Development of a Robust, Simple, and Affordable Human Gait Analysis System Using Bottom-Up Pose Estimation With a Smartphone Camera

Artificial intelligence-enhanced 3D gait analysis with a single consumer-grade camera

Gait analysis is crucial for diagnosing and monitoring various healthcare conditions, but traditional marker-based motion capture (MoCap) systems require expensive equipment, extensive setup, and trained personnel, limiting their accessibility in clinical and home settings. Markerless systems reduce setup complexity but often require multiple cameras, fixed calibration, and are not designed for widespread clinical adoption. This study introduces 3DGait, an artificial intelligence-enhanced markerless 3-Dimensional gait analysis system that operates with a single consumer-grade depth camera, providing a streamlined, accessible alternative. The system integrates advanced machine learning algorithms to produce 49 angular, spatial, and temporal gait biomarkers commonly used in mobility analysis. We validated 3DGait against a marker-based MoCap (OptiTrack) using 16 trials from 8 healthy adults performing the Timed Up and Go (TUG) test. The system achieved an overall average mean absolute error (MAE) of 2.3°, with all MAE under 5.2°, and a Pearson's correlation coefficient (PCC) of 0.75 for angular biomarkers. All spatiotemporal biomarkers had errors no greater than 15 %. Temporal biomarkers (excluding TUG time) had errors under 0.03 s, corresponding to one video frame at 30 frames per second. These results demonstrate that 3DGait provides clinically acceptable gait metrics relative to marker-based MoCap, while eliminating the need for markers, calibration, or fixed camera placement. 3DGait's accessible, non-invasive and single camera design makes it practical for use in non-specialist clinics and home settings, supporting patient monitoring and chronic disease management. Future research will focus on validating 3DGait with diverse populations, including individuals with gait abnormalities, to broaden its clinical applications.

Virtual reality-enhanced rehabilitation for improving musculoskeletal function and recovery after trauma

Orthopedic trauma remains a critical challenge in modern healthcare, often resulting in severe mobility limitations, acute pain, and delayed recovery. Conventional rehabilitation techniques, though effective, fail to address the individualized, high-precision interventions needed for musculoskeletal injuries like fractures, joint instability, ligament tears, and muscular atrophy. Virtual reality (VR) technologies, such as Apple Vision Pro and HTC Vive Pro, offer a transformative approach by enhancing diagnostic precision, rehabilitation effectiveness, and patient engagement through interactive, immersive environments that improve clinical outcomes. These VR technologies provide real-time biomechanical data, such as joint mechanics, muscle coordination, and movement patterns, allowing clinicians to design personalized rehabilitation programs. These technologies can thus facilitate neuromuscular re-education, improve muscle proprioception, and enhance muscle coordination. Studies have shown that VR-based rehabilitation advances functional recovery, improves pain management, and reduces psychological barriers associated with immobility. VR also facilitates telemedicine, increasing accessibility for patients with geographic or mobility issues. However, while VR may provide biomechanical data, it is important to note that they fall short in accurate motion tracking, particularly in fine motor control tasks. This scoping review follows PRISMA guidelines to explore the potential of VR in orthopedic rehabilitation, analyzing its diagnostic capabilities, personalized interventions, and real-time feedback systems. Despite this, barriers remain, including regulatory challenges, limitations in haptic feedback, high cost, and patient compliance. By presenting a balanced perspective on the landscape of VR in orthopedic care, this paper emphasizes the need for rigorous clinical validation, regulatory advancements, and interdisciplinary collaboration. Ultimately, VR offers the potential to significantly improve recovery outcomes, enhance patient engagement, and streamline rehabilitation protocols, but its successful integration into clinical practice must be approached with both optimism and caution.

