Gait analysis of knee osteoarthritis based on depth camera
10.3760/cma.j.cn121113-20201116-00661
- VernacularTitle:基于深度相机的膝关节骨关节炎步态分析研究
- Author:
Fang CHEN
1
;
Zhe ZHAO
;
Xiwen CUI
;
Yanting XIE
;
Licheng ZHANG
;
Hongen LIAO
;
Peifu TANG
Author Information
1. 南京航空航天大学计算机学院 211106
- Keywords:
Knee osteoarthritis;
gait analysis;
depth camera;
static features;
dynamic features
- From:
Chinese Journal of Orthopaedics
2021;41(22):1631-1639
- CountryChina
- Language:Chinese
-
Abstract:
Objective:In this study, a gait acquisition and analysis system is developed to provide a cheap, easy-to-use solution for quantitative recording and analysis of patients' gaits.Methods:From April 2017 to October 2018, we collected the gait data of 19 patients with knee osteoarthritis and 19 healthy volunteers in the orthopaedic outpatient department. Among 19 patients, there were 9 males and 10 females, aged 50.1±9.4 years old. Among 19 healthy volunteers, there were 8 males and 11 females, aged 50.7±10.3 years old. Then, from the collected gait data, the static gait features such as gait speed, step length, stride, and dynamic gait features were automatically calculated, and the statistical difference analysis was finished to determine the correlation between these quantitative gait features and knee osteoarthritis.Results:Firstly, the gait data collected by the depth camera was compared with the data from the multi infrared camera-based motion analysis system (gold standard). The average angle error of the collected knee joint angle was 0.98 degrees, which proved the correctness of the gait data recorded by the depth camera. The statistical difference analysis of gait characteristics between the patient group and the healthy group showed that the gait characteristics with P<0.05 included: gait speed ( r=-0.922, P<0.001), step length ( r=-0.897, P=0.004), stride ( r=-0.914 , P<0.001), dynamic characteristics of angle of knee joint ( r=0.775, P=0.001). Conclusion:The gait acquisition and analysis system based on the depth camera can accurately record and store the gait data of the patients with knee osteoarthritis. Moreover, the extracted quantitative gait features have statistical differences between the patients and the healthy group, which is helpful for the gait analysis of bone joint.