Moving outside the lab: Markerless motion capture accurately quantifies sagittal plane kinematics during the vertical jump

Motion Tracking of Daily Living and Physical Activities in Health Care: Systematic Review From Designers' Perspective

BACKGROUND

Motion tracking technologies serve as crucial links between physical activities and health care insights, facilitating data acquisition essential for analyzing and intervening in physical activity. Yet, systematic methodologies for evaluating motion tracking data, especially concerning user activity recognition in health care applications, remain underreported.

OBJECTIVE

This study aims to systematically review motion tracking in daily living and physical activities, emphasizing the critical interaction among devices, users, and environments from a design perspective, and to analyze the process involved in health care application research. It intends to delineate the design and application intricacies in health care contexts, focusing on enhancing motion tracking data's accuracy and applicability for health monitoring and intervention strategies.

METHODS

Using a systematic review, this research scrutinized motion tracking data and their application in health care and wellness, examining studies from Scopus, Web of Science, EBSCO, and PubMed databases. The review used actor network theory and data-enabled design to understand the complex interplay between humans, devices, and environments within these applications.

RESULTS

Out of 1501 initially identified studies, 54 (3.66%) were included for in-depth analysis. These articles predominantly used accelerometer and gyroscope sensors (n=43, 80%) to monitor and analyze motion, demonstrating a strong preference for these technologies in capturing both dynamic and static activities. While incorporating portable devices (n=11, 20%) and multisensor configurations (n=16, 30%), the application of sensors across the body (n=15, 28%) and within physical spaces (n=17, 31%) highlights the diverse applications of motion tracking technologies in health care research. This diversity reflects the application's alignment with activity types ranging from daily movements to specialized scenarios. The results also reveal a diverse participant pool, including the general public, athletes, and specialized groups, with a focus on healthy individuals (n=31, 57%) and athletes (n=14, 26%). Despite this extensive application range, the focus primarily on laboratory-based studies (n=39, 72%) aimed at professional uses, such as precise activity identification and joint functionality assessment, emphasizes a significant challenge in translating findings from controlled environments to the dynamic conditions of everyday physical activities.

CONCLUSIONS

This study's comprehensive investigation of motion tracking technology in health care research reveals a significant gap between the methods used for data collection and their practical application in real-world scenarios. It proposes an innovative approach that includes designers in the research process, emphasizing the importance of incorporating data-enabled design framework. This ensures that motion data collection is aligned with the dynamic and varied nature of daily living and physical activities. Such integration is crucial for developing health applications that are accessible, intuitive, and tailored to meet diverse user needs. By leveraging a multidisciplinary approach that combines design, engineering, and health sciences, the research opens new pathways for enhancing the usability and effectiveness of health technologies.

Large-scale citizen science reveals predictors of sensorimotor adaptation

Sensorimotor adaptation is essential for keeping our movements well calibrated in response to changes in the body and environment. For over a century, researchers have studied sensorimotor adaptation in laboratory settings that typically involve small sample sizes. While this approach has proved useful for characterizing different learning processes, laboratory studies are not well suited for exploring the myriad of factors that may modulate human performance. Here, using a citizen science website, we collected over 2,000 sessions of data on a visuomotor rotation task. This unique dataset has allowed us to replicate, reconcile and challenge classic findings in the learning and memory literature, as well as discover unappreciated demographic constraints associated with implicit and explicit processes that support sensorimotor adaptation. More generally, this study exemplifies how a large-scale exploratory approach can complement traditional hypothesis-driven laboratory research in advancing sensorimotor neuroscience.

Vertical Center-of-Mass Braking and Motor Performance during Gait Initiation in Young Healthy Adults, Elderly Healthy Adults, and Patients with Parkinson's Disease: A Comparison of Force-Plate and Markerless Motion Capture Systems

BACKGROUND

This study tested the agreement between a markerless motion capture system and force-plate system ("gold standard") to quantify stability control and motor performance during gait initiation.

METHODS

Healthy adults (young and elderly) and patients with Parkinson's disease performed gait initiation series at spontaneous and maximal velocity on a system of two force-plates placed in series while being filmed by a markerless motion capture system. Signals from both systems were used to compute the peak of forward center-of-mass velocity (indicator of motor performance) and the braking index (indicator of stability control).

RESULTS

Descriptive statistics indicated that both systems detected between-group differences and velocity effects similarly, while a Bland-Altman plot analysis showed that mean biases of both biomechanical indicators were virtually zero in all groups and conditions. Bayes factor 01 indicated strong (braking index) and moderate (motor performance) evidence that both systems provided equivalent values. However, a trial-by-trial analysis of Bland-Altman plots revealed the possibility of differences >10% between the two systems.

CONCLUSION

Although non-negligible differences do occur, a markerless motion capture system appears to be as efficient as a force-plate system in detecting Parkinson's disease and velocity condition effects on the braking index and motor performance.

