A Novel Training Bike and Camera System to Evaluate Pose of Cyclists

2020 ◽  
Author(s):  
Raman Garimella ◽  
Koen Beyers ◽  
Thomas Peeters ◽  
Stijn Verwulgen ◽  
Seppe Sels ◽  
...  
Keyword(s):  
Inertial Sensors ◽  
Sagittal Plane ◽  
Aerodynamic Drag ◽  
Linear Regression Analysis ◽  
The Body ◽  
Frontal Area ◽  
Motion Sensors ◽  
Joint Angles ◽  
Camera System ◽  
Flexion Extension

Abstract Aerodynamic drag force can account for up to 90% of the opposing force experienced by a cyclist. Therefore, aerodynamic testing and efficiency is a priority in cycling. An inexpensive method to optimize performance is required. In this study, we evaluate a novel indoor setup as a tool for aerodynamic pose training. The setup consists of a bike, indoor home trainer, camera, and wearable inertial motion sensors. A camera calculates frontal area of the cyclist and the trainer varies resistance to the cyclist by using this as an input. To guide a cyclist to assume an optimal pose, joint angles of the body are an objective metric. To track joint angles, two methods were evaluated: optical (RGB camera for the two-dimensional angles in sagittal plane of 6 joints), and inertial sensors (wearable sensors for three-dimensional angles of 13 joints). One (1) male amateur cyclist was instructed to recreate certain static and dynamic poses on the bike. The inertial sensors provide excellent results (absolute error = 0.28°) for knee joint. Based on linear regression analysis, frontal area can be best predicted (correlation > 0.4) by chest anterior/posterior tilt, pelvis left/right rotation, neck flexion/extension, chest left/right rotation, and chest left/right lateral tilt (p < 0.01).

Continuous Estimation Prediction of Knee Joint Angles Using Fusion of Electromyographic and Inertial Sensors for Active Transfemoral Leg Prostheses

2018 ◽  
Vol 10 (02) ◽  
pp. 1840008
Author(s):  
Alberto López-Delis ◽  
Cristiano J. Miosso ◽  
João L. A. Carvalho ◽  
Adson F. da Rocha ◽  
Geovany A. Borges
Keyword(s):  
Knee Joint ◽  
Joint Angle ◽  
Inertial Sensors ◽  
Sagittal Plane ◽  
Joint Angles ◽  
Knee Joint Angle ◽  
Improved Performance ◽  
Continuous Estimation ◽  
Movement Intention ◽  
Semg Signals

Information extracted from the surface electromyographic (sEMG) signals can allow for the detection of movement intention in transfemoral prostheses. The sEMG can help estimate the angle between the femur and the tibia in the sagittal plane. However, algorithms based exclusively on sEMG information can lead to inaccurate results. Data captured by inertial-sensors can improve this estimate. We propose three myoelectric algorithms that extract data from sEMG and inertial sensors using Kalman-filters. The proposed fusion-based algorithms showed improved performance compared to methods based exclusively on sEMG data, generating improvements in the accuracy of knee joint angle estimation and reducing estimation artifacts.

scholarly journals A three dimensional multiplane kinematic model for bilateral hind limb gait analysis in cats

2018 ◽  
Author(s):  
Nathan P. Brown ◽  
Gina E. Bertocci ◽  
Kimberly A. Cheffer ◽  
Dena R. Howland
Keyword(s):  
Gait Analysis ◽  
Hind Limb ◽  
Sagittal Plane ◽  
External Rotation ◽  
Kinematic Model ◽  
Three Dimensional ◽  
Joint Angles ◽  
Plane Model ◽  
Flexion Extension ◽  
Joint Flexion

AbstractBackground: Kinematic gait analysis is an important noninvasive technique used for quantitative evaluation and description of locomotion and other movements in healthy and injured populations. Three dimensional (3D) kinematic analysis offers additional outcome measures including internal-external rotation not characterized using sagittal plane analysis techniques.Methods: The objectives of this study were to 1) develop and evaluate a 3D hind limb multiplane kinematic model for gait analysis in cats using joint coordinate systems, 2) implement and compare two 3D stifle (knee) prediction techniques, and 3) compare flexion-extension determined using the multiplane model to a sagittal plane model. Walking gait was recorded in 3 female adult cats (age = 2.9 years, weight = 3.5 ± 0.2 kg). Kinematic outcomes included flexion-extension, internal-external rotation, and abduction-adduction of the hip, stifle, and tarsal (ankle) joints.Results: Each multiplane stifle prediction technique yielded similar findings. Joint angles determined using markers placed on skin above bony landmarks in vivo were similar to joint angles determined using a feline hind limb skeleton in which markers were placed directly on landmarks ex vivo. Differences in hip, stifle, and tarsal joint flexion-extension were demonstrated when comparing the multiplane model to the sagittal plane model.Conclusions: This multiplane cat kinematic model can predict joint rotational kinematics as a tool that can quantify frontal, transverse, and sagittal plane motion. This model has multiple advantages given its ability to characterize joint internal-external rotation and abduction-adduction. A further, important benefit is greater accuracy in representing joint flexion-extension movements.

