Automated Video Quality Assessment for the Edinburgh Visual Gait Score (EVGS).

This research addresses critical challenges in clinical gait analysis by developing an automated video quality assessment framework to support Edinburgh Visual Gait Score (EVGS) scoring. The proposed methodology uses the MoveNet Lightning pose estimation model to extract body keypoints from video frames, enabling detection of multiple persons, tracking the person of interest, assessment of plane orientation, identification of overlapping individuals, detection of zoom artifacts, and evaluation of video resolution. These components are integrated into a unified quality classification system using a random forest classifier. The framework achieved high performance across key metrics, with 96% accuracy in detecting multiple persons, 95% in assessing overlaps, and 92% in identifying zoom events, culminating in an overall video quality categorization accuracy of 95%. This performance not only facilitates the automated selection of videos suitable for analysis but also provides specific video improvement suggestions when quality standards are not met. Consequently, the proposed system has the potential to streamline gait analysis workflows, reduce reliance on manual quality checks in clinical practice, and enable automated EVGS scoring by ensuring appropriate video quality as input to the gait scoring system.