Differences between lower extremity joint running kinetics captured by marker-based and markerless systems were speed dependent

BACKGROUND

The development of computer vision technology has enabled the use of markerless movement tracking for biomechanical analysis. Recent research has reported the feasibility of markerless systems in motion analysis but has yet to fully explore their utility for capturing faster movements, such as running. Applied studies using markerless systems in clinical and sports settings are still lacking. Thus, the present study compared running biomechanics estimated by marker-based and markerless systems. Given running speed not only affects sports performance but is also associated with clinical injury prevention, diagnosis, and rehabilitation, we aimed to investigate the effects of speed on the comparison of estimated lower extremity joint moments and powers between markerless and marker-based technologies during treadmill running as a concurrent validating study.

METHODS

Kinematic data from marker-based/markerless technologies were collected, along with ground reaction force data, from 16 young adults running on an instrumented treadmill at 3 speeds: 2.24 m/s, 2.91 m/s, and 3.58 m/s (5.0 miles/h, 6.5 miles/h, and 8.0 miles/h). Sagittal plane moments and powers of the hip, knee, and ankle were calculated by inverse dynamic methods. Time series analysis and statistical parametric mapping were used to determine system differences.

RESULTS

Compared to the marker-based system, the markerless system estimated increased lower extremity joint kinetics with faster speed during the swing phase in most cases.

CONCLUSION

Despite the promising application of markerless technology in clinical settings, systematic markerless overestimation requires focused attention. Based on segment pose estimations, the centers of mass estimated by markerless technologies were farther away from the relevant distal joint centers, which led to greater joint moments and powers estimates by markerless vs. marker-based systems. The differences were amplified by running speed.

Feasibility of OpenPose markerless motion analysis in a real athletics competition

This study tested the performance of OpenPose on footage collected by two cameras at 200 Hz from a real-life competitive setting by comparing it with manually analyzed data in SIMI motion. The same take-off recording from the men's Long Jump finals at the 2017 World Athletics Championships was used for both approaches (markerless and manual) to reconstruct the 3D coordinates from each of the camera's 2D coordinates. Joint angle and Centre of Mass (COM) variables during the final step and take-off phase of the jump were determined. Coefficients of Multiple Determinations (CMD) for joint angle waveforms showed large variation between athletes with the knee angle values typically being higher (take-off leg: 0.727 ± 0.242; swing leg: 0.729 ± 0.190) than those for hip (take-off leg: 0.388 ± 0.193; swing leg: 0.370 ± 0.227) and ankle angle (take-off leg: 0.247 ± 0.172; swing leg: 0.155 ± 0.228). COM data also showed considerable variation between athletes and parameters, with position (0.600 ± 0.322) and projection angle (0.658 ± 0.273) waveforms generally showing better agreement than COM velocity (0.217 ± 0.241). Agreement for discrete data was generally poor with high random error for joint kinematics and COM parameters at take-off and an average ICC across variables of 0.17. The poor agreement statistics and a range of unrealistic values returned by the pose estimation underline that OpenPose is not suitable for in-competition performance analysis in events such as the long jump, something that manual analysis still achieves with high levels of accuracy and reliability.

Identifying special operative trainees at-risk for musculoskeletal injury using full body kinematics

Introduction: Non-combat musculoskeletal injuries (MSKIs) during military training significantly impede the US military's functionality, with an annual cost exceeding $3.7 billion. This study aimed to investigate the effectiveness of a markerless motion capture system and full-body biomechanical movement pattern assessments to predict MSKI risk among military trainees. Methods: A total of 156 male United States Air Force (USAF) airmen were screened using a validated markerless biomechanics system. Trainees performed multiple functional movements, and the resultant data underwent Principal Component Analysis and Uniform Manifold And Projection to reduce the dimensionality of the time-dependent data. Two approaches, semi-supervised and supervised, were then used to identify at-risk trainees. Results: The semi-supervised analysis highlighted two major clusters with trainees in the high-risk cluster having a nearly five times greater risk of MSKI compared to those in the low-risk cluster. In the supervised approach, an AUC of 0.74 was produced when predicting MSKI in a leave-one-out analysis. Discussion: The application of markerless motion capture systems to measure an individual's kinematic profile shows potential in identifying MSKI risk. This approach offers a novel way to proactively address one of the largest non-combat burdens on the US military. Further refinement and wider-scale implementation of these techniques could bring about substantial reductions in MSKI occurrence and the associated economic costs.

Examination of 2D frontal and sagittal markerless motion capture: Implications for markerless applications

This study examined if occluded joint locations, obtained from 2D markerless motion capture (single camera view), produced 2D joint angles with reduced agreement compared to visible joints, and if 2D frontal plane joint angles were usable for practical applications. Fifteen healthy participants performed over-ground walking whilst recorded by fifteen marker-based cameras and two machine vision cameras (frontal and sagittal plane). Repeated measures Bland-Altman analysis illustrated that markerless standard deviation of bias and limits of agreement for the occluded-side hip and knee joint angles in the sagittal plane were double that of the camera-side (visible) hip and knee. Camera-side sagittal plane knee and hip angles were near or within marker-based error values previously observed. While frontal plane limits of agreement accounted for 35-46% of total range of motion at the hip and knee, Bland-Altman bias and limits of agreement (-4.6-1.6 ± 3.7-4.2˚) were actually similar to previously reported marker-based error values. This was not true for the ankle, where the limits of agreement (± 12˚) were still too high for practical applications. Our results add to previous literature, highlighting shortcomings of current pose estimation algorithms and labelled datasets. As such, this paper finishes by reviewing methods for creating anatomically accurate markerless training data using marker-based motion capture data.

