk analysis using 3D human motion reconstructed from sports video. VAIR combines pose estimation, bio-mechanical simulation, and synchronized visualizations to help users explore how joint-level risk indicators evolve over time. Domain experts can inspect movement segments through temporally aligned joint angles, angular velocity, and internal forces to detect patterns associated with known injury mechanisms. Through case studies involving Achilles tendon and Anterior cruciate ligament (ACL) injuries in basketball, we show that VAIR enables more efficient identification and interpretation of risky movements. Expert feedback confirms that VAIR improves diagnostic reasoning and supports both retrospective analysis and proactive intervention planning.

Problem

• Identifies injury-prone events from sports video using 3D motion reconstruction.
• Analyzes joint-level biomechanical risks through synchronized visualizations and simulations.
• Enables efficient detection of risky movements for injury prevention and intervention planning.

Innovation

• 3D motion reconstruction from sports video
• Combines pose estimation and biomechanical simulation
• Synchronized visualizations for joint-level risk analysis