Clinical gait analysis using video-based pose estimation: Multiple perspectives, clinical populations, and measuring change

Reliability and validity of current computer vision based motion capture systems in gait analysis: A systematic review

BACKGROUND

Traditional instrumented gait analysis (IGA) objectively quantifies gait deviations, but its clinical use is hindered by high cost, lab environment, and complex protocols. Pose estimation algorithm (PEA)-based gait analysis, which infers joint positions from videos, offers an accessible method to detect gait abnormalities and tailor rehabilitation strategies. However, its reliability and validity in gait analysis and algorithmic factors affecting accuracy have not been reviewed.

RESEARCH QUESTION

This systematic review aims to evaluate the accuracy of PEA-based gait analysis systems and to identify the algorithmic factors impacting their accuracy.

METHOD

A total of 644 articles were initially identified through Scopus, PubMed, and IEEE, with 20 meeting the inclusion and exclusion criteria. Reliability, validity, and algorithmic parameters were extracted for detailed review.

RESULTS AND SIGNIFICANCE

Most included articles focus on validity against the gold standard, while limited evidence makes it challenging to determine reliability. OpenCap demonstrated an MAE of 4.1° for 3D joint angles, but higher errors in rotational angles require further validation. OpenPose demonstrated ICCs of 0.89-0.994 for spatiotemporal parameters and MAE < 5.2° for 2D hip and knee joint angles in the sagittal plane (ICCs = 0.67-0.92, CCCs = 0.83-0.979), but ankle kinematics exhibited poor accuracy (ICCs = 0.37-0.57, MAEs = 3.1°-9.77°, CCCs = 0.51-0.936). PEA accuracy depends on camera settings, backbone architecture, and training datasets. This study reviews the accuracy of PEA-based gait analysis systems, supporting future research in gait-related clinical applications of PEA.

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.

Computer Vision Technologies in Movement Disorders: A Systematic Review

BACKGROUND

Evaluation of movement disorders primarily relies on phenomenology. Despite refinements in diagnostic criteria, the accuracy remains suboptimal. Such a gap may be bridged by machine learning and video technology, which permit objective, quantitative, non-invasive motor analysis. Markerless automated video-analysis, namely Computer Vision, emerged as best suited for ecologically-valid assessment.

OBJECTIVES

To systematically review the application of Computer Vision for assessment, diagnosis, and monitoring of movement disorders.

METHODS

Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, we searched Cochrane, Embase, PubMed, and Scopus databases for articles published between 1984 and September 2024. We used the following search strategy: ("video analysis" OR "computer vision") AND ("Parkinson's disease" OR "PD" OR "tremor" OR "dystonia" OR "parkinsonism" OR "progressive supranuclear palsy" OR "PSP" OR "multiple system atrophy" OR "MSA" OR "corticobasal syndrome" OR "CBS" OR "chorea" OR "ballism" OR "myoclonus" OR "Tourette's syndrome").

RESULTS

Out of 1099 identified studies, 61 met inclusion criteria, and 10 additional studies were included based on authors' judgment. Parkinson's disease was the most investigated movement disorder, with gait as the prevalent motor task. OpenPose was the most used pose estimation software. Automated video-analysis consistently achieved diagnostic accuracies exceeding 80% across most movement disorders. For tremor, dystonia severity and tic detection, Computer Vision strongly aligned with accelerometery and clinical assessments.

CONCLUSIONS

Computer Vision holds potential to provide non-invasive quantification of presence and severity of movement disorders. Heterogeneity in video settings, software usage, and definition of standardized guidelines for videorecording are challenges to be addressed for real-word applications.

Kinematic and Kinetic Gait Principal Component Domains in Older Adults With and Without Functional Disability: A Cross-Sectional Study

Objectives: Gait kinematic and kinetic changes have been identified in older adults, highlighting the need to explore the principal age-related components and how these are associated with functional disability. This study aims to perform a factor analysis, including gait kinematic and kinetic parameters in older adults to establish determinant gait domains. Additionally, this study aims to identify which domains differentiate those without and with functional disability. Methods: Through a cross-sectional design, older adults aged 60 and over (n = 35 without and n = 25 with functional disability) were analyzed during overground gait. A principal component analysis (PCA) was used to determine principal components from gait parameters previously demonstrated to express age-related effects (spatiotemporal parameters, sagittal ankle moment and power, ground reaction forces peak, and tridimensional lower limb joints range of motion and positions at heel strike and toe-off). Results: Pace, variability, propulsion, hip and knee control, transverse ankle control, asymmetry, sagittal ankle control, frontal ankle control, frontal hip control, and pre-swing control domains explained 83.90% of the total gait variance in older adults. pace and frontal hip control distinguished individuals with disabilities. Conclusions: PCA identified ten gait domains in older adults. Pace and frontal hip control distinguished disabilities, revealing cautious walking patterns and weaker hip abductor strength.