Musculoskeletal simulation of professional ski jumpers during take-off considering aerodynamic forces

Introduction: Musculoskeletal simulation has been widely used to analyze athletes' movements in various competitive sports, but never in ski jumping. Aerodynamic forces during ski jumping take-off have been difficult to account for in dynamic simulation. The purpose of this study was to establish an efficient approach of musculoskeletal simulation of ski jumping take-off considering aerodynamic forces and to analyze the muscle function and activity. Methods: Camera-based marker-less motion capture was implemented to measure the take-off kinematics of eight professional jumpers. A suitable full-body musculoskeletal model was constructed for the simulation. A method based on inverse dynamics iteration was developed and validated to estimate the take-off ground reaction force. The aerodynamic forces, which were calculated based on body kinematics and computational fluid dynamics simulations, were exerted on the musculoskeletal model as external forces. The activation and joint torque contributions of lower extremity muscles were calculated through static optimization. Results: The estimated take-off ground reaction forces show similar trend with the results from past studies. Although overall inconsistencies between simulated muscle activation and EMG from previous studies were observed, it is worth noting that the activation of the tibialis anterior, gluteus maximus, and long head of the biceps femoris was similar to specific EMG results. Among lower extremity extensors, soleus, vastus lateralis, biceps femoris long head, gluteus maximus, and semimembranosus showed high levels of activation and joint extension torque contribution. Discussion: Results of this study advanced the understanding of muscle action during ski jumping take-off. The simulation approach we developed may help guide the physical training of jumpers for improved take-off performance and can also be extended to other phases of ski jumping.

Markerless motion capture estimates of lower extremity kinematics and kinetics are comparable to marker-based across 8 movements

Motion analysis is essential for assessing in-vivo human biomechanics. Marker-based motion capture is the standard to analyze human motion, but the inherent inaccuracy and practical challenges limit its utility in large-scale and real-world applications. Markerless motion capture has shown promise to overcome these practical barriers. However, its fidelity in quantifying joint kinematics and kinetics has not been verified across multiple common human movements. In this study, we concurrently captured marker-based and markerless motion data on 10 healthy study participants performing 8 daily living and exercise movements. We calculated the correlation (Rxy) and root-mean-square difference (RMSD) between markerless and marker-based estimates of ankle dorsi-plantarflexion, knee flexion, and three-dimensional hip kinematics (angles) and kinetics (moments) during each movement. Estimates from markerless motion capture matched closely with marker-based in ankle and knee joint angles (Rxy ≥ 0.877, RMSD ≤ 5.9°) and moments (Rxy ≥ 0.934, RMSD ≤ 2.66 % height × weight). High outcome comparability means the practical benefits of markerless motion capture can simplify experiments and facilitate large-scale analyses. Hip angles and moments demonstrated more differences between the two systems (RMSD: 6.7-15.9° and up to 7.15 % height × weight), especially during rapid movements such as running. Markerless motion capture appears to improve the accuracy of hip-related measures, yet more research is needed for validation. We encourage the biomechanics community to continue verifying, validating, and establishing best practices for markerless motion capture, which holds exciting potential to advance collaborative biomechanical research and expand real-world assessments needed for clinical translation.

Measurement of Shoulder Abduction Angle with Posture Estimation Artificial Intelligence Model

Substantial advancements in markerless motion capture accuracy exist, but discrepancies persist when measuring joint angles compared to those taken with a goniometer. This study integrates machine learning techniques with markerless motion capture, with an aim to enhance this accuracy. Two artificial intelligence-based libraries-MediaPipe and LightGBM-were employed in executing markerless motion capture and shoulder abduction angle estimation. The motion of ten healthy volunteers was captured using smartphone cameras with right shoulder abduction angles ranging from 10° to 160°. The cameras were set diagonally at 45°, 30°, 15°, 0°, -15°, or -30° relative to the participant situated at a distance of 3 m. To estimate the abduction angle, machine learning models were developed considering the angle data from the goniometer as the ground truth. The model performance was evaluated using the coefficient of determination R2 and mean absolute percentage error, which were 0.988 and 1.539%, respectively, for the trained model. This approach could estimate the shoulder abduction angle, even if the camera was positioned diagonally with respect to the object. Thus, the proposed models can be utilized for the real-time estimation of shoulder motion during rehabilitation or sports motion.

