Validation of a 3D Markerless Motion Capture Tool Using Multiple Pose and Depth Estimations for Quantitative Gait Analysis.

Kinematic motion analysis is widely used in health-care, sports medicine, robotics, biomechanics, sports science, etc. Motion capture systems are essential for motion analysis. There are three types of motion capture systems: marker-based capture, vision-based capture, and volumetric capture. Marker-based motion capture systems can achieve fairly accurate results but attaching markers to a body is inconvenient and time-consuming. Vision-based, marker-less motion capture systems are more desirable because of their non-intrusiveness and flexibility. Volumetric capture is a newer and more advanced marker-less motion capture system that can reconstruct realistic, full-body, animated 3D character models. But volumetric capture has rarely been used for motion analysis because volumetric motion data presents new challenges. We propose a new method for conducting kinematic motion analysis using volumetric capture data. This method consists of a three-stage pipeline. First, the motion is captured by a volumetric capture system. Then the volumetric capture data is processed using the Iterative Closest Points (ICP) algorithm to generate virtual markers that track the motion. Third, the motion tracking data is imported into the biomechanical analysis tool OpenSim for kinematic motion analysis. Our motion analysis method enables users to apply numerical motion analysis to the skeleton model in OpenSim while also studying the full-body, animated 3D model from different angles. It has the potential to provide more detailed and in-depth motion analysis for areas such as healthcare, sports science, and biomechanics.

Walking ability is essential for maintaining functional independence, but it can be impaired by conditions like hemiplegia resulting from a stroke event. In post-stroke populations, accurately assessing gait anomalies is crucial for rehabilitation to promote functional recovery, and to prevent falls or injuries. The aim of this study is to evaluate gait-related parameters using a solution based on a single RGB-D camera, specifically Microsoft Azure Kinect DK (MAK), on a short walkway in both healthy (n= 27) and post-stroke individuals with hemiplegia (n= 20). The spatio-temporal and center of mass (CoM) parameters estimated by this approach were compared with those obtained from a gold standard motion capture (MoCap) system for instrumented 3D gait analysis. The overall findings demonstrated high levels of accuracy (> 93%), and strong correlations (r > 0.9) between the parameters estimated by the two systems for both healthy and hemiplegic gait. In particular, some spatio-temporal parameters showed excellent agreement in both groups, while CoM displacements exhibited slightly lower correlation values in healthy individuals. The results of the study suggest that a solution based on a single optical sensor could serve as an effective intermediate tool for gait analysis, not only in clinical settings or controlled environments but also in those contexts where gold standard systems are not feasible.

Tracking the motions and positions in three-dimensional space is an exciting human gait analysis approach for healthcare and clinical examination. The high-end motion capture systems, such as Vicon cameras, could automate the gait analysis process, but the system is too costly for a clinical setting. We developed a cost-effective motion capture and gait analysis system using an existing commercial camera found on a mobile device. We take advantage of the Artificial Intelligence and Machine Learning technique in mobile devices for human pose estimation and detection to keep track of body motion in the environment. This paper presents our mobile application case study to measure three-dimensional kinematics of lower-body gait of the hip, knee, and ankle during walking tasks using the Apple Augmented reality toolkit. We evaluated our application by comparing it with the measurements observed by a Vicon T40s motion-tracking system. The results showed that the gait movement can be measured in real-time. The lower-gait angles of hip and knee agreed with those from the Vicon system, whereas the motions of small joint sections were not captured as accurately. The proposed application is a cost-effective, easy-to-use, and mobile gait analysis system that can be used to construct three-dimensional gait scores to improve the examination of gait and decision making in various clinical populations.