Gradual restoration of gait following unicompartmental knee arthroplasty: a prospective study

BACKGROUND

This study investigates the gait characteristics and clinical outcomes following Unicompartmental Knee Arthroplasty (UKA) to provide scientific evidence for optimizing postoperative rehabilitation and patient management.

METHODS

Between December 2022 and November 2023, 34 patients with unilateral medial compartment knee osteoarthritis (KOA) underwent UKA. Preoperative and postoperative videos of patients in standing, walking (side view), squatting, and supine knee-bending positions were captured using smartphones. Gait parameters including gait cycle, swing time, swing phase, stance time, stance phase, double support time, walking speed, step time, cadence, step length, stride length, stride width, active knee flexion angle, and maximum hip and knee flexion angles during squatting were analyzed using the MediaPipe framework for human pose estimation.

RESULTS

Postoperative WOMAC scores were significantly lower than preoperative scores (P < 0.001), while postoperative KSS scores were significantly higher than preoperative scores (P < 0.001).Compared to preoperatively, postoperative affected-side gait speed, step length, step width, and active knee flexion angle all increased (P < 0.05). Additionally, postoperative gait cycle time and double-limb support time were reduced compared to preoperative values (P < 0.05). Among the 17 patients who could perform squats preoperatively and postoperatively, the maximum knee flexion angle and hip flexion angle in the squat position increased from preoperative values of (96.41 ± 20.65)° and (113.77 ± 22.56)° to postoperative values of (110.15 ± 20.79)° and (124.84 ± 21.13)°.

CONCLUSIONS

UKA significantly enhances knee joint kinematics, facilitating the transition from basic to advanced functional activities.

Digital gait biomarkers in Parkinson's disease: susceptibility/risk, progression, response to exercise, and prognosis

This narrative review examines the utility of gait digital biomarkers in Parkinson's disease (PD) research and clinical trials across four contexts: disease susceptibility/risk, disease progression, response to exercise, and fall prediction. The review of the literature to date suggests that upper body characteristics of gait (e.g., arm swing, trunk motion) may indicate susceptibility/risk of PD, while pace aspects (e.g., gait speed, stride length) are informative for tracking disease progression, exercise response, and fall likelihood. Dynamic stability aspects (e.g., trunk regularity, double-support time) worsen with disease progression but can improve with exercise. Gait variability emerges as a sensitive biomarker across all 4 contexts but with low specificity. The lack of standardized gait testing protocols and the lack of a minimum set of quantified digital gait biomarkers limit data harmonization across studies. Future studies, using a commonly agreed upon protocol, could be used to demonstrate the utility of specific gait biomarkers for clinical practice.

Validation of markerless video-based gait analysis using pose estimation in toddlers with and without neurodevelopmental disorders

Introduction

The onset of locomotion is a critical motor milestone in early childhood and increases engagement with the environment. Toddlers with neurodevelopmental disabilities often have atypical motor development that impacts later outcomes. Video-based gait analysis using pose estimation offers an alternative to standardized motor assessments which are subjective and difficult to ascertain in some populations, yet very little work has been done to determine its accuracy in young children. To fill this gap, this study aims to assess the feasibility and accuracy of pose estimation for gait analysis in children with a range of developmental levels.

Methods

We analyzed the overground gait of 112 toddlers (M: 30 months, SD: 8 months) with and without developmental disabilities using the ProtoKinetics Zeno Walkway system. Simultaneously recorded videos were processed in OpenPose to perform pose estimation and a custom MATLAB workflow to calculate average spatiotemporal gait parameters. Pearson correlations were used to compare OpenPose with the Zeno Walkway for velocity, step length, and step time. A Bland-Altman analysis (difference vs. average) was used to assess the agreement between methodologies and determine the difference of means. Developmental levels were assessed using the Mullen Scales of Early Learning.

Results

Our analysis included children with autism (n = 77), non-autism developmental concerns (n = 6), tuberous sclerosis complex (n = 13), 22q deletion (n = 1), and typical development (n = 15). Mullen early learning composite scores ranged from 49 to 95 (m = 80.91, sd = 26.68). Velocity (r = 0.87, p < 0.0001), step length (r = 0.79, p < 0.0001), and step time (r = 0.96, p < 0.0001) were all highly correlated between OpenPose and the Zeno Walkway, with an absolute difference of means of 0.04 m/s, 0.03 m, and 0.01 s, respectively.