Quantifying Jump Height Using Markerless Motion Capture with a Single Smartphone

Goal: The countermovement jump (CMJ) is commonly used to measure lower-body explosive power. This study evaluates how accurately markerless motion capture (MMC) with a single smartphone can measure bilateral and unilateral CMJ jump height. Methods: First, three repetitions each of bilateral and unilateral CMJ were performed by sixteen healthy adults (mean age: 30.87 [Formula: see text] 7.24 years; mean BMI: 23.14 [Formula: see text] 2.55 [Formula: see text]) on force plates and simultaneously captured using optical motion capture (OMC) and one smartphone camera. Next, MMC was performed on the smartphone videos using OpenPose. Then, we evaluated MMC in quantifying jump height using the force plate and OMC as ground truths. Results: MMC quantifies jump heights with ICC between 0.84 and 0.99 without manual segmentation and camera calibration. Conclusions: Our results suggest that using a single smartphone for markerless motion capture is promising.

Inter-Device Reliability of a Three-Dimensional Markerless Motion Capture System Quantifying Elementary Movement Patterns in Humans

With advancements in technology able to quantify wide-ranging features of human movement, the aim of the present study was to investigate the inter-device technological reliability of a three-dimensional markerless motion capture system (3D-MCS), quantifying different movement tasks. A total of 20 healthy individuals performed a test battery consisting of 29 different movements, from which 214 different metrics were derived. Two 3D-MCS located in close proximity were utilized to quantify movement characteristics. Independent sample t-tests with selected reliability statistics (i.e., intraclass correlation coefficient (ICC), effect sizes, and mean absolute differences) were used to evaluate the agreement between the two systems. The study results suggested that 95.7% of all metrics analyzed revealed negligible or small between-device effect sizes. Further, 91.6% of all metrics analyzed showed moderate or better agreement when looking at the ICC values, while 32.2% of all metrics showed excellent agreement. For metrics measuring joint angles (198 metrics), the mean difference between systems was 2.9 degrees, while for metrics investigating distance measures (16 metrics; e.g., center of mass depth), the mean difference between systems was 0.62 cm. Caution is advised when trying to generalize the study findings beyond the specific technology and software used in this investigation. Given the technological reliability reported in this study, as well as the logistical and time-related limitations associated with marker-based motion capture systems, it may be suggested that 3D-MCS present practitioners with an opportunity to reliably and efficiently measure the movement characteristics of patients and athletes. This has implications for monitoring the health/performance of a broad range of populations.

Markerless motion capture estimates of lower extremity kinematics and kinetics are comparable to marker-based across 8 movements

Motion analysis is essential for assessing in-vivo human biomechanics. Marker-based motion capture is the standard to analyze human motion, but the inherent inaccuracy and practical challenges limit its utility in large-scale and real-world applications. Markerless motion capture has shown promise to overcome these practical barriers. However, its fidelity in quantifying joint kinematics and kinetics has not been verified across multiple common human movements. In this study, we concurrently captured marker-based and markerless motion data on 10 healthy subjects performing 8 daily living and exercise movements. We calculated the correlation (R xy ) and root-mean-square difference (RMSD) between markerless and marker-based estimates of ankle dorsi-plantarflexion, knee flexion, and three-dimensional hip kinematics (angles) and kinetics (moments) during each movement. Estimates from markerless motion capture matched closely with marker-based in ankle and knee joint angles (R xy ≥ 0.877, RMSD ≤ 5.9°) and moments (R xy ≥ 0.934, RMSD ≤ 2.66 % height × weight). High outcome comparability means the practical benefits of markerless motion capture can simplify experiments and facilitate large-scale analyses. Hip angles and moments demonstrated more differences between the two systems (RMSD: 6.7° - 15.9° and up to 7.15 % height × weight), especially during rapid movements such as running. Markerless motion capture appears to improve the accuracy of hip-related measures, yet more research is needed for validation. We encourage the biomechanics community to continue verifying, validating, and establishing best practices for markerless motion capture, which holds exciting potential to advance collaborative biomechanical research and expand real-world assessments needed for clinical translation.

Predictive utility of commercial grade technologies for assessing musculoskeletal injury risk in US Marine Corps Officer candidates

Recently, commercial grade technologies have provided black box algorithms potentially relating to musculoskeletal injury (MSKI) risk and functional movement deficits, in which may add value to a high-performance model. Thus, the purpose of this manuscript was to evaluate composite and component scores from commercial grade technologies associations to MSKI risk in Marine Officer Candidates. 689 candidates (Male candidates = 566, Female candidates = 123) performed counter movement jumps on SPARTA™ force plates and functional movements (squats, jumps, lunges) in DARI™ markerless motion capture at the start of Officer Candidates School (OCS). De-identified MSKI data was acquired from internal OCS reports for those who presented to the Physical Therapy department for MSKI treatment during the 10 weeks of training. Logistic regression analyses were conducted to validate the utility of the composite scores and supervised machine learning algorithms were deployed to create a population specific model on the normalized component variables in SPARTA™ and DARI™. Common MSKI risk factors (cMSKI) such as older age, slower run times, and females were associated with greater MSKI risk. Composite scores were significantly associated with MSKI, although the area under the curve (AUC) demonstrated poor discrimination (AUC = .55-.57). When supervised machine learning algorithms were trained on the normalized component variables and cMSKI variables, the overall training models performed well, but when the training models were tested on the testing data the models classified MSKI "by chance" (testing AUC avg = .55-.57) across all models. Composite scores and component population specific models were poor predictors of MSKI in candidates. While cMSKI, SPARTA™, and DARI™ models performed similarly, this study does not dismiss the use of commercial technologies but questions the utility of a singular screening task to predict MSKI over 10 weeks. Further investigations should evaluate occupation specific screening, serial measurements, and/or load exposure for creating MSKI risk models.