Field-based, portable motion-capture systems can be used to help identify individuals at greater risk of lower extremity injury. Microsoft Kinect-based markerless motion-capture systems meet these requirements; however, until recently, these systems were generally not automated, required substantial data postprocessing, and were not commercially available. To validate the kinematic measures of a commercially available markerless motion-capture system. Descriptive laboratory study. Laboratory. A total of 20 healthy, physically active university students (10 males, 10 females; age = 20.50 ± 2.78 years, height = 170.36 ± 9.82 cm, mass = 68.38 ± 10.07 kg, body mass index = 23.50 ± 2.40 kg/m2). Participants completed 5 jump-landing trials. Kinematic data were simultaneously recorded using Kinect-based markerless and stereophotogrammetric motion-capture systems. Sagittal- and frontal-plane trunk, hip-joint, and knee-joint angles were identified at initial ground contact of the jump landing (IC), for the maximum joint angle during the landing phase of the initial landing (MAX), and for the joint-angle displacement from IC to MAX (DSP). Outliers were removed, and data were averaged across trials. We used intraclass correlation coefficients (ICCs [2,1]) to assess intersystem reliability and the paired-samples t test to examine mean differences (α ≤ .05). Agreement existed between the systems (ICC range = -1.52 to 0.96; ICC average = 0.58), with 75.00% (n = 24/32) of the measures being validated (P ≤ .05). Agreement was better for sagittal- (ICC average = 0.84) than frontal- (ICC average = 0.35) plane measures. Agreement was best for MAX (ICC average = 0.77) compared with IC (ICC average = 0.56) and DSP (ICC average = 0.41) measures. Pairwise comparisons identified differences for 18.75% (6/32) of the measures. Fewer differences were observed for sagittal- (0.00%; 0/15) than for frontal- (35.29%; 6/17) plane measures. Between-systems differences were equivalent for MAX (18.18%; 2/11), DSP (18.18%; 2/11), and IC (20.00%; 2/10) measures. The markerless system underestimated sagittal-plane measures (86.67%; 13/15) and overestimated frontal-plane measures (76.47%; 13/17). No trends were observed for overestimating or underestimating IC, MAX, or DSP measures. Moderate agreement existed between markerless and stereophotogrammetric motion-capture systems. Better agreement existed for larger (eg, sagittal-plane, MAX) than for smaller (eg, frontal-plane, IC) joint angles. The DSP angles had the worst agreement. Markerless motion-capture systems may help clinicians identify individuals at greater risk of lower extremity injury.

Gait dysfunction is common in many clinical populations and often has a profound and deleterious impact on independence and quality of life. Gait analysis is a foundational component of rehabilitation because it is critical to identify and understand the specific deficits that should be targeted prior to the initiation of treatment. Unfortunately, current state-of-the-art approaches to gait analysis (e.g., marker-based motion capture systems, instrumented gait mats) are largely inaccessible due to prohibitive costs of time, money, and effort required to perform the assessments. Here, we demonstrate the ability to perform quantitative gait analyses in multiple clinical populations using only simple videos recorded using low-cost devices (tablets). We report four primary advances: 1) a novel, versatile workflow that leverages an open-source human pose estimation algorithm (OpenPose) to perform gait analyses using videos recorded from multiple different perspectives (e.g., frontal, sagittal), 2) validation of this workflow in three different populations of participants (adults without gait impairment, persons post-stroke, and persons with Parkinson's disease) via comparison to ground-truth three-dimensional motion capture, 3) demonstration of the ability to capture clinically relevant, condition-specific gait parameters, and 4) tracking of within-participant changes in gait, as is required to measure progress in rehabilitation and recovery. Importantly, our workflow has been made freely available and does not require prior gait analysis expertise. The ability to perform quantitative gait analyses in nearly any setting using only low-cost devices and computer vision offers significant potential for dramatic improvement in the accessibility of clinical gait analysis across different patient populations.

The resource-intensive nature of traditional marker-based motion capture systems limits opportunities for quantitative motion analysis. However, the advancement of markerless motion capture technology yields tremendous promise for accessible kinematic analyses beyond conventional research settings. This work compared the lower limb kinematics measured by a neural network-driven markerless motion capture system to those from a standard marker-based motion capture system during squat, hip hinge, and reverse lunge tasks. Fourteen adults performed three repetitions of each movement while being recorded simultaneously by two iPads and 17 infrared optical motion capture cameras. The mean peak cross-correlation values indicated high agreement for knee and hip flexion (>0.95) and poor agreement for hip adduction, knee varus, and internal rotation (<0.49) for all tasks; agreement for hip internal rotation and ankle flexion was task dependent (0.27–0.97). The average root mean square error indicated joint-specific offsets between systems, as values ranged from 6.43° to 12.32° for the knee, 11.25° to 17.35° for the hip, and 21.51° to 25.67° for the ankle. These findings suggest that, while the markerless system demonstrates the ability to capture gross motor patterns in the sagittal plane, further refinement of the underlying models is needed to improve the validity of the system’s measurements.