Discussion

Our results suggest that video-based gait analysis using pose estimation is accurate in toddlers with a range of developmental levels. Video-based gait analysis is low cost and can be implemented for remote data collection in natural environments such as a participant's home. These advantages open possibilities for using repeated measures to increase our knowledge of how gait ability changes over time in pediatric populations and improve clinical screening tools, particularly in those with neurodevelopmental disabilities who exhibit motor impairments.

Assessment of temporospatial and kinematic gait parameters using human pose estimation in patients with Parkinson's disease: A comparison between near-frontal and lateral views

Gait disturbance is one of the most common symptoms in patients with Parkinson's disease (PD) that is closely associated with poor clinical outcomes. Recently, video-based human pose estimation (HPE) technology has attracted attention as a cheaper and simpler method for performing gait analysis than marker-based 3D motion capture systems. However, it remains unclear whether video-based HPE is a feasible method for measuring temporospatial and kinematic gait parameters in patients with PD and how this function varies with camera position. In this study, treadmill and overground walking in 24 patients with early PD was measured using a motion capture system and two smartphone cameras placed on the near-frontal and lateral sides of the subjects. We compared the differences in temporospatial gait parameters and kinematic characteristics between joint position data obtained from the 3D motion capture system and the markerless HPE. Our results confirm the feasibility of analyzing gait in patients with PD using HPE. Although the near-frontal view, where the heel and toe are clearly visible, is effective for estimating temporal gait parameters, the lateral view is particularly well-suited for assessing spatial gait parameters and joint angles. However, in clinical settings where lateral recordings are not feasible, near-frontal view recordings can still serve as a practical alternative to motion capture systems.

Comprehensive Gait Analysis and Kinetic Intervention for Overweight and Obese Children

BACKGROUND/OBJECTIVES

Childhood obesity is a critical public health issue associated with biomechanical and functional impairments that influence gait and physical performance. This study aimed to evaluate the impact of a six-month personalized kinetic program on gait parameters and pelvic kinematics in overweight and obese children.

METHODS

The prospective observational study included 100 children aged 8 to 15, divided into a study group (SG, n = 50) and a control group (CG, n = 50). The SG participated in a tailored kinetic program focusing on flexibility, strength, and coordination exercises, while the CG maintained their usual activities. The program consisted of 60 min sessions conducted three times per week over a six-month period. Gait parameters and pelvic symmetry indices were assessed using the BTS G-WALK system. Ethical approval was granted by the Ethics Committee of the University of Medicine and Pharmacy, Craiova, under approval no. 38/1 March 2022.

RESULTS

Significant improvements were observed in the SG, with increases in cadence (steps/min), walking speed (m/s), and pelvic symmetry indices across all planes (sagittal, frontal, and transverse) (p < 0.0001). In contrast, no significant changes were observed in pelvic symmetry indices in the CG (p > 0.01). The Spearman correlation matrix and heatmaps highlighted a strong correlation between improved gait parameters and participation in the kinetic program (correlation coefficient over 0.45).

CONCLUSIONS

The findings demonstrate that a targeted kinetic program can significantly improve gait mechanics and pelvic kinematics in overweight and obese children. These results emphasize the importance of personalized exercise interventions in managing obesity-related gait abnormalities and improving functional mobility.

Estimating hip impact velocity and acceleration from video-captured falls using a pose estimation algorithm

Analyzing video footage of falls in older adults has emerged as an alternative to traditional lab studies. However, this approach is limited by the labor-intensive process of manually labeling body parts. To address this limitation, we aimed to validate the use of the AI-based pose estimation algorithm (OpenPose) in assessing the hip impact velocity and acceleration of video-captured falls. We analyzed 110 videos of 13 older adults (64.0 ± 5.9 years old) falling sideways in an experimental setting. By applying OpenPose to each video, we generated a time series of hip positions in the video, which were then analyzed using custom MATLAB code to calculate hip impact velocity and acceleration. These calculations were compared against ground truth measurements obtained from motion capture systems (VICON for hip impact velocity) and inertial measurement units (MC10 for hip impact acceleration). We examined the agreement between the ground truth and OpenPose measurements in terms of mean of absolute error (MAE), mean of absolute percentage error (MAPE), and bias (mean of error). Results showed that OpenPose had a good accuracy in estimating hip impact velocity with minimal bias (MAE: 0.17 ± 0.13 m/s, MAPE: 7.28 ± 5.21%; percent bias: - 1.27%). However, its estimation of hip impact acceleration (i.e., peak vertical hip acceleration at impact) showed poor accuracy (MAPE: 26.3 ± 19.4%), showing substantial underestimation in instances of high acceleration impacts (> 3.0 g). Further ANOVA analysis revealed OpenPose's ability to discern significant differences in hip impact velocity and acceleration based on the movement response utilized during the fall (e.g., stick-like fall, tuck-and-roll, knee block). This is the first study to validate the use of a pose estimation algorithm for identifying the hip impact kinematics in video-captured falls among older adults. Future validation studies involving diverse camera settings, fall contexts, and biomechanical parameters are warranted to extend this support for using pose estimation algorithms in this field.