Biomechanics beyond the lab: Remote technology for osteoarthritis patient data-A scoping review

The objective of this project is to produce a review of available and validated technologies suitable for gathering biomechanical and functional research data in patients with osteoarthritis (OA), outside of a traditionally fixed laboratory setting. A scoping review was conducted using defined search terms across three databases (Scopus, Ovid MEDLINE, and PEDro), and additional sources of information from grey literature were added. One author carried out an initial title and abstract review, and two authors independently completed full-text screenings. Out of the total 5,164 articles screened, 75 were included based on inclusion criteria covering a range of technologies in articles published from 2015. These were subsequently categorised by technology type, parameters measured, level of remoteness, and a separate table of commercially available systems. The results concluded that from the growing number of available and emerging technologies, there is a well-established range in use and further in development. Of particular note are the wide-ranging available inertial measurement unit systems and the breadth of technology available to record basic gait spatiotemporal measures with highly beneficial and informative functional outputs. With the majority of technologies categorised as suitable for part-remote use, the number of technologies that are usable and fully remote is rare and they usually employ smartphone software to enable this. With many systems being developed for camera-based technology, such technology is likely to increase in usability and availability as computational models are being developed with increased sensitivities to recognise patterns of movement, enabling data collection in the wider environment and reducing costs and creating a better understanding of OA patient biomechanical and functional movement data.

Validation of two-dimensional video-based inference of finger kinematics with pose estimation

Accurate capture finger of movements for biomechanical assessments has typically been achieved within laboratory environments through the use of physical markers attached to a participant’s hands. However, such requirements can narrow the broader adoption of movement tracking for kinematic assessment outside these laboratory settings, such as in the home. Thus, there is the need for markerless hand motion capture techniques that are easy to use and accurate enough to evaluate the complex movements of the human hand. Several recent studies have validated lower-limb kinematics obtained with a marker-free technique, OpenPose. This investigation examines the accuracy of OpenPose, when applied to images from single RGB cameras, against a ‘gold standard’ marker-based optical motion capture system that is commonly used for hand kinematics estimation. Participants completed four single-handed activities with right and left hands, including hand abduction and adduction, radial walking, metacarpophalangeal (MCP) joint flexion, and thumb opposition. The accuracy of finger kinematics was assessed using the root mean square error. Mean total active flexion was compared using the Bland–Altman approach, and the coefficient of determination of linear regression. Results showed good agreement for abduction and adduction and thumb opposition activities. Lower agreement between the two methods was observed for radial walking (mean difference between the methods of 5.03°) and MCP flexion (mean difference of 6.82°) activities, due to occlusion. This investigation demonstrated that OpenPose, applied to videos captured with monocular cameras, can be used for markerless motion capture for finger tracking with an error below 11° and on the order of that which is accepted clinically.

Automatic extraction of upper-limb kinematic activity using deep learning-based markerless tracking during deep brain stimulation implantation for Parkinson's disease: A proof of concept study

Optimal placement of deep brain stimulation (DBS) therapy for treating movement disorders routinely relies on intraoperative motor testing for target determination. However, in current practice, motor testing relies on subjective interpretation and correlation of motor and neural information. Recent advances in computer vision could improve assessment accuracy. We describe our application of deep learning-based computer vision to conduct markerless tracking for measuring motor behaviors of patients undergoing DBS surgery for the treatment of Parkinson's disease. Video recordings were acquired during intraoperative kinematic testing (N = 5 patients), as part of standard of care for accurate implantation of the DBS electrode. Kinematic data were extracted from videos post-hoc using the Python-based computer vision suite DeepLabCut. Both manual and automated (80.00% accuracy) approaches were used to extract kinematic episodes from threshold derived kinematic fluctuations. Active motor epochs were compressed by modeling upper limb deflections with a parabolic fit. A semi-supervised classification model, support vector machine (SVM), trained on the parameters defined by the parabolic fit reliably predicted movement type. Across all cases, tracking was well calibrated (i.e., reprojection pixel errors 0.016-0.041; accuracies >95%). SVM predicted classification demonstrated high accuracy (85.70%) including for two common upper limb movements, arm chain pulls (92.30%) and hand clenches (76.20%), with accuracy validated using a leave-one-out process for each patient. These results demonstrate successful capture and categorization of motor behaviors critical for assessing the optimal brain target for DBS surgery. Conventional motor testing procedures have proven informative and contributory to targeting but have largely remained subjective and inaccessible to non-Western and rural DBS centers with limited resources. This approach could automate the process and improve accuracy for neuro-motor mapping, to improve surgical targeting, optimize DBS therapy, provide accessible avenues for neuro-motor mapping and DBS implantation, and advance our understanding of the function of different brain areas.