DeepLabCut custom-trained model and the refinement function for gait analysis

The current gold standard for the study of human movement is the marker-based motion capture system that offers high precision but constrained by costs and controlled environments. Markerless pose estimation systems emerge as ecological alternatives, allowing unobtrusive data acquisition in natural settings. This study compares the performance of two popular markerless systems, OpenPose (OP) and DeepLabCut (DLC), in assessing locomotion. Forty healthy subjects walked along a 5 m walkway equipped with four force platforms and a camera. Gait parameters were obtained using OP "BODY_25" Pre-Trained model (OPPT), DLC "Model Zoo full_human" Pre-Trained model (DLCPT) and DLC Custom-Trained model (DLCCT), then compared with those acquired from the force platforms as reference system. Our results showed that DLCCT outperformed DLCPT and OPPT, highlighting the importance of leveraging DeepLabCut transfer learning to enhance the pose estimation performance with a custom-trained neural networks. Moreover, DLCCT, with the implementation of the DLC refinement function, offers the most promising markerless pose estimation solution for evaluating locomotion. Therefore, our data provide insights into the DLC training and refinement processes required to achieve optimal performance. This study proposes perspectives for clinicians and practitioners seeking accurate low-cost methods for movement assessment beyond laboratory settings.

Concurrent Validity of Wearable Nanocomposite Strain Sensor with Two-Dimensional Goniometer and its Reliability for Monitoring Knee Active Range of Motion in Multiple Participants

The range of motion (ROM) of joints in the human body is essential for movement and functional performance. Real-time monitoring of joint angles is crucial for confirming pathologic biomechanics, providing feedback during rehabilitation, and evaluating the treatment efficacy. This study aims to evaluate the concurrent validity of a wearable nanocomposite strain sensor with a two-dimensional electrical goniometer and its repeatability for measuring knee ROM during repetitive joint movements in 10 healthy female participants. The participants performed seated knee flexion and extension in three sessions, during which knee ROM was measured simultaneously using the two devices. A statistical analysis was conducted using the intraclass correlation coefficient (ICC) and Bland-Altman analysis. The strain sensor demonstrated excellent concurrent validity (ICC = 0.94) and good reliability (ICC = 0.87), with biases close to zero and the magnitude of disagreements lying within ±5-10° for validity and ±10-15° for reliability. The standard deviation of the mean (SEM) for absolute reliability was 2.18°, with the width of variability based on SEM at 9.88°. The results indicate that the strain sensor exhibits clinically acceptable accuracy and precision, comparable to the existing wearable sensors. However, careful interpretation is required for variations in repeated measurements exceeding 10°. Future research should focus on enhancing the sensor attachment and calibration methods, along with broadening the application scope to more dynamic activities, other joints, and patients with specific pathologies. The strain sensor presents significant potential for real-time and continuous monitoring of joint angles during real-world activities as well as rehabilitation programs.

A simple 2D multibody model to better quantify the movement quality of anterior cruciate ligament patients during single leg hop

Patients with anterior cruciate ligament reconstruction frequently present asymmetries in the sagittal plane dynamics when performing single leg jumps but their assessment is inaccessible to health-care professionals as it requires a complex and expensive system. With the development of deep learning methods for human pose detection, kinematics can be quantified based on a video and this study aimed to investigate whether a relatively simple 2D multibody model could predict relevant dynamic biomarkers based on the kinematics using inverse dynamics. Six participants performed ten vertical and forward single leg hops while the kinematics and the ground reaction force "GRF" were captured using an optoelectronic system coupled with a force platform. The participants are modelled by a seven rigid bodies system and the sagittal plane kinematics was used as model input. Model outputs were compared to values measured by the force platform using intraclass correlation coefficients for seven outcomes: the peak vertical and antero-posterior GRFs and the impulses during the propulsion and landing phases and the loading ratio. The model reliability is either good or excellent for all outcomes (0,845 ≤ ICC ≤ 0.987). The study results are promising for deploying the developed model following a kinematics analysis based on a video. This could enable clinicians to assess their patients' jumps more effectively using video recordings made with widely available smartphones, even outside the laboratory.

