Markerless Gait Research Articles

Two-step deep-learning identification of heel keypoints from video-recorded gait.

Accurate and fast extraction of step parameters from video recordings of gait allows for richer information to be obtained from clinical tests such as Timed Up and Go. Current deep-learning methods are promising, but lack in accuracy for many clinical use cases. Extracting step parameters will often depend on extracted landmarks (keypoints) on the feet. We hypothesize that such keypoints can be determined with an accuracy relevant for clinical practice from video recordings by combining an existing general-purpose pose estimation method (OpenPose) with custom convolutional neural networks (convnets) specifically trained to identify keypoints on the heel. The combined method finds keypoints on the posterior and lateral aspects of the heel of the foot in side-view and frontal-view images from which step length and step width can be determined for calibrated cameras. Six different candidate convnets were evaluated, combining three different standard architectures as networks for feature extraction (backbone), and with two different networks for predicting keypoints on the heel (head networks). Using transfer learning, the backbone networks were pre-trained on the ImageNet dataset, and the combined networks (backbone + head) were fine-tuned on data from 184 trials of older, unimpaired adults. The data was recorded at three different locations and consisted of 193 k side-view images and 110 k frontal-view images. We evaluated the six different models using the absolute distance on the floor between predicted keypoints and manually labelled keypoints. For the best-performing convnet, the median error was 0.55 cm and the 75% quartile was below 1.26 cm using data from the side-view camera. The predictions are overall accurate, but show some outliers. The results indicate potential for future clinical use by automating a key step in marker-less gait parameter extraction.

Feasibility and usefulness of video-based markerless two-dimensional automated gait analysis, in providing objective quantification of gait and complementing the evaluation of gait in children with cerebral palsy

BackgroundGait analysis aids in evaluation, classification, and follow-up of gait pattern over time in children with cerebral palsy (CP). The analysis of sagittal plane joint kinematics is of special interest to assess flexed knee gait and ankle joint deviations that commonly progress with age and indicate deterioration of gait. Although most children with CP are ambulatory, no objective quantification of gait is currently included in any of the known international follow-up programs. Is video-based 2-dimensional markerless (2D ML) gait analysis with automated processing a feasible and useful tool to quantify deviations, evaluate and classify gait, in children with CP?MethodsTwenty children with bilateral CP with Gross Motor Function Classification Scale (GMFCS) levels I–III, from five regions in Sweden, were included from the national CP registry. A single RGB-Depth video camera, sensitive to depth and contrast, was positioned laterally to a green walkway and background, with four light sources. A previously validated markerless method was employed to estimate sagittal plane hip, knee, ankle kinematics, foot orientation and spatio-temporal parameters including gait speed and step length.ResultsMean age was 10.4 (range 6.8–16.1) years. Eight children were classified as GMFCS level I, eight as II and four as III. Setup of the measurement system took 15 min, acquisition 5–15 min and processing 50 min per child. Using the 2D ML method kinematic deviations from normal could be determined and used to implement the classification of gait pattern, proposed by Rodda et al. 2001.Conclusion2D ML assessment is feasible, since it is accessible, easy to perform and well tolerated by the children. The 2D ML adds consistency and quantifies objectively important gait variables. It is both relevant and reasonable to include 2D ML gait assessment in the evaluation of children with CP.

AI-driven single camera markerless gait analysis in Parkinson’s disease for home-based rehabilitation: Reliability assessment

AI-driven single camera markerless gait analysis in Parkinson’s disease for home-based rehabilitation: Reliability assessment

Markerless three-dimensional gait analysis in healthy older adults: test–retest reliability and measurement error

In older adults, gait analysis may detect changes that signal early disease states, yet challenges in biomechanical screening limit widespread use in clinical or community settings. Recently, a markerless method from multi-camera video data has become accessible, making screenings less challenging. This study evaluated the test–retest reliability and measurement error of markerless gait kinematics and kinetics in healthy older adults. Twenty-nine healthy older adults performed gait analysis on two occasions, at preferred walking speed, using their everyday clothes. Lower limb angles and moments were averaged from 8 gait cycles. Integrated pointwise indices [Intraclass Correlation Coefficient (ICCA,K) and Standard Error of Measurement (SEM)] were calculated for curve data, as well as ICCA,K, and SEM [95 % confidence intervals] for selected peaks. Generally, kinematic ICCs were good (>0.75) and reasonably stable throughout the gait cycle, except for the hip kinematics during the swing phase in the sagittal plane and pelvis tilt and rotation. The integrated and peaks SEM were <2.4°. The reliability of kinetics was similar (ICC>0.75), except for the transverse hip moment and abduction peak, fluctuating more during the swing than through the stance phase. SEM were < 0.07Nm/Kg. In conclusion, these results showed good overall test–retest reliability for markerless gait kinematics and kinetics for the hip, knee, and ankle joints, moderate for the pelvis angles, and error levels of ≤5°, and SEM%≤5% for the sagittal plane. This supports this method’s use in assessing gait in healthy older adults, including kinetics, for which reliability data from markerless systems is difficult to find reported.