Accuracy of a markerless motion capture system in estimating upper extremity kinematics during boxing

Kinematic analysis of the upper extremity can be useful to assess the performance and skill levels of athletes during combat sports such as boxing. Although marker-based approach is widely used to obtain kinematic data, it is not suitable for “in the field” activities, i.e., when performed outside the laboratory environment. Markerless video-based systems along with deep learning-based pose estimation algorithms show great potential for estimating skeletal kinematics. However, applicability of these systems in assessing upper-limb kinematics remains unexplored in highly dynamic activities. This study aimed to assess kinematics of the upper limb estimated with a markerless motion capture system (2D video cameras along with commercially available pose estimation software Theia3D) compared to those measured with marker-based system during “in the field” boxing. A total of three elite boxers equipped with retroreflective markers were instructed to perform specific sequences of shadow boxing trials. Their movements were simultaneously recorded with 12 optoelectronic and 10 video cameras, providing synchronized data to be processed further for comparison. Comparative assessment showed higher differences in 3D joint center positions at the elbow (more than 3 cm) compared to the shoulder and wrist (<2.5 cm). In the case of joint angles, relatively weaker agreement was observed along internal/external rotation. The shoulder joint revealed better performance across all the joints. Segment velocities displayed good-to-excellent agreement across all the segments. Overall, segment velocities exhibited better performance compared to joint angles. The findings indicate that, given the practicality of markerless motion capture system, it can be a promising alternative to analyze sports-performance.

Smart Phone-Based Motion Capture and Analysis: Importance of Operating Envelope Definition and Application to Clinical Use

Human movement is vital for life, with active engagement affording function, limiting disease, and improving quality; with loss resulting in disability; and the treatment and training leading to restoration and enhancement. To foster these endeavors a need exists for a simple and reliable method for the quantitation of movement, favorable for widespread user availability. We developed a Mobile Motion Capture system (MO2CA) employing a smart-phone and colored markers (2, 5, 10 mm) and here define its operating envelope in terms of: (1) the functional distance of marker detection (range), (2) the inter-target resolution and discrimination, (3) the mobile target detection, and (4) the impact of ambient illumination intensity. MO2CA was able to detect and discriminate: (1) single targets over a range of 1 to 18 ft, (2) multiple targets from 1 ft to 11 ft, with inter-target discrimination improving with an increasing target size, (3) moving targets, with minimal errors from 2 ft to 8 ft, and (4) targets within 1 to 18 ft, with an illumination of 100–300 lux. We then evaluated the utility of motion capture in quantitating regional-finger abduction/adduction and whole body–lateral flex motion, demonstrating a quantitative discrimination between normal and abnormal motion. Overall, our results demonstrate that MO2CA has a wide operating envelope with utility for the detection of human movements large and small, encompassing the whole body, body region, and extremity and digit movements. The definition of the effective operating envelope and utility of smart phone-based motion capture as described herein will afford accuracy and appropriate use for future application studies and serve as a general approach for defining the operational bounds of future video capture technologies that arise for potential clinical use.

Comparison of marker-less and marker-based motion capture for baseball pitching kinematics

The purpose of this study was to compare baseball pitching kinematics measured with marker-less and marker-based motion capture. Two hundred and seventy-five fastball pitches were captured at 240 Hz simultaneously with a 9-camera marker-less system and a 12-camera marker system. The pitches were thrown by 30 baseball pitchers (age 17.1 ± 3.1 years). Data for each trial were time-synchronised between the two systems using the instant of ball release. Coefficients of Multiple Correlations (CMC) were computed to assess the similarity of waveforms between the two systems. Discrete measurements at foot contact, during arm cocking, and at ball release were compared between the systems using Bland-Altman plots and descriptive statistics. CMC values for the five time series analysed ranged from 0.88 to 0.97, indicating consistency in movement patterns between systems. Biases for discrete measurements ranged in magnitude from 0 to 16 degrees. Standard deviations of the differences between systems ranged from 0 to 14 degrees, while intraclass correlations ranged from 0.64 to 0.92. Thus, the marker-based and marker-less motion capture systems produced similar patterns for baseball pitching kinematics. However, based on the variations between the systems, it is recommended that a database of normative ranges be established for each system.

