Evaluation of Calibrated Kinect Gait Kinematics Using a Vicon Motion Capture System

Lamine, Houssein; Bennour, Sami; Laribi, Med Amine; Romdhane, Lotfi; Zaghloul, Soha S.

doi:10.1080/10255842.2017.1382886

Cited by 32 publications

(20 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optical motion-tracking system [ 6 ] estimates orientation through multiple cameras to track pre-designated points on moving limbs in a fixed working space. Similar to LIDAR motion trackers, this method needs hefty computers to store data and run image-processing algorithms.…”

Section: Introductionmentioning

confidence: 99%

Estimating Three-Dimensional Body Orientation Based on an Improved Complementary Filter for Human Motion Tracking

Guo

et al. 2018

Sensors

View full text Add to dashboard Cite

Rigid body orientation determined by IMU (Inertial Measurement Unit) is widely applied in robotics, navigation, rehabilitation, and human-computer interaction. In this paper, aiming at dynamically fusing quaternions computed from angular rate integration and FQA algorithm, a quaternion-based complementary filter algorithm is proposed to support a computationally efficient, wearable motion-tracking system. Firstly, a gradient descent method is used to determine a function from several sample points. Secondly, this function is used to dynamically estimate the fusion coefficient based on the deviation between measured magnetic field, gravity vectors and their references in Earth-fixed frame. Thirdly, a test machine is designed to evaluate the performance of designed filter. Experimental results validate the filter design and show its potential of real-time human motion tracking.

show abstract

Section: Introductionmentioning

confidence: 99%

Estimating Three-Dimensional Body Orientation Based on an Improved Complementary Filter for Human Motion Tracking

Guo

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…There were significant limitations in evaluating the ankle angle because it involved the toe coordinate, which had low accuracy with our depth sensor. Similar limitations have occurred in other studies, such as [11] or [18]. For this reason, we solely excluded the ankle angle from the analysis.…”

Section: Discussionmentioning

confidence: 94%

“…Mentiplay et al [10] concluded that Kinect V2 cannot accurately obtain the kinematic parameters of lower extremities. In contrast, Lamine et al [11] concluded that with preliminary calibrations gait kinematics could be accurately evaluated in several joints. To validate the ability of RGBD sensors to obtain human gait data, the well-known difference associated with gender was used.…”

Section: Introductionmentioning

confidence: 97%

Non-Invasive Multi-Camera Gait Analysis System and its Application to Gender Classification

2020

View full text Add to dashboard Cite

Objective: Most studies have conducted human gait analysis using expensive and invasive photogrammetric systems. The objective of this study was to demonstrate that non-invasive and costeffective systems based on depth cameras may be able to retrieve relevant features of human gait patterns. We aimed to prove this by solving the problem of gait classification by gender. Methods: 81 participants (40 female and 41 male) walked at a self-selected speed across a 4.8-meter walkway. Gait data was recorded using multiple depth sensors. Analysis in time domain included joint excursions by gait phases, range of movement (ROM), central tendency and dispersion measures, spatial variables, and center of mass (COM) position. The spectral analysis included principal frequency, magnitude, and phase shift during walking. Only features with significant differences by gender were used to train a support vector machine (SVM) classifier. Results: A total of 108 features presented significant differences by gender (p<0.05). On this basis, the accuracy of the chosen model was 96.7%. Trunk rotation, trunk sway, knee abduction/adduction, and pelvic obliquity were the most differentiated between the groups. The COM position shown a significant difference by gender (p=0.0065) with 51.7% and 51.0% for men and women respectively. Women proved to have significantly shorter normalized step width than men (p=0.0472). Conclusion: The proposed method was able to retrieve most of human gait features correctly, including differences in gait pattern by gender. Significance: Depth cameras represent a cost-effective system that could be used for a deeper biomechanical human gait analysis. INDEX TERMS Gender, gait analysis, joint, limb, machine learning.

show abstract

“…Therefore, studies focused on analyzing the validity of these systems under different circumstances are especially important. In this context, a markerless motion capture system (ie, the Kinect) has received much attention from clinicians, sports practitioners, and researchers [1,[3][4][5][6][7][8][9]. The Kinect sensor was originally designed for using body movement to interact with video games on the Microsoft Xbox platform.…”

Section: Introductionmentioning

confidence: 99%

Agreement Between Spatiotemporal Gait Parameters Measured by a Markerless Motion Capture System and Two Reference Systems—a Treadmill-Based Photoelectric Cell and High-Speed Video Analyses: Comparative Study (Preprint)

García‐Pinillos¹,

Jaén-Carrillo²,

Soto-Hermoso³

et al. 2020

Preprint

View full text Add to dashboard Cite

BACKGROUND Markerless systems require no markers to be attached to the body, improving clinical feasibility and testing time. However, the lack of markers might affect the measurements’ accuracy OBJECTIVE This study aimed to determine the absolute reliability and concurrent validity of the Kinect™ system with the MotionMetrix™ software for spatiotemporal variables evaluation during running at comfortable velocity by comparing data with two widely used systems (i.e., OptoGait™ and high-speed video-analysis at 1,000 Hz) METHODS Twenty-five runners performed a running protocol on a treadmill at 12 km.h-1. The Kinect™-MotionMetrix™ combination reported spatiotemporal parameters during running (i.e. contact time [CT], flight time [FT], step frequency [SF] and step length [SL]) and were compared to two reference systems. The Kinect™-MotionMetrix™ system obtained higher coefficients of variation than the reference systems in every spatiotemporal parameter. RESULTS Regardless of the system, FT displayed the highest values (OptoGait™ 16.4%, video analysis 17.3% and MotionMetrix™ 23.2%). The rest of CVs reported were lower than 8.1%. The correlation analysis reported very large correlations (r>0.8, p<0.001) and almost a perfect association (ICC>0.81) between systems for all the spatiotemporal parameters, except for CT, which reported lower values. The Bland-Altman plots between systems revealed small systematic biases and random errors for SF and SL, but greater systematic biases and random errors for temporal parameters as compared with both OptoGait™ (CT: +3.0%, FT: -7.9%) and high-speed video analysis at 1,000 Hz (CT: +4.2%, FT: -11.3%). Accordingly, heteroscedasticity was found between systems for temporal parameters (r2>0.1). CONCLUSIONS Therefore, the results indicate that the Kinect™-MotionMetrix™ combination slightly overestimates CT and strongly underestimates FT according to both OptoGait™ system and high-speed video analysis at 1,000 Hz, but it is a valid tool to measure SF and SL according to those reference systems. The results also question the reliability of this system for determining temporal parameters.

show abstract

Evaluation of Calibrated Kinect Gait Kinematics Using a Vicon Motion Capture System

Cited by 32 publications

References 4 publications

Estimating Three-Dimensional Body Orientation Based on an Improved Complementary Filter for Human Motion Tracking

Estimating Three-Dimensional Body Orientation Based on an Improved Complementary Filter for Human Motion Tracking

Non-Invasive Multi-Camera Gait Analysis System and its Application to Gender Classification

Agreement Between Spatiotemporal Gait Parameters Measured by a Markerless Motion Capture System and Two Reference Systems—a Treadmill-Based Photoelectric Cell and High-Speed Video Analyses: Comparative Study (Preprint)

Contact Info

Product

Resources

About