Comparison of Markerless Gait Analysis Results of Two Non-motorized Treadmills for VR Gait training

Comparison of Markerless Gait Analysis Results of Two Non-motorized Treadmills for VR Gait training

Improved markerless gait kinematics measurement using a biomechanically-aware algorithm with subject-specific geometric modeling

Despite the advancements in developing markerless gait analysis systems, they still demonstrate lower accuracy compared to gold-standard systems. Hence, in this research, a novel approach is presented to improve the lower limb kinematics accuracy in markerless gait analysis. This approach refines the 3D lower-limb skeletons obtained by AI-based pose estimation algorithms in a subject-specific geometric manner, preserves skeleton links’ length, benefits from gait phases information that adds biomechanical awareness to the algorithm, and utilizes an embedded trajectory smoothing. Validation of the proposed method shows that it reduces 12.6–43.5 % of root mean square error (RMSE) and significantly improves kinematic curves’ similarity to the gold-standard ones. Results also prove the feasibility of more accurate lower limb kinematics calculation using a single (2.02–7.57° RMSE) or dual RGB-D camera (1.66–7.25° RMSE). Development of such algorithms could result in requirement of fewer cameras that deliver comparable or even superior measurement accuracy compared to multi-camera approaches.

Robotics‐driven gait analysis: Assessing Azure Kinect's performance in in‐lab versus in‐corridor environments

AbstractGait analysis offers vital insights into human movement, aiding in the diagnosis, treatment, and rehabilitation of various conditions. Analyzing gait in corridors, rather than in lab, provides unique advantages for a more comprehensive understanding of human locomotion. However, limited dedicated technologies constrain gait data analysis in this context. In this study, a markerless gait analysis system using an Azure Kinect sensor mounted on a mobile robot is proposed and validated as a potential solution for gait analysis in corridors. Ten healthy participants (4 males and 6 females) underwent two tests. The first test (5 trials per participant) took place in the laboratory. Here, Azure Kinect performance was validated against a Vicon system, assessing eight gait signals and 22 gait parameters. The second test (2 trials per participant) was performed in the corridors over a 32‐m walking distance to compare this gait pattern with the one developed within the laboratory. The intrasession Intraclass Correlation Coefficient (ICC) reliability for in‐lab experiments was assessed by calculating the ICC between gait cycles captured in each session per participant. Notably, knee flexion/extension (ICC‐0.95), hip flexion/extension (ICC‐0.96), pelvis rotation (ICC‐0.88), and interankle distance (ICC‐0.98) demonstrated excellent reliability with high confidence. Similarly, hip adduction/abduction showed good reliability (ICC‐0.79), while trunk rotation exhibited moderate reliability (ICC‐0.72). In contrast, both trunk tilt (ICC‐0.24) and pelvis tilt (ICC‐0.41) consistently displayed lower reliability. This was observed for both the Vicon and the Azure systems, highlighting the intricate nature of capturing precise data for these specific signals in both systems. Validity outcomes indicated comparable error rates to literature standards ( knee flexion/extension, hip flexion/extension, and hip adduction/abduction), with 11 parameters having no significant differences from Vicon. Comparison of in‐lab and in‐corridor experiments show that individuals exhibit significantly longer stride time (1.10 s vs. 1.05 s), lower pelvis tilt ( vs. ), and lower minimum pelvis rotation ( vs. ) when walking in the laboratory. This study demonstrates promising outcomes in outdoor gait analysis with a robot‐mounted camera, revealing significant distinctions from controlled laboratory evaluations

Clinical Feasibility of a Markerless Gait Analysis System.