Unsupervised Clustering Techniques Identify Movement Strategies in the Countermovement Jump Associated With Musculoskeletal Injury Risk During US Marine Corps Officer Candidates School

Musculoskeletal injuries (MSKI) are a significant burden on the military healthcare system. Movement strategies, genetics, and fitness level have been identified as potential contributors to MSKI risk. Screening measures associated with MSKI risk are emerging, including novel technologies, such as markerless motion capture (mMoCap) and force plates (FP) and allow for field expedient measures in dynamic military settings. The aim of the current study was to evaluate movement strategies (i.e., describe variables) of the countermovement jump (CMJ) in Marine officer candidates (MOCs) via mMoCap and FP technology by clustering variables to create distinct movement strategies associated with MSKI sustained during Officer Candidates School (OCS). 728 MOCs were tested and 668 MOCs (Male MOCs = 547, Female MOCs = 121) were used for analysis. MOCs performed 3 maximal CMJs in a mMoCap space with FP embedded into the system. De-identified MSKI data was acquired from internal OCS reports for those who presented to the OCS Physical Therapy department for MSKI treatment during the 10 weeks of OCS training. Three distinct clusters were formed with variables relating to CMJ kinetics and kinematics from the mMoCap and FPs. Proportions of MOCs with a lower extremity and torso MSKI across clusters were significantly different (p < 0.001), with the high-risk cluster having the highest proportions (30.5%), followed by moderate-risk cluster (22.5%) and low-risk cluster (13.8%). Kinetics, including braking rate of force development (BRFD), braking net impulse and propulsive net impulse, were higher in low-risk cluster compared to the high-risk cluster (p < 0.001). Lesser degrees of flexion and shorter CMJ phase durations (braking phase and propulsive phase) were observed in low-risk cluster compared to both moderate-risk and high-risk clusters. Male MOCs were distributed equally across clusters while female MOCs were primarily distributed in the high-risk cluster. Movement strategies (i.e., clusters), as quantified by mMoCap and FPs, were successfully described with MOCs MSKI risk proportions between clusters. These results provide actionable thresholds of key performance indicators for practitioners to use for screening measures in classifying greater MSKI risk. These tools may add value in creating modifiable strength and conditioning training programs before or during military training.

Agreement Between Sagittal Foot and Tibia Angles During Running Derived From an Open-Source Markerless Motion Capture Platform and Manual Digitization

Several open-source platforms for markerless motion capture offer the ability to track 2-dimensional (2D) kinematics using simple digital video cameras. We sought to establish the performance of one of these platforms, DeepLabCut. Eighty-four runners who had sagittal plane videos recorded of their left lower leg were included in the study. Data from 50 participants were used to train a deep neural network for 2D pose estimation of the foot and tibia segments. The trained model was used to process novel videos from 34 participants for continuous 2D coordinate data. Overall network accuracy was assessed using the train/test errors. Foot and tibia angles were calculated for 7 strides using manual digitization and markerless methods. Agreement was assessed with mean absolute differences and intraclass correlation coefficients. Bland-Altman plots and paired t tests were used to assess systematic bias. The train/test errors for the trained network were 2.87/7.79 pixels, respectively (0.5/1.2 cm). Compared to manual digitization, the markerless method was found to systematically overestimate foot angles and underestimate tibial angles (P < .01, d = 0.06-0.26). However, excellent agreement was found between the segment calculation methods, with mean differences ≤1° and intraclass correlation coefficients ≥.90. Overall, these results demonstrate that open-source, markerless methods are a promising new tool for analyzing human motion.

Applications and limitations of current markerless motion capture methods for clinical gait biomechanics

BACKGROUND

Markerless motion capture has the potential to perform movement analysis with reduced data collection and processing time compared to marker-based methods. This technology is now starting to be applied for clinical and rehabilitation applications and therefore it is crucial that users of these systems understand both their potential and limitations. This literature review aims to provide a comprehensive overview of the current state of markerless motion capture for both single camera and multi-camera systems. Additionally, this review explores how practical applications of markerless technology are being used in clinical and rehabilitation settings, and examines the future challenges and directions markerless research must explore to facilitate full integration of this technology within clinical biomechanics.

METHODOLOGY

A scoping review is needed to examine this emerging broad body of literature and determine where gaps in knowledge exist, this is key to developing motion capture methods that are cost effective and practically relevant to clinicians, coaches and researchers around the world. Literature searches were performed to examine studies that report accuracy of markerless motion capture methods, explore current practical applications of markerless motion capture methods in clinical biomechanics and identify gaps in our knowledge that are relevant to future developments in this area.

RESULTS

Markerless methods increase motion capture data versatility, enabling datasets to be re-analyzed using updated pose estimation algorithms and may even provide clinicians with the capability to collect data while patients are wearing normal clothing. While markerless temporospatial measures generally appear to be equivalent to marker-based motion capture, joint center locations and joint angles are not yet sufficiently accurate for clinical applications. Pose estimation algorithms are approaching similar error rates of marker-based motion capture, however, without comparison to a gold standard, such as bi-planar videoradiography, the true accuracy of markerless systems remains unknown.

CONCLUSIONS

Current open-source pose estimation algorithms were never designed for biomechanical applications, therefore, datasets on which they have been trained are inconsistently and inaccurately labelled. Improvements to labelling of open-source training data, as well as assessment of markerless accuracy against gold standard methods will be vital next steps in the development of this technology.

