Multi‐feature gait analysis approach using deep learning in constraint‐free environment

Abstract

AbstractA quantitative gait assessment system is crucial for clinical analysis and decision‐making. Such rigorous evaluation involves costly clinical setups and domain experts for observation and analysis. To circumvent such constraints, the proposed work is conducted in a markerless environment and divided into three stages: First, we prepared a markerless gait database using videos from MNIT RAMAN LABORATORY in Jaipur. Second, we adapt the skeletal landmark data to generate kinematic gait characteristics comparable to gold‐standard marker‐based techniques. We provide a novel set of parameters based on video sequences and spatiotemporal and sagittal kinematic parameters to optimize accuracy and reliability. Third, we develop multi‐feature based gait analysis, an ensemble model based on Convolutional Neural Networks + LSTM (Long‐Short Term Memory), for gait classification. In addition, we deployed transfer learning models to correlate with our ensemble model. The findings indicate that gait analysis can be used successfully in a low‐cost clinical gait monitoring system in a constraint‐free environment. While considering the multiple gait variables, our proposed model attained an accuracy of 95.3%. Our model for quantifying gait analysis will improve access to quantitative gait analysis in clinics and rehabilitation centers and enable researchers to conduct large‐scale studies for gait‐related disorders.