scholarly journals Comparison of three methods for reconstructing 3D motion from 2D video recordings for low cost gait analysis systems

2021 ◽  
Vol 27 (4) ◽  
pp. 271-277
Author(s):  
Szymon Cygan ◽  
Adriana Specyalska
Keyword(s):  
Standard Deviation ◽  
Gait Analysis ◽  
Motion Tracking ◽  
Low Cost ◽  
Maximum Error ◽  
Reconstruction Method ◽  
3D Motion ◽  
Video Recordings ◽  
Reconstruction Methods ◽  
Analysis System

Abstract Purpose: The aim of this study was to quantify the accuracy of 3D trajectory reconstructions performed from two planar video recordings, using three different reconstruction methods. Additionally, the recordings were carried out using easily available equipment, like built-in cellphone cameras, making the methods suitable for low-cost applications. Methods: A setup for 3D motion tracking was constructed and used to acquire 2D video recordings subsequently used to reconstruct the 3D trajectories by 1) merging appropriate coordinates, 2) merging coordinates with proportional scaling, and 3) calculating the 3D position based on markers’ projections on the viewing plane. As experimental verification, two markers moving at a fixed distance of 98.9 cm were used to assess the consistency of results. Next, gait analysis in five volunteers was carried out to quantify the differences resulting from different reconstruction methods. Results: Quantitative evaluation of the investigated 3D trajectories reconstruction methods showed significant differences between those methods, with the worst reconstruction approach resulting in a maximum error of 50% (standard deviation 13%), while the best resulting in a maximum error of 1% (standard deviation 0.44%). The gait analysis results showed differences in mean angles obtained with each reconstruction method reaching only 2°, which can be attributed to the limited measurement volume. Conclusions: Reconstructing 3D trajectory from 2D views without accounting for the “perspective error” results in significant reconstruction errors. The third method described in this study enables a significant reduction of this issue. Combined with the proposed setup, it provides a functional, low-cost gait analysis system.

Development and Assessment of a Low-Cost Clinical Gait Analysis System

2018 ◽  
Vol 34 (6) ◽  
pp. 503-508 ◽  
Author(s):  
Mary Emily Littrell ◽  
Young-Hui Chang ◽  
Brian P. Selgrade
Keyword(s):  
Gait Analysis ◽  
Motion Tracking ◽  
Low Cost ◽  
Reaction Force ◽  
Sampling Rate ◽  
Video Camera ◽  
Force Platform ◽  
Cost System ◽  
Variable Sampling ◽  
Analysis System

Clinically, measuring gait kinematics and ground reaction force (GRF) is useful to determine the effectiveness of treatment. However, it is inconvenient and expensive to maintain a laboratory-grade gait analysis system in most clinics. The purpose of this study was to validate a Wii Balance Board, Kinovea motion-tracking software, and a video camera as a portable, low-cost system, and overground gait analysis system. We validated this low-cost system against a multicamera Vicon system and research-grade force platform (Advanced Mechanical Technology, Inc). After validation trials with known weights and angles, 5 subjects walked across an instrumented walkway for multiple times (n = 8/subject). We collected vertical GRF and segment angles. Average GRF data from the 2 systems were similar, with peak GRF errors below 3.5%BW. However, variability in the balance board’s sampling rate led to large GRF errors early and late in stance, when the GRF changed rapidly. The thigh, shank, and foot angle measurements were similar between the single and multicamera, but the pelvis angle was far less accurate. The proposed system has the potential to provide accurate segment angles and peak GRF at low cost but does not match the accuracy of the multicamera system and force platform, in part because of the Wii Balance Board’s variable sampling rate.

A low-cost Kinect™ for Windows® v2-based gait analysis system

2017 ◽  
Author(s):  
Jorge Latorre ◽  
Roberto Llorens ◽  
Adrian Borrego ◽  
Mariano Alcaniz ◽  
Carolina Colomer ◽  
...  
Keyword(s):  
Gait Analysis ◽  
Low Cost ◽  
Analysis System

scholarly journals Low-cost three-dimensional gait analysis system for mice with an infrared depth sensor

2015 ◽  
Vol 100 ◽  
pp. 55-62 ◽  
Author(s):  
Akihiro Nakamura ◽  
Hiroyuki Funaya ◽  
Naohiro Uezono ◽  
Kinichi Nakashima ◽  
Yasumasa Ishida ◽  
...  
Keyword(s):  
Gait Analysis ◽  
Low Cost ◽  
Three Dimensional ◽  
Depth Sensor ◽  
Analysis System

scholarly journals A Validation of Supervised Deep Learning for Gait Analysis in the Cat