scholarly journals Validation of a Device to Measure Knee Joint Angles for a Dynamic Movement

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1747 ◽  
Author(s):  
Mirel Ajdaroski ◽  
Ruchika Tadakala ◽  
Lorraine Nichols ◽  
Amanda Esquivel
Keyword(s):  
Knee Joint ◽  
Motion Capture ◽  
Cruciate Ligament ◽  
Linear Regression Analysis ◽  
Knee Kinematics ◽  
The United States ◽  
Wearable Device ◽  
Joint Angles ◽  
Dynamic Movement ◽  
Flexion Extension

Participation in sports has risen in the United States over the last few years, increasing the risk of injuries such as tears to the anterior cruciate ligament (ACL) in the knee. Previous studies have shown a correlation between knee kinematics when landing from a jump and this injury. The purpose of this study was to validate the ability of a commercially available inertial measurement units (IMUs) to accurately measure knee joint angles during a dynamic movement. Eight healthy subjects participated in the study. Validation was performed by comparing the angles measured by the wearable device to those obtained through the gold standard motion capture system when landing from a jump. Root mean square, linear regression analysis, and Bland–Altman plots were performed/constructed. The mean difference between the wearable device and the motion capture data was 8.4° (flexion/extension), 4.9° (ab/adduction), and 3.9° (rotation). In addition, the device was more accurate at smaller knee angles. In our study, a commercially available wearable IMU was able to perform fairly well under certain conditions and was less accurate in other conditions.

scholarly journals Estimating Minimal Clinically Important Differences for Knee Range of Motion after Stroke

2020 ◽  
Vol 9 (10) ◽  
pp. 3305
Author(s):  
Agnieszka Guzik ◽  
Mariusz Drużbicki ◽  
Andżelina Wolan-Nieroda ◽  
Andrea Turolla ◽  
Pawel Kiper
Keyword(s):  
Range Of Motion ◽  
Roc Curve ◽  
Sagittal Plane ◽  
Linear Regression Analysis ◽  
Unaffected Side ◽  
Point Change ◽  
Post Stroke ◽  
Gait Parameters ◽  
Flexion Extension ◽  
Estimate Method

The importance of knee sagittal kinematic parameters, as a predictor of walking performance in post-stroke gait has been emphasised by numerous researchers. However, no studies so far were designed to determine the minimal clinically important differences (MCID), i.e., the smallest difference in the relevant score for the kinematic gait parameters, which are perceived as beneficial for patients with stroke. Studies focusing on clinically important difference are useful because they can identify the clinical relevance of changes in the scores. The purpose of the study was to estimate the MCID for knee range of motion (ROM) in the sagittal plane for the affected and unaffected side at a chronic stage post-stroke. Fifty individuals were identified in a database of a rehabilitation clinic. We estimated MCID values using: an anchor-based method, distribution-based method, linear regression analysis and specification of the receiver operating characteristic (ROC) curve. In the anchor-based study, the mean change in knee flexion/extension ROM for the affected/unaffected side in the MCID group amounted to 8.48°/6.81° (the first MCID estimate). In the distribution-based study, the standard error of measurement for the no-change group was 1.86°/5.63° (the second MCID estimate). Method 3 analyses showed 7.71°/4.66° change in the ROM corresponding to 1.85-point change in the Barthel Index. The best cut-off point, determined with ROC curve, was the value corresponding to 3.9°/3.8° of change in the knee sagittal ROM for the affected/unaffected side (the fourth MCID estimate). We have determined that, in chronic stroke, MCID estimates of knee sagittal ROM for the affected side amount to 8.48° and for the unaffected side to 6.81°. These findings will assist clinicians and researchers in interpreting the significance of changes observed in kinematic sagittal plane parameters of the knee. The data are part of the following clinical trial: Australian New Zealand Clinical Trials Registry: ACTRN12617000436370

scholarly journals Estimating Cycling Aerodynamic Performance Using Anthropometric Measures

2020 ◽  
Vol 10 (23) ◽  
pp. 8635
Author(s):  
Raman Garimella ◽  
Thomas Peeters ◽  
Eduardo Parrilla ◽  
Jordi Uriel ◽  
Seppe Sels ◽  
...  
Keyword(s):  
Drag Force ◽  
Joint Angle ◽  
Aerodynamic Drag ◽  
Linear Regression Analysis ◽  
3D Models ◽  
Frontal Area ◽  
Coefficient Of Determination ◽  
Anthropometric Measures ◽  
Aerodynamic Efficiency ◽  
Angle Data

