Inertial motion capture validation of 3D knee kinematics at various gait speed on the treadmill with a double-pose calibration

Robert-Lachaîne, Xavier; Parent, G.; Fuentes, Alexandre; Hagemeister, Nicola; Aïssaoui, Rachid

doi:10.1016/j.gaitpost.2020.01.029

Cited by 29 publications

(43 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While validation with true sensor data is a necessary follow-up step, the accuracy of the presented framework is a promising advance toward prediction of joint kinematics from IMUs without relying on drift-prone algorithms and error-prone calibration techniques. Previously proposed approaches have reported RMSEs of more than 3 • over limited durations (Dorschky et al, 2019 [4]; Karatsidis et al, 2018 [13]; Robert-Lachaine et al, 2020 [26], 2017b [25]). Because they rely on the use of magnetometers and filtering approaches, long-term reliability remains a limitation for natural environment applications.…”

Section: Discussionmentioning

confidence: 99%

“…Strapdown integration of inertial data introduces drift, and sensor fusion algorithms that rely on magnetometer data suffer from ferromagnetic disturbances (de Vries et al, 2009 [3]). Solutions that incorporate full-body biomechanical models (Robert-Lachaine et al, 2017a [24], 2017b [25], 2020 [26]) are currently not portable for anytime, anywhere use, and accuracy over long durations remains to be demonstrated. Additionally, the dependence of most algorithms on accurate sensor-to-segment alignment makes translation difficult for multi-day monitoring outside of the laboratory, given human error in sensor placement.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of kinematics from inertial measurement units using a combined deep learning and optimization framework

Rapp

Shin

Thomsen

et al. 2021

Journal of Biomechanics

View full text Add to dashboard Cite

The difficulty of estimating joint kinematics remains a critical barrier toward widespread use of inertial measurement units in biomechanics. Traditional sensor-fusion filters are largely reliant on magnetometer readings, which may be disturbed in uncontrolled environments. Careful sensor-to-segment alignment and calibration strategies are also necessary, which may burden users and lead to further error in uncontrolled settings. We introduce a new framework that combines deep learning and top-down optimization to accurately predict lower extremity joint angles directly from inertial data, without relying on magnetometer readings. We trained deep neural networks on a large set of synthetic inertial data derived from a clinical marker-based motion-tracking database of hundreds of subjects. We used data augmentation techniques and an automated calibration approach to reduce error due to variability in sensor placement and limb alignment. On leftout subjects, lower extremity kinematics could be predicted with a mean (± STD) root mean squared error of less than 1.27 • (± 0.38 • ) in flexion/extension, less than 2.52 • (± 0.98 • ) in ad/abduction, and less than 3.34 • (± 1.02 • ) internal/external rotation, across walking and running trials. Errors decreased exponentially with the amount of training data, confirming the need for large datasets when training deep neural networks. While this framework remains to be validated with true inertial measurement unit (IMU) data, the results presented here are a promising advance toward convenient estimation of gait kinematics in natural environments. Progress in this direction could enable large-scale studies and offer an unprecedented view into disease progression, patient recovery, and sports biomechanics.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Estimation of kinematics from inertial measurement units using a combined deep learning and optimization framework

Rapp

Shin

Thomsen

et al. 2021

Journal of Biomechanics

View full text Add to dashboard Cite

show abstract

“…Typically, accuracy has been quantified by comparing joint angles calculated using IMU systems to optical motion capture through root mean squared error (RMSE) [ 10 , 11 ], correlation coefficients [ 12 , 13 ], and/or Bland-Altman limits of agreement [ 14 , 15 ]. Efforts have largely been focused on IMU system validation for lower limb angles during gait [ 16 , 17 , 18 ]. However, other activities, including stair climbing, kicking, materials handling, and skiing [ 14 , 19 , 20 , 21 ] and upper body angles [ 22 , 23 ] have been examined as well.…”

Section: Introductionmentioning

confidence: 99%

Validation of an IMU Suit for Military-Based Tasks

Mavor

Ross

Clouthier

et al. 2020

Sensors

View full text Add to dashboard Cite

Investigating the effects of load carriage on military soldiers using optical motion capture is challenging. However, inertial measurement units (IMUs) provide a promising alternative. Our purpose was to compare optical motion capture with an Xsens IMU system in terms of movement reconstruction using principal component analysis (PCA) using correlation coefficients and joint kinematics using root mean squared error (RMSE). Eighteen civilians performed military-type movements while their motion was recorded using both optical and IMU-based systems. Tasks included walking, running, and transitioning between running, kneeling, and prone positions. PCA was applied to both the optical and virtual IMU markers, and the correlations between the principal component (PC) scores were assessed. Full-body joint angles were calculated and compared using RMSE between optical markers, IMU data, and virtual markers generated from IMU data with and without coordinate system alignment. There was good agreement in movement reconstruction using PCA; the average correlation coefficient was 0.81 ± 0.14. RMSE values between the optical markers and IMU data for flexion-extension were less than 9°, and 15° for the lower and upper limbs, respectively, across all tasks. The underlying biomechanical model and associated coordinate systems appear to influence RMSE values the most. The IMU system appears appropriate for capturing and reconstructing full-body motion variability for military-based movements.

show abstract

“…Studies with full-body IMUs measuring either mobility-related tasks in older adults or symptoms in PD patients did not measure simultaneously with optical motion capture [ 41 , 42 , 43 ]. Other mobility related-studies that validated IMU-based algorithms against optical motion capture only measured the lower body simultaneously with both systems [ 44 , 45 ]. The upper body can however also provide relevant information regarding mobility [ 4 , 46 ].…”

Section: Discussionmentioning

confidence: 99%

Proposed Mobility Assessments with Simultaneous Full-Body Inertial Measurement Units and Optical Motion Capture in Healthy Adults and Neurological Patients for Future Validation Studies: Study Protocol

Warmerdam

Romijnders

Geritz

et al. 2021

Sensors

View full text Add to dashboard Cite

Healthy adults and neurological patients show unique mobility patterns over the course of their lifespan and disease. Quantifying these mobility patterns could support diagnosing, tracking disease progression and measuring response to treatment. This quantification can be done with wearable technology, such as inertial measurement units (IMUs). Before IMUs can be used to quantify mobility, algorithms need to be developed and validated with age and disease-specific datasets. This study proposes a protocol for a dataset that can be used to develop and validate IMU-based mobility algorithms for healthy adults (18–60 years), healthy older adults (>60 years), and patients with Parkinson’s disease, multiple sclerosis, a symptomatic stroke and chronic low back pain. All participants will be measured simultaneously with IMUs and a 3D optical motion capture system while performing standardized mobility tasks and non-standardized activities of daily living. Specific clinical scales and questionnaires will be collected. This study aims at building the largest dataset for the development and validation of IMU-based mobility algorithms for healthy adults and neurological patients. It is anticipated to provide this dataset for further research use and collaboration, with the ultimate goal to bring IMU-based mobility algorithms as quickly as possible into clinical trials and clinical routine.

show abstract

Inertial motion capture validation of 3D knee kinematics at various gait speed on the treadmill with a double-pose calibration

Cited by 29 publications

References 29 publications

Estimation of kinematics from inertial measurement units using a combined deep learning and optimization framework

Estimation of kinematics from inertial measurement units using a combined deep learning and optimization framework

Validation of an IMU Suit for Military-Based Tasks

Proposed Mobility Assessments with Simultaneous Full-Body Inertial Measurement Units and Optical Motion Capture in Healthy Adults and Neurological Patients for Future Validation Studies: Study Protocol

Contact Info

Product

Resources

About