Accurate assessment of jumping is important for sports performance and rehabilitation. While laboratory-based motion capture is considered gold-standard, markerless motion capture (MMC) systems offer an accessible alternative for field and clinical settings. However, their validity and reliability vary, warranting a comprehensive synthesis of current literature. Six databases (CINAHL, Embase, MEDLINE, Scopus, SPORTDiscus, Web of Science) were searched following PRISMA for studies comparing MMC derived kinematics, kinetics or performance with gold-standard measures during vertical or horizontal jump tasks. Twenty studies met inclusion. The meta-analysis for sagittal-plane pooled root mean square error (RMSE) values were 5.3° for hip (95% CI 2.9–7.6°), 4.4° for knee (2.9–5.9°) and 4.9° for ankle (3.9–5.9°). Frontal-plane RMSE values were 3.0° for hip (2.5–3.5°) and 7.5° for ankle (4.1–10.9°). Pooled jump-height bias was −2.9 cm (−8.1 to 2.3 cm). Between-study heterogeneity ranged from low to substantial, with wider prediction intervals for sagittal hip, frontal ankle and jump height. This review suggests that current MMC systems can achieve moderate accuracy for lower limb jump biomechanics, but performance varies widely between systems and contexts. Practitioners should consider system-specific evidence to make informed decisions regarding the suitability of a given system for their needs.

Marker-based 3D motion capture systems, widely used for gait analysis, are accurate but have disadvantages such as cost and accessibility. Whereas markerless pose estimation has emerged as a convenient and cost-effective alternative for gait analysis, challenges remain in achieving optimal accuracy. Given the limited research on the effects of camera location and orientation on data collection accuracy, this study investigates how camera placement affects gait assessment accuracy utilizing five smartphones. This study aimed to explore the differences in data collection accuracy between marker-based systems and pose estimation, as well as to assess the impact of camera location and orientation on accuracy in pose estimation. The results showed that the differences in joint angles between pose estimation and marker-based systems are below 5°, an acceptable level for gait analysis, with a strong correlation between the two datasets supporting the effectiveness of pose estimation in gait analysis. In addition, hip and knee angles were accurately measured at the front diagonal of the subject and ankle angle at the lateral side. This research highlights the significance of careful camera placement for reliable gait analysis using pose estimation, serving as a concise reference to guide future efforts in enhancing the quantitative accuracy of gait analysis.

Markerless motion capture (MMC) shows promise for examining human movement across many domains because of its nonintrusive nature and negligible per-subject setup time. However, published MMC systems typically require specific hardware. This validation study compared lower-body joint kinematics from Ergomechanic, a hardware-agnostic pose model-based MMC system, to an established marker-based motion capture (MBMC) system. Static trial data from eighteen people were used to register MMC keypoints within a widely used musculoskeletal model. The registered model was used to calculate joint kinematics for static pose, squatting, and walking trials. A novel perturbation analysis estimated the contributions to differences in MBMC and MMC approaches to measurement disparities. Very good (0.87-1.0) correlations between the systems were calculated for ankle, knee, and hip flexion-extension angles. Good (0.70-0.86) correlations were found for hip external-internal and abduction-adduction. Pelvis and lumbar spine angles had a wider range of correlation results (-0.06 to 0.95), likely due to the few MMC keypoints in these body regions. Relative contributions from the perturbation analysis were (i) 75% from variations in MMC data relative to MBMC; (ii) 8% because MMC keypoints (26) < MBMC markers (67); and (iii) 3% from differences in musculoskeletal model scaling. These results validate Ergomechanic for leg kinematics during standing, walking, and squatting. Further, they suggest system improvements for pelvis and torso kinematics and provide new insights into the sources of known differences between MMC and MBMC measurements.

Validity of time series kinematical data as measured by a markerless motion capture system on a flatland for gait assessment

Fast and accurate pose estimation is essential for the local motion control of robots such as drones. At present, camera-based motion capture (Mocap) systems are mostly used by robots. However, this kind of Mocap system is easily affected by light noise and camera occlusion, and the cost of common commercial Mocap systems is high. To address these challenges, we propose Easy Rocap, a low-cost, open-source robot motion capture system, which can quickly and robustly capture the accurate position and orientation of the robot. Firstly, based on training a real-time object detector, an object-filtering algorithm using class and confidence is designed to eliminate false detections. Secondly, multiple-object tracking (MOT) is applied to maintain the continuity of the trajectories, and the epipolar constraint is applied to multi-view correspondences. Finally, the calibrated multi-view cameras are used to calculate the 3D coordinates of the markers and effectively estimate the 3D pose of the target robot. Our system takes in real-time multi-camera data streams, making it easy to integrate into the robot system. In the simulation scenario experiment, the average position estimation error of the method is less than 0.008 m, and the average orientation error is less than 0.65 degrees. In the real scenario experiment, we compared the localization results of our method with the advanced LiDAR-Inertial Simultaneous Localization and Mapping (SLAM) algorithm. According to the experimental results, SLAM generates drifts during turns, while our method can overcome the drifts and accumulated errors of SLAM, making the trajectory more stable and accurate. In addition, the pose estimation speed of our system can reach 30 Hz.