Kinect-Based Gait Analysis System Design and Concurrent Validity in Persons with Anterolateral Shoulder Pain Syndrome, Results from a Pilot Study

As part of an investigation to detect asymmetries in gait patterns in persons with shoulder injuries, the goal of the present study was to design and validate a Kinect-based motion capture system that would enable the extraction of joint kinematics curves during gait and to compare them with the data obtained through a commercial motion capture system. The study included eight male and two female participants, all diagnosed with anterolateral shoulder pain syndrome in their right upper extremity with a minimum 18 months of disorder evolution. The participants had an average age of 31.8 ± 9.8 years, a height of 173 ± 18 cm, and a weight of 81 ± 15 kg. The gait kinematics were sampled simultaneously with the new system and the Clinical 3DMA system. Shoulder, elbow, hip, and knee kinematics were compared between systems for the pathological and non-pathological sides using repeated measures ANOVA and 1D statistical parametric mapping. For most variables, no significant difference was found between systems. Evidence of a significant difference between the newly developed system and the commercial system was found for knee flexion-extension (p < 0.004, between 60 and 80% of the gait cycle), and for shoulder abduction-adduction. The good concurrent validity of the new Kinect-based motion analysis system found in this study opens promising perspectives for clinical motion tracking using an affordable and simple system.

Validity and Reliability of OpenPose-Based Motion Analysis in Measuring Knee Valgus during Drop Vertical Jump Test

OpenPose-based motion analysis (OpenPose-MA), utilizing deep learning methods, has emerged as a compelling technique for estimating human motion. It addresses the drawbacks associated with conventional three-dimensional motion analysis (3D-MA) and human visual detection-based motion analysis (Human-MA), including costly equipment, time-consuming analysis, and restricted experimental settings. This study aims to assess the precision of OpenPose-MA in comparison to Human-MA, using 3D-MA as the reference standard. The study involved a cohort of 21 young and healthy adults. OpenPose-MA employed the OpenPose algorithm, a deep learning-based open-source two-dimensional (2D) pose estimation method. Human-MA was conducted by a skilled physiotherapist. The knee valgus angle during a drop vertical jump task was computed by OpenPose-MA and Human-MA using the same frontal-plane video image, with 3D-MA serving as the reference standard. Various metrics were utilized to assess the reproducibility, accuracy and similarity of the knee valgus angle between the different methods, including the intraclass correlation coefficient (ICC) (1, 3), mean absolute error (MAE), coefficient of multiple correlation (CMC) for waveform pattern similarity, and Pearson's correlation coefficients (OpenPose-MA vs. 3D-MA, Human-MA vs. 3D-MA). Unpaired t-tests were conducted to compare MAEs and CMCs between OpenPose-MA and Human-MA. The ICCs (1,3) for OpenPose-MA, Human-MA, and 3D-MA demonstrated excellent reproducibility in the DVJ trial. No significant difference between OpenPose-MA and Human-MA was observed in terms of the MAEs (OpenPose: 2.4° [95%CI: 1.9-3.0°], Human: 3.2° [95%CI: 2.1-4.4°]) or CMCs (OpenPose: 0.83 [range: 0.99-0.53], Human: 0.87 [range: 0.24-0.98]) of knee valgus angles. The Pearson's correlation coefficients of OpenPose-MA and Human-MA relative to that of 3D-MA were 0.97 and 0.98, respectively. This study demonstrated that OpenPose-MA achieved satisfactory reproducibility, accuracy and exhibited waveform similarity comparable to 3D-MA, similar to Human-MA. Both OpenPose-MA and Human-MA showed a strong correlation with 3D-MA in terms of knee valgus angle excursion.

Position paper on how technology for human motion analysis and relevant clinical applications have evolved over the past decades: Striking a balance between accuracy and convenience

BACKGROUND

Over the past decades, tremendous technological advances have emerged in human motion analysis (HMA).

RESEARCH QUESTION

How has technology for analysing human motion evolved over the past decades, and what clinical applications has it enabled?