The gait analysis method that has been used in clinical practice to date is an optical tracking system (OTS) using a marker, but a markerless gait analysis (MGA) system is being developed because of the expensive cost and complicated examination of the OTS. To apply this MGA clinically, a comparative study of the MGA and OTS methods is necessary. The purpose of this study was to evaluate the compatibility between the OTS and the MGA methods and to evaluate the usefulness of the MGA system in actual clinical settings. From March 2021 to August 2021, 14 patients underwent gait analysis using the OTS and MGA system, and the spatiotemporal parameters and kinematic results obtained by the 2 methods were compared. To evaluate the practicality of the MGA system in an actual clinical setting, MGA was performed on 14 symptomatic children with idiopathic toe walking, who had been treated with a corrective cast, and the pre-cast and post-cast results were compared. For the OTS, the Motion Analysis Eagle system was used, and for MGA, DH Walk was used. The spatiotemporal parameters showed no significant difference between the OTS and MGA system. The joint angle graphs of the kinematics along the sagittal plane showed similar shapes as a whole, with particularly high correlations in the hip and knee (pelvis: 29.4%, hip joint: 96.7%, knee joint: 94.9%, and ankle joint: 68.5%). A quantified comparison using the CORrelation and Analysis (CORA) score also showed high similarity between the 2 methods. The MGA results of pre-cast application and post-cast removal for children with idiopathic toe walking showed a statistically significant improvement in ankle dorsiflexion after treatment (p < 0.001). MGA showed a good correlation with the conventional OTS in terms of spatiotemporal parameters and kinematics. We demonstrated that ankle sagittal kinematics improved after treatment by corrective cast in children with idiopathic toe walking using the MGA method. Thus, after the improvement of a few limitations, the MGA system may soon be able to be clinically applied.

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

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. 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. 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. 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.

The effects of tight or loose-fitting clothing on markerless gait kinematics in adults

The effects of tight or loose-fitting clothing on markerless gait kinematics in adults

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.

Comparison of kinematics between Theia markerless and conventional marker-based gait analysis in clinical patients

BackgroundMarkerless motion capture systems have the potential to make clinical gait analysis more efficient and convenient. Theia3D is a commercially available markerless system that may serve as an alternative to traditional gait analysis for clinical gait laboratories. Research QuestionWhat is the concurrent validity of markerless gait analysis using Theia3D compared to traditional marker-based gait analysis in pediatric clinical gait patients? MethodsThirty-six patients (20 male, age 2–25 years) with a range of diagnoses underwent clinical gait analysis with data being captured concurrently by a traditional marker-based motion capture system (Vicon Nexus) and a commercial markerless system (Theia3D). Multiple left strides were averaged for each subject, and the difference in kinematics (Theia - Vicon) was calculated over the gait cycle and evaluated using root mean square difference (RMSD), mean difference, and RMSD after subtracting the mean value across the gait cycle (RMSDoffset). Sub-analysis was performed for 25 patients with foot deformities, 9 wearing ankle-foot orthoses, and 6 walking with assistance (cane, crutches, walker, or handheld). ResultsKinematics showed similar patterns between the marker-based and markerless systems. RMSD was < 6° except for pelvic tilt, hip flexion, ankle inversion, foot progression, and transverse plane rotation of the hip, knee, and ankle. These measures mainly differed due to an offset between the curves. After adjusting for offsets, all RMSDoffset were < 6°. RMSD was larger for patients with foot deformities, wearing orthoses, or using assistive devices, but all RMSDoffset were still < 8°. In some cases, however, the markerless system had greater trial-to-trial variability, showed a larger knee varus “bump” in swing, or failed to track the subject. SignificanceThis study provides preliminary evidence of concurrent validity of Theia3D for pediatric patients with abnormal gait. However, some questions remain regarding identification of the knee axis and for patients with foot deformity or assistive devices.

Simplified Markerless Stride Detection Pipeline (sMaSDP) for Surface EMG Segmentation.