Clinical Whole-Body Gait Characterization Using a Single RGB-D Sensor

Instrumented gait analysis is widely used in clinical settings for the early detection of neurological disorders, monitoring disease progression, and evaluating fall risk. However, the gold-standard marker-based 3D motion analysis is limited by high time and personnel demands. Advances in computer vision now enable markerless whole-body tracking with high accuracy. Here, we present vGait, a comprehensive 3D gait assessment method using a single RGB-D sensor and state-of-the-art pose-tracking algorithms. vGait was validated in healthy participants during frontal- and sagittal-perspective walking. Performance was comparable across perspectives, with vGait achieving high accuracy in detecting initial and final foot contacts (F1 scores > 95%) and reliably quantifying spatiotemporal gait parameters (e.g., stride time, stride length) and whole-body coordination metrics (e.g., arm swing and knee angle ROM) at different levels of granularity (mean, step-to-step variability, side asymmetry). The flexibility, accuracy, and minimal resource requirements of vGait make it a valuable tool for clinical and non-clinical applications, including outpatient clinics, medical practices, nursing homes, and community settings. By enabling efficient and scalable gait assessment, vGait has the potential to enhance diagnostic and therapeutic workflows and improve access to clinical mobility monitoring.

Towards Wearable and Portable Spine Motion Analysis Through Dynamic Optimization of Smartphone Videos and IMU Data

BACKGROUND

Monitoring spine kinematics is crucial for applications like disease evaluation and ergonomics analysis. However, the small scale of vertebrae and the number of degrees of freedom present significant challenges for noninvasive and convenient spine kinematics estimation.

METHODS

This study developed a dynamic optimization framework for wearable spine motion tracking at the intervertebral joint level by integrating smartphone videos and Inertia Measurement Units (IMUs) with dynamic constraints from a thoracolumbar spine model. Validation involved motion data from 10 healthy males performing static standing, dynamic upright trunk rotations, and gait. This data included rotations of ten IMUs on vertebrae and virtual landmarks from three smartphone videos preprocessed by OpenCap, an application leveraging computer vision for pose estimation. The kinematic measures derived from the optimized solution were compared against simultaneously collected infrared optical marker-based measurements and in vivo literature data. Solutions only based on IMUs or videos were also compared for accuracy evaluation.

RESULTS

The proposed optimization approach closely matched the reference data in the intervertebral or segmental rotation range, demonstrating minimal angular differences across all motions and the highest correlation in 3D rotations (maximal Pearson and intraclass correlation coefficients of 0.92 and 0.94, respectively). Time-series changes of joint angles also aligned well with the optical-marker reference.

CONCLUSION

Dynamic optimization of the spine simulation that integrates IMUs and computer vision outperforms the single-modality method.

SIGNIFICANCE

This markerless 3D spine motion capture method holds potential for spinal health assessment in large cohorts in real-world settings without dedicated laboratories.

Biomechanical Gait Analysis Using a Smartphone-Based Motion Capture System (OpenCap) in Patients with Neurological Disorders

This study evaluates the utility of OpenCap (v0.3), a smartphone-based motion capture system, for performing gait analysis in patients with neurological disorders. We compared kinematic and kinetic gait parameters between 10 healthy controls and 10 patients with neurological conditions, including stroke, Parkinson's disease, and cerebral palsy. OpenCap captured 3D movement dynamics using two smartphones, with data processed through musculoskeletal modeling. The key findings indicate that the patient group exhibited significantly slower gait speeds (0.67 m/s vs. 1.10 m/s, p = 0.002), shorter stride lengths (0.81 m vs. 1.29 m, p = 0.001), and greater step length asymmetry (107.43% vs. 91.23%, p = 0.023) compared to the controls. Joint kinematic analysis revealed increased variability in pelvic tilt, hip flexion, knee extension, and ankle dorsiflexion throughout the gait cycle in patients, indicating impaired motor control and compensatory strategies. These results indicate that OpenCap can effectively identify significant gait differences, which may serve as valuable biomarkers for neurological disorders, thereby enhancing its utility in clinical settings where traditional motion capture systems are impractical. OpenCap has the potential to improve access to biomechanical assessments, thereby enabling better monitoring of gait abnormalities and informing therapeutic interventions for individuals with neurological disorders.

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.