Aerodynamic drag force and projected frontal area (A) are commonly used indicators of aerodynamic cycling efficiency. This study investigated the accuracy of estimating these quantities using easy-to-acquire anthropometric and pose measures. In the first part, computational fluid dynamics (CFD) drag force calculations and A (m2) values from photogrammetry methods were compared using predicted 3D cycling models for 10 male amateur cyclists. The shape of the 3D models was predicted using anthropometric measures. Subsequently, the models were reposed from a standing to a cycling pose using joint angle data from an optical motion capture (mocap) system. In the second part, a linear regression analysis was performed to predict A using 26 anthropometric measures combined with joint angle data from two sources (optical and inertial mocap, separately). Drag calculations were strongly correlated with benchmark projected frontal area (coefficient of determination R2 = 0.72). A can accurately be predicted using anthropometric data and joint angles from optical mocap (root mean square error (RMSE) = 0.037 m2) or inertial mocap (RMSE = 0.032 m2). This study showed that aerodynamic efficiency can be predicted using anthropometric and joint angle data from commercially available, inexpensive posture tracking methods. The practical relevance for cyclists is to quantify and train posture during cycling for improving aerodynamic efficiency and hence performance.

The Effect of Air Resistance on the Jumping Performance of Insects

1979 ◽  
Vol 82 (1) ◽  
pp. 105-121
Author(s):  
H. C. BENNET-CLARK ◽  
G. M. ALDER
Keyword(s):  
Reynolds Number ◽  
Drag Coefficient ◽  
Optimal Condition ◽  
Scale Effect ◽  
Aerodynamic Drag ◽  
The Body ◽  
Frontal Area ◽  
Mass Ratio ◽  
Design Constraints ◽  
Air Resistance

A spring gun was constructed to propel objects at known velocities of between 1 and 4.5 m.s−1. This was used to project insects and various models in a vertical trajectory. By comparing the height attained in air by the insects or models with the height theoretically possible in vacuo, the energy lost against air resistance was observed. Small insects have a higher frontal area to mass ratio than larger ones so have relatively more aerodynamic drag and attain lower heights. The observed effect may be expressed in terms of the drag coefficient, CD. Fleas and locusts have CD of about 1 Winged flies have CD of about 1.5 which falls to about 1 when the wings are amputated and to about o-8 when the legs are amputated. Aptery is advantageous in jumping insects. From experiments with models, it appears that the optimal condition for small jumping insects is that the body should be as compact as possible to reduce the frontal area to mass ratio. Thus dense spherical bodies are favoured. Some species of jumping insect have densities of about 1 mg.mm−3 while some flying beetles and flies have densities between 0.3 and 0.8 mg.mm−3. The Reynolds number at which the experiments were performed was from 65–205 for fleas up to 740-2340 for locusts. The models operated in similar ranges. At a velocity which would propel a larger animal to a height of 1 m, fleas weighing 0.4 mg only reach about 0.4 m. At lower initial velocities, proportionately less energy is wasted against air resistance so the jump efficiency is higher. Most fleas jump to a height of about 0.1 m with an efficiency of 0.8 while locusts jump to a height of 0.35 m with an efficiency of over 0.9. Air resistance is thus an important scale effect in jumping insects and provides its own design constraints.

scholarly journals Lower Limb Kinematics Using Inertial Sensors during Locomotion: Accuracy and Reproducibility of Joint Angle Calculations with Different Sensor-to-Segment Calibrations

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 715 ◽  
Author(s):  
Julien Lebleu ◽  
Thierry Gosseye ◽  
Christine Detrembleur ◽  
Philippe Mahaudens ◽  
Olivier Cartiaux ◽  
...  
Keyword(s):  
Lower Limb ◽  
Inertial Sensors ◽  
Sagittal Plane ◽  
Frontal Plane ◽  
Human Movement ◽  
Absolute Difference ◽  
Measurement Unit ◽  
Joint Angles ◽  
3D Tracking ◽  
Limb Kinematics

Inertial measurement unit (IMU) records of human movement can be converted into joint angles using a sensor-to-segment calibration, also called functional calibration. This study aims to compare the accuracy and reproducibility of four functional calibration procedures for the 3D tracking of the lower limb joint angles of young healthy individuals in gait. Three methods based on segment rotations and one on segment accelerations were used to compare IMU records with an optical system for their accuracy and reproducibility. The squat functional calibration movement, offering a low range of motion of the shank, provided the least accurate measurements. A comparable accuracy was obtained in other methods with a root mean square error below 3.6° and an absolute difference in amplitude below 3.4°. The reproducibility was excellent in the sagittal plane (intra-class correlation coefficient (ICC) > 0.91, standard error of measurement (SEM) < 1.1°), good to excellent in the transverse plane (ICC > 0.87, SEM < 1.1°), and good in the frontal plane (ICC > 0.63, SEM < 1.2°). The better accuracy for proximal joints in calibration movements using segment rotations was traded to distal joints in calibration movements using segment accelerations. These results encourage further applications of IMU systems in unconstrained rehabilitative contexts.

