Comparison of three methods for reconstructing 3D motion from 2D video recordings for low cost gait analysis systems

Gait analysis has emerged as one of the most important medical field recently due to its wide range applications. Many recent computer-vision-based approaches have been made to reduce the cost of the expensive motion capture systems while assuring high accuracy result. In this paper, we introduce our new low-cost gait analysis system that is composed of two cheap monocular cameras (camcorders) placed on the left and right side of a treadmill. Each half human skeleton model is reconstructed from each view based on dynamic color segmentation, the gait analysis is then performed on these two models. We validate our method with ground truth data obtained with markers manually placed on the subject body. Comparison with the 3D skeleton reconstructed with the Kinect sensor are also presented. Our results on different subjects show that although our methodology is simple and low-cost, it is very efficient and provides accurate measure for gait assessment.

Marker-less analysis of human gait has made considerable progress in recent years. However, developing a gait analysis system capable of extracting reliable and precise kinematic data in a standard and unobtrusive manner remains an open challenge. This narrative review considers the transformation of methods for extracting gait extremity information from videos or images, perceived how analysis methods have improved from arduous manual procedures to semi-objective and objective marker-based systems and then marker-less systems. The gait analysis systems widely used restrict the analysis process with the use of markers, inhibited environmental conditions, and long processing duration. Such limitations can impede the use of a gait analysis system in multiple applications. Advancement in marker-less pose estimation and Q-learning-based techniques are opening the possibility of adopting productive methods for estimating precise poses of humans and information of movement from video frames. Vision-Based gait analysis techniques are capable of providing a cost-effective, unobtrusive solution for estimation of stick images and thus the analysis of the gait. This work provides a comprehensive review of marker-less computer vision and deep neural network-based gait analysis, parameters, design specifications, and the latest trends. This survey provides a birds-eye view of the domain. This review aims to introduce the latest trends in gait analysis using computer vision methods thus provide a single platform to learn various marker-less methods for the analysis of the gait that is likely to have a future impact in bio-mechanics while considering the challenges with accuracy and robustness that are yet to be addressed.KeywordsHuman Gait analysisMarker-less techniquesPose estimationStick imagesAbnormality detection

Objectives:Gait and motion analysis are important tools in assessment of athletic performance and clinical evaluation. Wearable sensor based solutions have advantages over video based systems by their prices and ease. Resistive, magnetic or optic Encoders, flexible resistors and accelerometers are common sensor types unsed in gait analysis systems used in rehabilitation. All these sensors have similar mounting and electronic instrumentation approach but all have separate mechanical joint design. The purpose of this study is to develop a single mechanical joint for multitype angular position sensors used in gait analysis.Methods:Single turn analog encoder, flexible resistor and 3 axis accelerometer was used as angular position sensor. Constant voltage source (7805) was used for instrumentation of analog encoder and 3 axis accelerometer driver circuit. A voltage divider was used for flexible resistor driver circuit. Mechanical design was made to obtain small and light mechanical joint where all sensors can be mounted.Results:Flexible sensor and encoder was mounded on the center of mechanical joint. Encoder is mounted outside and flexible sensor was mounted in side of the mechanical joint center. Accelerometer was mounted on lower (movable) arm of mechanical joint. Encoder has direct connection with upper and lower arms of mechanical joint. Root of flexible sensor is mounted on one side o the mechanical joint and driven by a mechanical dial on the other arm. Range of motion for analog encoder is 0-360 degree in a single plane, flexible is 0-180 degree for single plane and accelerometer is 0-360 degree for tree planes.Conclusion:Most difficult part of the design was to obtain highest range for flexible resistor. This sensor have 3 inclenght and changes its restinte related to its bending angle. It’s possible to obtain measurement by directly paste it on skin and it’s also easy to have measurement on mechanical joints in narrow angles. For a conventional mechanical joint the range can not be lower then 180 degrees. The length of resistor limits the range. This design problem was solved by adding a secondary mechanical shaft to joint center, winding the sensor over it a mechanical dial. This design can be used in training and research purpose where double check is needed. Future studies may focus on adding contless sensors and integrated circuit type angular sensors to mechanical joint.

