Markerless gait estimation and tracking for postural assessment

Abstract

Postural assessment is crucial in the sports screening system to reduce the risk of severe injury. The capture of the athlete’s posture using computer vision attracts huge attention in the sports community due to its markerless motion capture and less interference in the physical training. In this paper, a novel markerless gait estimation and tracking algorithm is proposed to locate human key-points in spatial-temporal sequences for gait analysis. First, human pose estimation using OpenPose network to detect 14 core key-points from the human body. The ratio of body joints is normalized with neck-to-pelvis distance to obtain camera invariant key-points. These key-points are subsequently used to generate a spatial-temporal sequences and it is fed into Long-Short-Term-Memory network for gait recognition. An indexed person is tracked for quick local pose estimation and postural analysis. This proposed algorithm can automate the capture of human joints for postural assessment to analyze the human motion. The proposed system is implemented on Intel Up Squared Board and it can achieve up to 9 frames-per-second with 95% accuracy of gait recognition.

Integrating OpenPose and SVM for Quantitative Postural Analysis in Young Adults: A Temporal-Spatial Approach

“…Researchers have used SVM to extract insights from video data, deepening understanding of human movement and balance dynamics. Additionally, SVM have advanced automated systems for analyzing walking videos, aiding in identifying abnormal movements and improving medical diagnostics, sports performance evaluation, and rehabilitation strategies [ 15 , 16 , 17 , 18 ]. The integration of SVM with deep learning algorithms such as Openpose has further enhanced the accuracy and robustness of postural control analysis, paving the way for continued advancements in this field.…”

Internet-of-Things-Enabled Markerless Running Gait Assessment from a Single Smartphone Camera

“…In the referenced studies, both spatial [ 20 , 21 , 22 ] and temporal [ 21 ] outcomes are evaluated with generally positive results. In contrast, there are significantly fewer developments for running gait with 2D pose estimation, although the use of OpenPose has demonstrated an ability to examine cadence [ 23 ]. Yet, within running gait, there are a significantly higher number of relevant outcomes to inform, e.g., performance optimization such as contact time, swing time, and knee flexion angle [ 24 , 25 ].…”