METHODS

The literature on HMA has been extensively reviewed, focusing on three main approaches: Fully-Instrumented Gait Analysis (FGA), Wearable Sensor Analysis (WSA), and Deep-Learning Video Analysis (DVA), considering both technical and clinical aspects.

RESULTS

FGA techniques relying on data collected using stereophotogrammetric systems, force plates, and electromyographic sensors have been dramatically improved providing highly accurate estimates of the biomechanics of motion. WSA techniques have been developed with the advances in data collection at home and in community settings. DVA techniques have emerged through artificial intelligence, which has marked the last decade. Some authors have considered WSA and DVA techniques as alternatives to "traditional" HMA techniques. They have suggested that WSA and DVA techniques are destined to replace FGA.

SIGNIFICANCE

We argue that FGA, WSA, and DVA complement each other and hence should be accounted as "synergistic" in the context of modern HMA and its clinical applications. We point out that DVA techniques are especially attractive as screening techniques, WSA methods enable data collection in the home and community for extensive periods of time, and FGA does maintain superior accuracy and should be the preferred technique when a complete and highly accurate biomechanical data is required. Accordingly, we envision that future clinical applications of HMA would favour screening patients using DVA in the outpatient setting. If deemed clinically appropriate, then WSA would be used to collect data in the home and community to derive relevant information. If accurate kinetic data is needed, then patients should be referred to specialized centres where an FGA system is available, together with medical imaging and thorough clinical assessments.

Integrating OpenPose and SVM for Quantitative Postural Analysis in Young Adults: A Temporal-Spatial Approach

Noninvasive tracking devices are widely used to monitor real-time posture. Yet significant potential exists to enhance postural control quantification through walking videos. This study advances computational science by integrating OpenPose with a Support Vector Machine (SVM) to perform highly accurate and robust postural analysis, marking a substantial improvement over traditional methods which often rely on invasive sensors. Utilizing OpenPose-based deep learning, we generated Dynamic Joint Nodes Plots (DJNP) and iso-block postural identity images for 35 young adults in controlled walking experiments. Through Temporal and Spatial Regression (TSR) models, key features were extracted for SVM classification, enabling the distinction between various walking behaviors. This approach resulted in an overall accuracy of 0.990 and a Kappa index of 0.985. Cutting points for the ratio of top angles (TAR) and the ratio of bottom angles (BAR) effectively differentiated between left and right skews with AUC values of 0.772 and 0.775, respectively. These results demonstrate the efficacy of integrating OpenPose with SVM, providing more precise, real-time analysis without invasive sensors. Future work will focus on expanding this method to a broader demographic, including individuals with gait abnormalities, to validate its effectiveness across diverse clinical conditions. Furthermore, we plan to explore the integration of alternative machine learning models, such as deep neural networks, enhancing the system's robustness and adaptability for complex dynamic environments. This research opens new avenues for clinical applications, particularly in rehabilitation and sports science, promising to revolutionize noninvasive postural analysis.

The Difference in the Assessment of Knee Extension/Flexion Angles during Gait between Two Calibration Methods for Wearable Goniometer Sensors

Frontal and axial knee motion can affect the accuracy of the knee extension/flexion motion measurement using a wearable goniometer. The purpose of this study was to test the hypothesis that calibrating the goniometer on an individual's body would reduce errors in knee flexion angle during gait, compared to bench calibration. Ten young adults (23.2 ± 1.3 years) were enrolled. Knee flexion angles during gait were simultaneously assessed using a wearable goniometer sensor and an optical three-dimensional motion analysis system, and the absolute error (AE) between the two methods was calculated. The mean AE across a gait cycle was 2.4° (0.5°) for the on-body calibration, and the AE was acceptable (<5°) throughout a gait cycle (range: 1.5-3.8°). The mean AE for the on-bench calibration was 4.9° (3.4°) (range: 1.9-13.6°). Statistical parametric mapping (SPM) analysis revealed that the AE of the on-body calibration was significantly smaller than that of the on-bench calibration during 67-82% of the gait cycle. The results indicated that the on-body calibration of a goniometer sensor had acceptable and better validity compared to the on-bench calibration, especially for the swing phase of gait.