To diagnose mobility impairments and select appropriate physiotherapy, gait assessment studies are often recommended. These studies are usually conducted in confined clinical settings, which may feel foreign to a subject and affect their motivation, coordination, and overall mobility. Conducting gait studies in unconstrained natural settings instead, such as the subject's Activities of Daily Life (ADL), could provide a more accurate assessment. To appropriately diagnose gait deficiencies, muscle activity should be recorded in parallel with typical kinematic studies. To achieve this, Electromyography (EMG) and kinematic are collected synchronously. Our protocol sMaSDP introduces a simplified markerless gait event detection pipeline for the segmentation of EMG signals via Inertial Measurement Unit (IMU) data, based on a publicly available dataset. This methodology intends to provide a simple, detailed sequence of processing steps for gait event detection via IMU and EMG, and serves as tutorial for beginners in unconstrained gait assessment studies. In an unconstrained gait experiment, 10 healthy subjects walk through a course designed to mimic everyday walking, with their kinematic and EMG data recorded, for a total of 20 trials. Five different walking modalities, such as level walking, ramp up/down, and staircase up/down are included. By segmenting and filtering the data, we generate an algorithm that detects heel-strike events, using a single IMU, and isolates EMG activity of gait cycles. Applicable to different datasets, sMaSDP was tested in healthy gait and gait data of Parkinson's Disease (PD) patients. Using sMaSDP, we extracted muscle activity in healthy walking and identified heel-strike events in PD patient data. The algorithm parameters, such as expected velocity and cadence, are adjustable and can further improve the detection accuracy, and our emphasis on the wearable technologies makes this solution ideal for ADL gait studies.

Multi‐feature gait analysis approach using deep learning in constraint‐free environment

AbstractA quantitative gait assessment system is crucial for clinical analysis and decision‐making. Such rigorous evaluation involves costly clinical setups and domain experts for observation and analysis. To circumvent such constraints, the proposed work is conducted in a markerless environment and divided into three stages: First, we prepared a markerless gait database using videos from MNIT RAMAN LABORATORY in Jaipur. Second, we adapt the skeletal landmark data to generate kinematic gait characteristics comparable to gold‐standard marker‐based techniques. We provide a novel set of parameters based on video sequences and spatiotemporal and sagittal kinematic parameters to optimize accuracy and reliability. Third, we develop multi‐feature based gait analysis, an ensemble model based on Convolutional Neural Networks + LSTM (Long‐Short Term Memory), for gait classification. In addition, we deployed transfer learning models to correlate with our ensemble model. The findings indicate that gait analysis can be used successfully in a low‐cost clinical gait monitoring system in a constraint‐free environment. While considering the multiple gait variables, our proposed model attained an accuracy of 95.3%. Our model for quantifying gait analysis will improve access to quantitative gait analysis in clinics and rehabilitation centers and enable researchers to conduct large‐scale studies for gait‐related disorders.

Verification of gait analysis method fusing camera-based pose estimation and an IMU sensor in various gait conditions

A markerless gait analysis system can measure useful gait metrics to determine effective clinical treatment. Although this gait analysis system does not require a large space, several markers, or time constraints, it inaccurately measure lower limb joint kinematics during gait. In particular, it has a substantial ankle joint angle error. In this study, we investigated the markerless gait analysis method capability using single RGB camera-based pose estimation by OpenPose (OP) and an inertial measurement unit (IMU) sensor on the foot segment to measure ankle joint kinematics under various gait conditions. Sixteen healthy young adult males participated in the study. We compared temporo-spatial parameters and lower limb joint angles during four gait conditions with varying gait speeds and foot progression angles. These were measured by optoelectronic motion capture, markerless gait analysis method using OP, and proposed method using OP and IMU. We found that the proposed method using OP and an IMU significantly decreased the mean absolute errors of peak ankle joint angles compared with OP in the four gait conditions. The proposed method has the potential to measure temporo-spatial gait parameters and lower limb joint angles, including ankle angles, in various gait conditions as a clinical settings gait assessment tool.

Markerless gait estimation and tracking for postural assessment

Postural assessment is crucial in the sports screening system to reduce the risk of severe injury. The capture of the athlete’s posture using computer vision attracts huge attention in the sports community due to its markerless motion capture and less interference in the physical training. In this paper, a novel markerless gait estimation and tracking algorithm is proposed to locate human key-points in spatial-temporal sequences for gait analysis. First, human pose estimation using OpenPose network to detect 14 core key-points from the human body. The ratio of body joints is normalized with neck-to-pelvis distance to obtain camera invariant key-points. These key-points are subsequently used to generate a spatial-temporal sequences and it is fed into Long-Short-Term-Memory network for gait recognition. An indexed person is tracked for quick local pose estimation and postural analysis. This proposed algorithm can automate the capture of human joints for postural assessment to analyze the human motion. The proposed system is implemented on Intel Up Squared Board and it can achieve up to 9 frames-per-second with 95% accuracy of gait recognition.