Understanding human behaviors and generating human-like motions are key technologies for human-robot interaction, motion synthesis in computer animation, sports training, and rehabilitation. Motion capture systems have been developed to accomplish this, and marker-based motion capture systems, in particular, have been used in measuring human actions and performing action recognition. However, marker-based motion capture systems have several drawbacks; in particular, the capture system is expensive, intrusive, and complex to use. Markerless motion capture systems have the potential to overcome these drawbacks. Recently, databases containing a large number of configurations of human whole body actions are available, and they are expected to be reused as new approaches to recognizing actions and recovering action configurations from motion depicted in videos comprising monocular images. This paper describes a design of an action database that consists of action configurations, pose descriptors from silhouette images, a stochastic model encoding each sequence of the pose descriptors, and relations between the data and the stochastic models. The proposed action database is applied to recognizing a video containing a performer doing a specific action and to recovering all the joint angles from the video. We tested the action database on recognition and configuration recovery, and the results show that the database is suitable for this purpose.

Purpose - walking gait analysis is a critical field within biomechanics, providing essential insights into human motion for applications in medical diagnostics, rehabilitation, sports science, and robotics. This study presents a comprehensive review of gait analysis techniques, examining their applications, strengths, and limitations. Method - The gait cycle, comprising stance and swing phases, is analyzed using methods such as visual gait analysis, kinematic and kinetic analysis, electromyography (EMG), motion capture systems, and wearable sensors. Visual gait analysis, despite its qualitative nature, is enhanced by quantitative approaches that offer objective data. Kinematic analysis tracks limb movements, while kinetic analysis measures forces exerted during gait. EMG reveals muscle activity, aiding in neuromuscular diagnosis. Advanced technologies like motion capture and wearable sensors provide detailed and portable monitoring capabilities. Result - Integrating these methods offers a holistic view of gait, essential for clinical interventions, athletic performance enhancement, and the development of assistive technologies. Conclusion - This study underscores the importance of multi-faceted gait analysis for advancing understanding and treatment of gait abnormalities.

As pose estimation has garnered considerable attention for kinematic analysis, numerous pose estimation models have been developed in recent times. A pose estimation model is a trained neural network that predicts human body landmarks from an image. Each model contains different strong and weak points, which make it difficult for users to decide which model to use for kinematic analysis. The accuracy of the model can be one big factor for model selection, but there are not many studies investigating this critical point. Therefore, this study aims to investigate the accuracy of different models and variants by comparing the measurements from the models and variants against reference measurements. Five male participants were invited to this study. Each participant was asked to perform five exercises: squat, squat jump, counter movement jump, walk, and jog while being recorded by twelve normal RGB cameras (Contemplas) and ten marker-based tracking cameras (VICON). The video recordings from the Contemplas were processed by six different pose estimation models and variants: Mediapipe, MeTRAbs Small, MeTRAbs X Large, YOLO, MoveNet Lightning, and MoveNet Thunder to detect joint positions. From the detected joint positions, four joint angles, left hip, right hip, left knee, and right knee, were calculated. Three-way repeated measures ANOVA and Tukey HSD post-hoc analysis were applied to compare the pose estimation models with VICON measurements. The ANOVA result showed that exercise and model factors had a significant impact on the measurement errors although angle factor did not. In the post-hoc analysis, knee joint angle errors from YOLO, MoveNet Lightning, and MoveNet Thunder in jog and walk were significantly higher than those from Mediapipe, MeTRAbs Small, and MeTRAbs X Large. In conclusion, differentiated recommendations can be given for optimum model and variant choice in different conditions in kinematic analyses.

Marker-less motion capture has been extensively studied in recent years as a means of evaluating productivity, safety, and workplace design for manual operations on-site. These technologies are ideal for circumstances in which traditional motion capture systems are ineffective due to the need for a laboratory setting and movement-inhibiting markers or sensors. However, many marker-less motion capture systems rely on RGB-D sensors that have limited range and susceptibility to interference from sunlight and ferromagnetic radiation, making them unsuitable for modeling worker actions on construction sites. To address this issue, we propose a marker-less motion capture approach utilizing optical images and depth data obtained from stereo vision cameras. Multiple camera lenses and triangulation algorithms generate depths maps similar to those produced by RGB-D sensors, while still utilizing an optical recording process unhindered by potentially harsh construction site conditions. These data are adapted for existing kinematic modeling systems (i.e. iPiMocap Studio) for 3-D pose estimation. The experiments show that the proposed approach can provide data precision comparable to that of RGB-D-based systems with fewer operational constraints; thus, motion data can be collected where previously developed methods fail due to environmental or maneuverability restrictions. With the proposed approach, kinematic modeling of human movements can be carried out on construction sites without inhibiting the mobility of the recorded subject.