Video-Based Deep Learning Approach for 3D Human Movement Analysis in Institutional Hallways: A Smart Hallway

New artificial intelligence- (AI) based marker-less motion capture models provide a basis for quantitative movement analysis within healthcare and eldercare institutions, increasing clinician access to data improving decision making. This research modelled, simulated, designed, implemented novel AI motion-analysis approach institutional hallways, Smart Hallway. Computer simulations were used develop system configuration with four ceiling-mounted cameras. After implementing camera synchronization calibration methods, OpenPose was generate body keypoints each frame. BODY25 generated 2D keypoints, 3D calculated postprocessed extract outcome measures. The validated by comparing ground-truth body-segment length measurements lengths foot events detected using the system. Body-segment 1.56 (SD = 2.77) cm foot-event detection frames (67 ms), an absolute error of three (50 ms) from event labels. Hallway delivers stride parameters, limb angles, aid in clinical making, providing relevant information without user intervention extraction, thereby high-quality gait institutions.