BackgroundQuantification of locomotion is central to the study of animal movement ecology. Although technological advances have enabled researchers to acquire high-resolution kinematic data, the associated methods often require multiple cameras and complicate the analysis process. Quantifying complex animal locomotion in three-dimensional space lacks an accurate, user-friendly method.MethodsBy combining deep learning tools and the pinhole camera model, we develop a novel method for reconstructing three-dimensional animal motion trajectories from monocular videos and analyzing kinematic data. We tested spatial precision and occlusion robustness in both aerial-based and ground-based scenarios. Subsequently, the method was applied to a bat-predation biomechanics study to demonstrate its capabilities. The application is based on low-cost single camera and does not require multiple devices or precise calibration.ResultsOur method rapidly reconstructs 3D trajectories for various animal movements, including flight, walking, and preying. The estimated 3D coordinates have an average bias of 0.09 m for aerial motion and 0.044 m for ground motion. Moreover, our method is extremely robust in distance estimation when faced with foreground occlusion. We extracted kinematic parameters from the 3D trajectory and gait frequencies from pixel area changes. Applying these parameters to biomechanical analysis, the results show that the obtained parameters can accurately describe the animal’s movement.ConclusionsThis lightweight and cost-effective approach allows the analysis of animal locomotion in the natural environment. It also allows researchers to flexibly adapt it to their specific needs, facilitating intelligent monitoring of the wild animals and enhancing the understanding of their locomotion data.Supplementary informationThe online version contains supplementary material available at 10.1186/s40462-025-00608-8.

It is recognized that gait analysis is a powerful tool used to capture human locomotion and quantify the related parameters. PODOSmart® insoles have been designed to provide accurate measurements for gait analysis. PODOSmart® insoles are lightweight, slim and cost-effective. A recent publication presented the characteristics and data concerning the validity of PODOSmart® insoles in gait analysis. In literature, there is still no evidence about the repeatability of PODOSmart® gait analysis system. Such evidence is essential in order to use this device in both research and clinical settings. The aim of the present study was to assess the repeatability of PODOSmart® system. In this context, it was hypothesized that the parameters of gait analysis captured by PODOSmart® would be repeatable. In a sample consisting of 22 healthy male adults, participants performed two walking trials on a six-meter walkway. The ICC values for 28 gait variables provided by PODOSmart® indicated good to excellent test-retest reliability, ranging from 0.802 to 0.997. The present findings confirm that PODOSmart® gait analysis insoles present excellent repeatability in gait analysis parameters. These results offer additional evidence regarding the reliability of this gait analysis tool.

Gait analysis systems are essential for rehabilitation but are often time-consuming and less accessible in low- and middle-income countries. GAITWell was developed to address these challenges with its portable and modular design for automated gait data collection and analysis. This study evaluates its methodological properties. GAITWell uses discrete binary sensors on interconnected plates to capture gait data, analyzed using the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm, which identifies key reference points like foot contact and toe-off. DBSCAN detects clusters of arbitrary shapes and sizes, separates noise from data, and identifies natural patterns within the data space without prior group knowledge. Each plate measures 44 cm × 37 cm and has an 11 × 7 sensor array with 4 cm spacing. Test–retest reliability was evaluated using the intraclass correlation coefficient (ICC), standard error of the mean (SEM), and Bland–Altman plots. Concurrent validity was assessed by comparing GAITWell measurements to those from the Qualisys Pro-Reflex system. Results: 38 healthy adults participated (average age 33.2 years, SD 13.0). Correlations between GAITWell and Qualisys ranged from moderate (right step length) to very high (gait speed, cycle time, right and left step time, left step length, stance time, swing time, right and left cadence, and base of support). Moderate to good agreement was found for gait speed, cycle time, stride length, right and left step length, right and left step time, and stance and swing time, but poor agreement was observed for double support times, right and left cadence, and base of support. Preliminary analysis suggests that increasing sensor resolution could reduce measurement error by 70%. Conclusions: GAITWell is a promising tool, with future research focusing on enhancing sensor accuracy for improved reliability.

6: Treadmill training with partial body weight support in children with cerebral palsy

Biometric systems are developing and generally-used technology. Because of this generalization today many secure systems are taking advantage of biometric systems. And one of these latest growing research areas of biometric systems is gait analysis systems. Gait analysis investigates human body parts to find personal features for human identification. Getting the features successively leads the way for successful human identification based on gait analysis. Thus we will present some recent studies to capture those feature and identify humans. Several studies on this study area are examined during the survey. The advantages and disadvantages of the techniques discussed. Finally some important conclusions withdrew from these gait analysis paper.