2021 ◽  
Vol 15 ◽  
Author(s):  
Charly G. Lecomte ◽  
Johannie Audet ◽  
Jonathan Harnie ◽  
Alain Frigon
Keyword(s):  
Deep Learning ◽  
Gait Analysis ◽  
Correlation Coefficient ◽  
Motion Tracking ◽  
Low Cost ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Bony Landmarks ◽  
Custom Made ◽  
Adult Cat

Gait analysis in cats and other animals is generally performed with custom-made or commercially developed software to track reflective markers placed on bony landmarks. This often involves costly motion tracking systems. However, deep learning, and in particular DeepLabCutTM (DLC), allows motion tracking without requiring placing reflective markers or an expensive system. The purpose of this study was to validate the accuracy of DLC for gait analysis in the adult cat by comparing results obtained with DLC and a custom-made software (Expresso) that has been used in several cat studies. Four intact adult cats performed tied-belt (both belts at same speed) and split-belt (belts operating at different speeds) locomotion at different speeds and left-right speed differences on a split-belt treadmill. We calculated several kinematic variables, such as step/stride lengths and joint angles from the estimates made by the two software and assessed the agreement between the two measurements using intraclass correlation coefficient or Lin’s concordance correlation coefficient as well as Pearson’s correlation coefficients. The results showed that DLC is at least as precise as Expresso with good to excellent agreement for all variables. Indeed, all 12 variables showed an agreement above 0.75, considered good, while nine showed an agreement above 0.9, considered excellent. Therefore, deep learning, specifically DLC, is valid for measuring kinematic variables during locomotion in cats, without requiring reflective markers and using a relatively low-cost system.

A Low Cost System for 3D Motion Analysis Using Microsoft Kinect

2013 ◽  
Vol 284-287 ◽  
pp. 1996-2000 ◽  
Author(s):  
Hai Trieu Pham ◽  
Jung Ja Kim ◽  
Yong Gwan Won
Keyword(s):  
Motion Analysis ◽  
Color Image ◽  
Low Cost ◽  
Infrared Camera ◽  
Microsoft Kinect ◽  
Depth Image ◽  
3D Motion ◽  
Acceptable Accuracy ◽  
3D Motion Analysis ◽  
Analysis System

Many motion analysis systems which have been introduced in the past few years are currently receiving interests from researchers and developers due to their usefulness and wide application capability in the future. However, many of those systems meet with difficulties for the real applications because of high cost for the implementation and less accuracy. This paper introduces a new 3D motion analysis system which can be implemented at a lower cost and acceptable accuracy for various applications. The key component of our new system is the use of the MSK (Microsoft Kinect) sensor system which is equipped with both visual camera and infrared camera. It can provide the color image, the 3D depth image and the 3D skeleton data without wearing any marker device on the human body while it can provide acceptable accuracy in 3D motion trace at low cost. Our system can be exploited for a base framework for various 3D motion-based applications such as physical rehabilitation support, sport motion analysis and biomechanical applications.

Using a Maximum Error Statistic to Evaluate Measurement Errors in 3D Position and Orientation Tracking Systems

1993 ◽  
Vol 2 (4) ◽  
pp. 314-343 ◽  
Author(s):  
Ted Morris ◽  
Max Donath
Keyword(s):  
Relative Motion ◽  
Measurement Errors ◽  
Degrees Of Freedom ◽  
Motion Tracking ◽  
Computer Experiments ◽  
Maximum Error ◽  
Tracking Systems ◽  
3D Motion ◽  
Six Degrees Of Freedom ◽  
Error Statistic

One approach to tracking anatomical and robot joint motion consists of tracking the XYZ locations of multiple point targets that are attached to each of the moving segments and then computing the three translations and three orientation angles between adjoining segments. The complexity of such systems requires that we introduce a new conservative maximum error statistic to be used for evaluating the accuracy of 3D motion tracking systems. This paper addresses the various phenomena that contribute to measurement error when computing six degrees of freedom associated with the relative motion between the adjacent segments. The characteristics of these errors, common to many 3D motion tracking systems, were first determined by experimentation using one such system (MnSCAN). These and additional artifacts were then modeled in order to quantitatively evaluate their effects using the maximum error statistic. Based on these computer experiments, several relationships were identified that predict how each of these phenomena influences the predicted measurement of relative motion between bodies. These suggest where design emphasis should be placed in order to minimize the error in tracking the six degrees of freedom. The methodology and the conclusions based on these results can be applied to designing most six degree of freedom position and motion measurement systems.

Sign in / Sign up

Export Citation Format

Share Document