Reliability of sagittal plane hip, knee, and ankle joint angles from a single frame of video data using the GAITRite camera system

2014 ◽  
Vol 31 (1) ◽  
pp. 53-60 ◽  
Author(s):  
Sandy A. Ross ◽  
Clinton Rice ◽  
Kristyn Von Behren ◽  
April Meyer ◽  
Rachel Alexander ◽  
...  
Keyword(s):  
Ankle Joint ◽  
Sagittal Plane ◽  
Video Data ◽  
Joint Angles ◽  
Camera System ◽  
Single Frame

Design and evaluation of a novel triaxial isometric trunk muscle strength measurement system

2009 ◽  
Vol 223 (6) ◽  
pp. 755-766 ◽  
Author(s):  
M R Azghani ◽  
F Farahmand ◽  
A Meghdari ◽  
G Vossoughi ◽  
M Parnianpour
Keyword(s):  
Measurement System ◽  
High Reliability ◽  
Linear Regression Analysis ◽  
Correlation Coefficients ◽  
The Body ◽  
Trunk Muscles ◽  
Published Data ◽  
Strength Measurement ◽  
Intra Class Correlation ◽  
Flexion Extension

Maximal strength measurements of the trunk have been used to evaluate the maximum functional capacity of muscles and the potential mechanical overload or overuse of the lumbar spine tissues in order to estimate the risk of developing musculoskeletal injuries. A new triaxial isometric trunk strength measurement system was designed and developed in the present study, and its reliability and performance was investigated. The system consisted of three main revolute joints, equipped with torque sensors, which intersect at L5—S1 and adjustment facilities to fit the body anthropometry and to accommodate both symmetric and asymmetric postures in both seated and standing positions. The dynamics of the system was formulated to resolve validly the moment generated by trunk muscles in the three anatomic planes. The optimal gain and offset of the system were obtained using deadweights based on the least-squares linear regression analysis. The R2 results of calibration for all loading courses of all joints were higher than 0.99, which indicated an excellent linear correlation. The results of the validation analysis of the regression model suggested that the mean absolute error and the r.m.s. error were less than 2 per cent of the applied load. The maximum value of the minimum detectable change was found to be 1.63 N m for the sagittal plane torque measurement, 0.8 per cent of the full-scale load. The trial-to-trial variability analysis of the device using deadweights provided intra-class correlation coefficients of higher than 0.99, suggesting excellent reliability. The cross-talk analysis of the device indicated maximum cross-talks of 1.7 per cent and 3.4 per cent when the system was subjected to flexion—extension and lateral bending torques respectively. The trial-to-trial variability of the system during in-vivo strength measurement tests resulted in good to excellent reliability, with intra-class correlation coefficients ranging from 0.69 to 0.91. The results of the maximum voluntary isometric torques exertion measurements for 30 subjects indicated good agreement with the previously published data in the literature. The extensive capabilities and high reliability of the system are promising for more comprehensive investigations on the trunk biomechanics in future, e.g. isometric strength measurement at symmetric and asymmetric postures, muscle endurance, and recruitment pattern analysis.

Deadlift Recognition and Application based on Multiple Modalities using Recurrent Neural Network

2020 ◽  
Vol 2020 (17) ◽  
pp. 2-1-2-6
Author(s):  
Shih-Wei Sun ◽  
Ting-Chen Mou ◽  
Pao-Chi Chang
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Network Structure ◽  
Inertial Sensors ◽  
Body Movement ◽  
The Body ◽  
Body Parts ◽  
Multimodal Sensing ◽  
Multiple Devices ◽  
Neural Network Structure

To improve the workout efficiency and to provide the body movement suggestions to users in a “smart gym” environment, we propose to use a depth camera for capturing a user’s body parts and mount multiple inertial sensors on the body parts of a user to generate deadlift behavior models generated by a recurrent neural network structure. The contribution of this paper is trifold: 1) The multimodal sensing signals obtained from multiple devices are fused for generating the deadlift behavior classifiers, 2) the recurrent neural network structure can analyze the information from the synchronized skeletal and inertial sensing data, and 3) a Vaplab dataset is generated for evaluating the deadlift behaviors recognizing capability in the proposed method.

Sign in / Sign up

Export Citation Format

Share Document