Underlying Injury Detection Model with High-Speed Multi-Tracking Motion Capture System

This paper introduces a novel framework for non-invasive gait analysis using a marker-based motion capture system and gait kinematic data. The system captures the 3D position of reflective markers on the human body, reconstructs the skeletal structure using inverse kinematics and probabilistic methods, detects gait events using displacement algorithms, and computes gait kinematic parameters. These parameters are used to identify and classify gait phases and patterns, and to diagnose and evaluate various injuries that impair human locomotion, such as traumatic brain injury, stroke, cerebral palsy, lower limb amputation, and spinal cord injury. The paper also explores the possibility of applying machine learning techniques for automated injury diagnosis using gait kinematic data, which would improve the diagnosis and treatment of patients with locomotor impairments, as well as foster research and innovation in biomechanics and clinical practice. The paper demonstrates the potential of this framework to revolutionize gait analysis in Vietnam, where it can enhance the quality of life and health outcomes for millions of people with locomotor impairments.