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

Gait analysis is used in many fields such as Medical Diagnostics, Osteopathic medicine, Comparative and Sports-related biomechanics, etc. The most commonly used system for capturing gait is the advanced video camera-based passive marker system such as VICON. However, such systems are expensive, and reflective markers on subjects can be intrusive and time-consuming. Moreover, the setup of markers for certain rehabilitation patients, such as people with stroke or spinal cord injuries, could be difficult. Recently, some markerless systems were introduced to overcome the challenges of marker-based systems. However, current markerless systems have low accuracy and pose other challenges in gait analysis with people in long clothing, hiding the gait kinematics. The present work attempts to make an affordable, easy-to-use, accurate gait analysis system while addressing all the mentioned issues. The system in this study uses images from a video taken with a smartphone camera (800 × 600 pixels at an average rate of 30 frames per second). The system uses OpenPose, a 2D real-time multi-person keypoint detection technique. The system learns to associate body parts with individuals in the image using Convolutional Neural Networks (CNNs). This bottom-up system achieves high accuracy and real-time performance, regardless of the number of people in the image. The proposed system is called the “OpenPose based Markerless Gait Analysis System” (OMGait). Ankle, knee, and hip flexion/extension angle values were measured using OMGait in 16 healthy volunteers under different lighting and clothing conditions. The measured kinematic values were compared with a standard video camera based normative dataset and data from a markerless MS Kinect system. The mean absolute error value of the joint angles from the proposed system was less than 90 for different lighting conditions and less than 110 for different clothing conditions compared to the normative dataset. The proposed system is adequate in measuring the kinematic values of the ankle, knee, and hip. It also performs better than the markerless systems like MS Kinect that fail to measure the kinematics of ankle, knee, and hip joints under dark and bright light conditions and in subjects with long robe clothing.

A Single RGB Camera Based Gait Analysis With A Mobile Tele-Robot For Healthcare.

With the increasing awareness of high-quality life, there is a growing need for health monitoring devices running robust algorithms in home environment. Health monitoring technologies enable real-time analysis of users' health status, offering long-term healthcare support and reducing hospitalization time. The propose of this work is twofold, the software focuses on the analysis of gait, which is widely adopted for joint correction and assessing any lower limb, or spinal problem. On the hardware side, a novel marker-less gait analysis device using a low-cost RGB camera mounted on a mobile tele-robot is designed. As gait analysis with a single camera is much more challenging compared to previous works utilizing multi-cameras, a RGB-D camera or wearable sensors, we propose using vision-based human pose estimation approaches. More specifically, based on the out-put of state-of-the-art human pose estimation models, we devise measurements for four bespoke gait parameters: inversion/eversion, dorsiflexion/plantarflexion, ankle and foot progression angles. We thereby classify walking patterns into normal, supination, pronation and limp. We also illustrate how to run the proposed machine learning models in low-resource environments such as a single entry-level CPU. Experiments show that our single RGB camera method achieves competitive performance compared to multi-camera motion capture systems, at smaller hardware costs.

Silhouette-Length-Scaled Gait Parameters for Motor Functional Analysis in Mice and Rats.

Gait analysis of transgenic mice and rats modeling human diseases often suffers from the condition that those models exhibit genotype-driven differences in body size, weight, and length. Thus, we hypothesized that scaling by the silhouette length improves the reliability of gait analysis allowing normalization for individual body size differences. Here, we computed video-derived silhouette length and area parameters from a standard markerless gait analysis system using image-processing techniques. By using length- and area-derived data along with body weight and age, we systematically scaled individual gait parameters. We compared these different scaling approaches and report here that normalization for silhouette length improves the validity and reliability of gait analysis in general. The application of this silhouette length scaling to transgenic Huntington disease mice and Parkinson´s disease rats identifies the remaining differences reflecting more reliable, body length-independent motor functional differences. Overall, this emphasizes the need for silhouette-length-based intra-assay scaling as an improved standard approach in rodent gait analysis.

A comparative study of three segmentation algorithms for 2-dimensional markerless gait analysis

A comparative study of three segmentation algorithms for 2-dimensional markerless gait analysis