SR-POSE: A Novel Non-Contact Real-Time Rehabilitation Evaluation Method Using Lightweight Technology

Rehabilitation movement assessment often requires patients to wear expensive and inconvenient sensors or optical markers. To address this issue, we propose a non-contact and real-time approach using a lightweight pose detection algorithm-Sports Rehabilitation-Pose (SR-Pose), and a depth camera for a...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on neural systems and rehabilitation engineering 2023, Vol.31, p.4179-4188
Main Authors: Zhang, Kun, Zhang, Pengcheng, Tu, Xintao, Liu, Zhicheng, Xu, Peixia, Wu, Chenggang, Crookes, Danny, Hua, Liang
Format: Article
Language:English
Subjects:
Algorithms
Decoding
Detection algorithms
Distance measurement
DTW
E-Shufflenet
Evaluation
Feature extraction
Lightweight
Modules
Pose estimation
Real time
Rehabilitation
Rehabilitation exercise assessment
RLE-Decoder
Sports
SR-Pose
Three-dimensional displays
Training
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Rehabilitation movement assessment often requires patients to wear expensive and inconvenient sensors or optical markers. To address this issue, we propose a non-contact and real-time approach using a lightweight pose detection algorithm-Sports Rehabilitation-Pose (SR-Pose), and a depth camera for accurate assessment of rehabilitation movement. Our approach utilizes an E-Shufflenet network to extract underlying features of the target, a RLE-Decoder module to directly regress the coordinate values of 16 key points, and a Weight Fusion Unit (WFU) module to output optimal human posture detection results. By combining the detected human pose information with depth information, we accurately calculate the angle between each joint in three-dimensional space. Furthermore, we apply the DTW algorithm to solve the distance measurement and matching problem of video sequences with different lengths in rehabilitation evaluation tasks. Experimental results show that our method can detect human joint nodes with an average detection speed of 14.32ms and an average detection accuracy for pose of 91.2%, demonstrating its computational efficiency and effectiveness for practical application. Our proposed approach provides a low-cost and user-friendly alternative to traditional sensor-based methods, making it a promising solution for rehabilitation movement assessment.
ISSN:1534-4320
1558-0210
DOI:10.1109/TNSRE.2023.3324960