A SWOT Analysis of Portable and Low-Cost Markerless Motion Capture Systems to Assess Lower-Limb Musculoskeletal Kinematics in Sport

Markerless motion capture systems are promising for the assessment of movement in more real world research and clinical settings. While the technology has come a long way in the last 20 years, it is important for researchers and clinicians to understand the capacities and considerations for implementing these types of systems. The current review provides a SWOT (Strengths, Weaknesses, Opportunities, and Threats) analysis related to the successful adoption of markerless motion capture technology for the assessment of lower-limb musculoskeletal kinematics in sport medicine and performance settings. 31 articles met the a priori inclusion criteria of this analysis. Findings from the analysis indicate that the improving accuracy of these systems via the refinement of machine learning algorithms, combined with their cost efficacy and the enhanced ecological validity outweighs the current weaknesses and threats. Further, the analysis makes clear that there is a need for multidisciplinary collaboration between sport scientists and computer vision scientists to develop accurate clinical and research applications that are specific to sport. While work remains to be done for broad application, markerless motion capture technology is currently on a positive trajectory and the data from this analysis provide an efficient roadmap toward widespread adoption.

Biomechanical Analysis of the Throwing Athlete and Its Impact on Return to Sport

Throwing sports remain a popular pastime and frequent source of musculoskeletal injuries, particularly those involving the shoulder and elbow. Biomechanical analyses of throwing athletes have identified pathomechanic factors that predispose throwers to injury or poor performance. These factors, or key performance indicators, are an ongoing topic of research, with the goals of improved injury prediction, prevention, and rehabilitation. Important key performance indicators in the literature to date include shoulder and elbow torque, shoulder rotation, kinetic chain function (as measured by trunk rotation timing and hip-shoulder separation), and lower-extremity mechanics (including stride characteristics). The current gold standard for biomechanical analysis of the throwing athlete involves marker-based 3-dimensional) video motion capture. Emerging technologies such as marker-less motion capture, wearable technology, and machine learning have the potential to further refine our understanding. This review will discuss the biomechanics of throwing, with particular attention to baseball pitching, while also delineating methods of modern throwing analysis, implications for clinical orthopaedic practice, and future areas of research interest.

Level of Evidence

V, expert opinion.

Long-Term Motor Learning in the "Wild" With High Volume Video Game Data

Motor learning occurs over long periods of practice during which motor acuity, the ability to execute actions more accurately, precisely, and in less time, improves. Laboratory-based studies of motor learning are typically limited to a small number of participants and a time frame of minutes to several hours per participant. There is a need to assess the generalizability of theories and findings from lab-based motor learning studies on larger samples and time scales. In addition, laboratory-based studies of motor learning use relatively simple motor tasks which participants are unlikely to be intrinsically motivated to learn, limiting the interpretation of their findings in more ecologically valid settings ("in the wild"). We studied the acquisition and longitudinal refinement of a complex sensorimotor skill embodied in a first-person shooter video game scenario, with a large sample size (N = 7174, 682,564 repeats of the 60 s game) over a period of months. Participants voluntarily practiced the gaming scenario for up to several hours per day up to 100 days. We found improvement in performance accuracy (quantified as hit rate) was modest over time but motor acuity (quantified as hits per second) improved considerably, with 40-60% retention from 1 day to the next. We observed steady improvements in motor acuity across multiple days of video game practice, unlike most motor learning tasks studied in the lab that hit a performance ceiling rather quickly. Learning rate was a non-linear function of baseline performance level, amount of daily practice, and to a lesser extent, number of days between practice sessions. In addition, we found that the benefit of additional practice on any given day was non-monotonic; the greatest improvements in motor acuity were evident with about an hour of practice and 90% of the learning benefit was achieved by practicing 30 min per day. Taken together, these results provide a proof-of-concept in studying motor skill acquisition outside the confines of the traditional laboratory, in the presence of unmeasured confounds, and provide new insights into how a complex motor skill is acquired in an ecologically valid setting and refined across much longer time scales than typically explored.

Pose2Sim: An End-to-End Workflow for 3D Markerless Sports Kinematics-Part 1: Robustness

Being able to capture relevant information about elite athletes' movement "in the wild" is challenging, especially because reference marker-based approaches hinder natural movement and are highly sensitive to environmental conditions. We propose Pose2Sim, a markerless kinematics workflow that uses OpenPose 2D pose detections from multiple views as inputs, identifies the person of interest, robustly triangulates joint coordinates from calibrated cameras, and feeds those to a 3D inverse kinematic full-body OpenSim model in order to compute biomechanically congruent joint angles. We assessed the robustness of this workflow when facing simulated challenging conditions: (Im) degrades image quality (11-pixel Gaussian blur and 0.5 gamma compression); (4c) uses few cameras (4 vs. 8); and (Cal) introduces calibration errors (1 cm vs. perfect calibration). Three physical activities were investigated: walking, running, and cycling. When averaged over all joint angles, stride-to-stride standard deviations lay between 1.7° and 3.2° for all conditions and tasks, and mean absolute errors (compared to the reference condition-Ref) ranged between 0.35° and 1.6°. For walking, errors in the sagittal plane were: 1.5°, 0.90°, 0.19° for (Im), (4c), and (Cal), respectively. In conclusion, Pose2Sim provides a simple and robust markerless kinematics analysis from a network of calibrated cameras.