Fall Risk and Gait Analysis in Community-Dwelling Older Adults using World-Spaced 3D Human Mesh Recovery

2026-04-13

AI Summary

This study addresses the limitations of traditional clinical gait assessment, which relies on manual timing and struggles to objectively and efficiently identify fall risk among older adults in community settings. For the first time, it applies 3D human mesh reconstruction (HMR) in world coordinates to real-world community scenarios, automatically extracting spatiotemporal gait parameters from Timed Up-and-Go test videos to enable non-invasive, ecologically valid fall risk evaluation. Through multimodal validation by fusing video data with inertial measurement unit (IMU) measurements, the proposed method demonstrates significant correlation with IMU-derived step duration. Furthermore, shorter step length, higher gait variability, and longer sit-to-stand transition time are significantly associated with self-reported fall risk and fear of falling, thereby overcoming the constraints of laboratory-based protocols or wearable device dependency.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

Abstract

Gait assessment is a key clinical indicator of fall risk and overall health in older adults. However, standard clinical practice is largely limited to stopwatch-measured gait speed. We present a pipeline that leverages a 3D Human Mesh Recovery (HMR) model to extract gait parameters from recordings of older adults completing the Timed Up and Go (TUG) test. From videos recorded across different community centers, we extract and analyze spatiotemporal gait parameters, including step time, sit-to-stand duration, and step length. We found that video-derived step time was significantly correlated with IMU-based insole measurements. Using linear mixed effects models, we confirmed that shorter, more variable step lengths and longer sit-to-stand durations were predicted by higher self-rated fall risk and fear of falling. These findings demonstrate that our pipeline can enable accessible and ecologically valid gait analysis in community settings.

Problem

• Fall Risk
• Gait Analysis
• Older Adults
• Timed Up and Go
• 3D Human Mesh Recovery

Innovation

• 3D Human Mesh Recovery
• gait analysis
• fall risk assessment
• Timed Up and Go test
• ecological validity