Improving Gait Analysis Techniques with Markerless Pose Estimation Based on Smartphone Location

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.

Clinical reliability and validity of a video-based markerless gait evaluation method

Objective

To explore the reliability and validity of gait parameters obtained from gait assessment system software employing a human posture estimation algorithm based on markerless videos of children walking in clinical practice.

Methods

Eighteen typical developmental (TD) children and ten children with developmental dysplasia of the hip (DDH) were recruited to walk along a designated sidewalk at a comfortable walking speed. A 3-dimensional gait analysis (3D GA) and a 2-dimensional markerless (2D ML) gait evaluation system were used to extract the gait kinematics parameters twice at an interval of 2 h.

Results

The two measurements of the children's kinematic gait parameters revealed no significant differences (P > 0.05). Intra-class correlation coefficients (ICC) were generally high (ICC >0.7), showing moderate to good relative reliability. The standard error of measurement (SEM) values of all gait parameters measured by the two walks were 1.26°-2.91°. The system software had good to excellent validity compared to the 3D GA, with ICC values between 0.835 and 0.957 and SEM values of 0.87°-1.71° for the gait parameters measured by both methods. The Bland-Altman plot analysis indicated no significant systematic errors.

Conclusions

The feasibility of the markerless gait assessment method using the human posture estimation-based algorithm may provide reliable and valid gait analysis results for practical clinical applications.

Validity of AI-Based Gait Analysis for Simultaneous Measurement of Bilateral Lower Limb Kinematics Using a Single Video Camera

Accuracy validation of gait analysis using pose estimation with artificial intelligence (AI) remains inadequate, particularly in objective assessments of absolute error and similarity of waveform patterns. This study aimed to clarify objective measures for absolute error and waveform pattern similarity in gait analysis using pose estimation AI (OpenPose). Additionally, we investigated the feasibility of simultaneous measuring both lower limbs using a single camera from one side. We compared motion analysis data from pose estimation AI using video footage that was synchronized with a three-dimensional motion analysis device. The comparisons involved mean absolute error (MAE) and the coefficient of multiple correlation (CMC) to compare the waveform pattern similarity. The MAE ranged from 2.3 to 3.1° on the camera side and from 3.1 to 4.1° on the opposite side, with slightly higher accuracy on the camera side. Moreover, the CMC ranged from 0.936 to 0.994 on the camera side and from 0.890 to 0.988 on the opposite side, indicating a "very good to excellent" waveform similarity. Gait analysis using a single camera revealed that the precision on both sides was sufficiently robust for clinical evaluation, while measurement accuracy was slightly superior on the camera side.

Automated Gait Analysis Based on a Marker-Free Pose Estimation Model

Gait analysis is an essential tool for detecting biomechanical irregularities, designing personalized rehabilitation plans, and enhancing athletic performance. Currently, gait assessment depends on either visual observation, which lacks consistency between raters and requires clinical expertise, or instrumented evaluation, which is costly, invasive, time-consuming, and requires specialized equipment and trained personnel. Markerless gait analysis using 2D pose estimation techniques has emerged as a potential solution, but it still requires significant computational resources and human involvement, making it challenging to use. This research proposes an automated method for temporal gait analysis that employs the MediaPipe Pose, a low-computational-resource pose estimation model. The study validated this approach against the Vicon motion capture system to evaluate its reliability. The findings reveal that this approach demonstrates good (ICC_(2,1) > 0.75) to excellent (ICC_(2,1) > 0.90) agreement in all temporal gait parameters except for double support time (right leg switched to left leg) and swing time (right), which only exhibit a moderate (ICC_(2,1) > 0.50) agreement. Additionally, this approach produces temporal gait parameters with low mean absolute error. It will be useful in monitoring changes in gait and evaluating the effectiveness of interventions such as rehabilitation or training programs in the community.

Mechanical Factors Contributing to Altered Knee Extension Moment during Gait after ACL Reconstruction: A Longitudinal Analysis

PURPOSE

This study aimed to comprehensively examine the extent to which knee flexion angle at initial contact, peak knee flexion angle, and vertical ground reaction force (vGRF) contribute to knee extension moments during gait in individuals with anterior cruciate ligament (ACL) reconstruction.

METHODS

Overground gait biomechanics were evaluated in 26 participants with ACL reconstruction at three time points (about 2, 4, and 6 months after the surgery). Knee flexion angle at initial contact, peak knee flexion angle, peak vGRF, and peak knee extension moment were calculated for each limb during the early stance phase of gait for all three time points. A change score from baseline (time point 2 - time point 1 and time point 3 - time point 1) along with limb symmetry values (ACL - non-ACL limb values) was also calculated for these variables. Multiple linear regressions utilizing classical and Bayesian interference methods were used to determine the contribution of knee flexion angle and vGRF to knee extension moment during gait.

RESULTS

Peak knee flexion angle and peak vGRF positively contributed to knee extension moment during gait in both the reconstructed ( R2 = 0.767, P < 0.001) and nonreconstructed limbs ( R2 = 0.815, P < 0.001). Similar results were observed for the symmetry values ( R2 = 0.673, P < 0.001) and change scores ( R2 = 0.731-0.883; all P < 0.001), except that the changes in knee flexion angle at initial contact also contributed to the model using the change scores in the nonreconstructed limb (time point 2 - time point 1: R2 = 0.844, P < 0.001; time point 3 - time point 1: R2 = 0.883, P < 0.001). Bayesian regression evaluating the likelihood of these prediction models showed that there was decisive evidence favoring the alternative model over the null model (all Bayes factors >1000). Standardized β coefficients indicated that changes in knee flexion angle had a greater impact (>2×) on knee extension moments than vGRF at both time points in both limbs ( βvGRF = 0.204-0.309; βkneeflexion = 0.703-0.831).

CONCLUSIONS

The findings indicate that both knee flexion angle and peak vGRF positively contribute to altered knee extension moments during gait, but the contribution of knee flexion angle is much greater than vGRF. Therefore, treatment strategies targeting these variables may improve knee loading after ACL reconstruction.

Alzheimer's Disease Detection Using Comprehensive Analysis of Timed Up and Go Test via Kinect V.2 Camera and Machine Learning

Alzheimer's disease (AD) is a progressive neurodegenerative disease affecting cognitive and functional abilities. However, many patients presume lower cognitive or functional abilities because of aging and do not undergo clinical assessments until the symptoms become too advanced. Developing a low-cost and easy-to-use AD detection tool, which can be used in any clinical or non-clinical setting, can enable widespread AD assessments and diagnosis. This paper investigated the feasibility of developing such a tool to detect AD vs. healthy control (HC) from a simple balance and walking assessment called the Timed Up and Go (TUG) test. We collected joint position data of 47 HC and 38 AD subjects as they performed TUG in front of a Kinect V.2 camera. Our signal processing and statistical analyses provided a comprehensive analysis of balance and gait with 12 significant features for discriminating AD from HC after adjusting for age and the Geriatric Depression Scale. Using these features and a support vector machine classifier, our model classified the two groups with an average accuracy of 97.75% and an F-score of 97.67% for five-fold cross-validation and 98.68% and 98.67% for leave-one-subject out cross-validation. These results demonstrate the potential of our approach as a new quantitative complementary tool for detecting AD among older adults. Our work is novel as it presents the first application of Kinect V.2 camera and machine learning to provide a comprehensive and quantitative analysis of the TUG test to detect AD patients from HC. This study supports the feasibility of developing a low-cost and convenient AD assessment tool that can be used during routine checkups or even at home; however, future investigations could confirm its clinical diagnostic value in a larger cohort.