Dynamic and Functional Gait Analysis of Severely Displaced Intra-Articular Calcaneus Fractures Treated with a Hinged External Fixator or Internal Stabilization

Cardiac and respiratory motion present a challenge to accurate dose delivery during stereotactic arrhythmia radioablation (STAR). This study investigated a motion tracking method using kilovoltage (kV) images on a gantry-mounted linear accelerator during STAR. An implantable cardioverter-defibrillator (ICD) lead tip was used for motion tracking. Planning computed tomography and cone beam computed tomography scans were analysed retrospectively on ten patients treated with STAR in RAdiosurgery for VENtricular TAchycardia (RAVENTA) (four patients underwent deep inspiratory breath-hold, two with free breathing, three under abdominal compression, and one using high frequency ventilation). A template-matching approach was developed to segment ICD lead tips in kV projections, with successful segmentation defined as a segmented position within 2mm of the two-dimensional (2D) ground truth derived from manual annotations. A probability distribution function method was used to convert 2D coordinates to three-dimensional (3D) trajectories. 3D trajectories from the 2D ground truth were used to measure ICD lead tip displacements from its mean position. Differences between 3D trajectories from 2D ground truth and segmentations were analysed. The median (range) 2D segmentation success rate was 85% (71-96%). Median (range) motion displacements were 1.4 (0.1-7.4) mm (left-right), 1.5 (0.1-10.4) mm (superior-inferior), and 0.8 (0.0-6.3) mm (anterior-posterior). The median (range) proportion of 3D estimations with errors below 2mm in all axes was 78% (43-96%). ICD lead tip motion showed patient-specific variability. This study presented a potential 3D motion tracking method for ICD lead tips during STAR.

Gait analysis is an important research field in neurodegenerative disease diagnosis. Various IMU-based and vision-based methods have been developed for measuring joint angles during walking process. Dynamic Vision Sensor (DVS) is a neuromorphic engineering product which outputs sequences of events describing the level of brightness change at the pixel level in an asynchronized manner, instead of discrete frames at a predefined frame rate. Due to its microsecond level resolution, DVS is regarded possessing a huge potential to dramatically increase the speed of sensing pipeline for various applications which traditional CMOS camera cannot fulfill. Hence, in this paper we introduce a novel system for gait analysis application; DVS and special markers are used to detect the ankle joint during walking and a method is developed to calculate the desired angle. Further, the robust locally weighted regression is employed as signal smoothing method to reduce the amount of noise. In order to evaluation its performance, an Inertial Measurement Unit (IMU)-based sensory system is also examined and compared in the same experiment and goniometer is used for providing the ground truth. By comparing the captured ankle joint angle trajectories using Dynamic Time Warping (DTW), DVS-based system appears to have higher accuracy in terms of ankle joint angle detection than IMU-based system.

Robotic walkers are assistive robotic devices that provide mobility assistance, in a domestic or clinical scenario, to individuals suffering from a gait disorder, being age related or due to injuries, surgery, or diseases. Walkers also provide a significant potential for lower limb rehabilitation. In this paper, we present a novel multimodal robotic walker platform, the ISR-AIWALKER, where innovative contributions were made both in the human- machine interface (HMI) and in a gait analysis system placed on board the platform. Taking into account the application potential of these devices, an effort was made to use low-cost sensors without sacrificing the overall performance of the system. A change was made in the HMI paradigm, moving from a force-sensing to a vision-based approach, while maintaining a natural user interaction and adding complementary safety features like correct gripping enforcement. To cope with the close proximity of the user's body, a multimodal sensor setup was considered. Using both RGB and depth map data, a kinematic model of the user's lower limbs is obtained, allowing the identification of a set of features that are used in a machine learning approach to discriminate gait asymmetries. Experiments made with several subjects revealed that the proposed HMI is able to correctly estimate the user intention in a natural and intuitive way. The gait analysis system was also evaluated and evidenced a good discrimination capability to distinguish between different gait patterns.

Although previous studies have evidenced the value of three-dimensional gait analysis (3DGA) for evaluating gait disorder, the time-consuming measurement process and space requirement has hampered its use in the clinical setting. The aim of this study was to examine the feasibility of a simplified 3DGA system for stroke patients. Thirteen pairs of stroke patients and age- (± 1 year), gender-, and gait speed- (± 0.5 m/s) matched controls were drawn from the Fujita Health University gait analysis database. 3DGA was performed using the KinemaTracer® treadmill gait analysis system. Comparisons of the spatiotemporal and kinematic parameters were performed between stroke patients and matched controls. The correlations between items from the Wisconsin Gait Scale (WGS) and 3DGA data in stroke patients were also investigated. 3DGA measurements clearly showed reduced toe clearance, hip flexion, and knee flexion in stroke patients compared with the matched controls. In contrast, significant increases were observed in hip elevation, shoulder elevation, shoulder lateral shift, and step width in stroke patients. For the four items drawn from the WGS, a significant correlation with three 3DGA parameters was observed: stance time on the impaired side, stance width, and knee flexion from toe off to midswing. In this study, significant differences in gait parameters of stroke patients and age-, gender-, and speed-matched controls were found using a simplified 3DGA system. A significant correlation with WGS was also observed. These results support the validity of the clinical measurement of gait parameters using a simplified 3DGA system.

Scientific gait analysis methods aim to offer objective measurements, to assist physicians towards an accurate diagnosis or pre-diagnosis of ailments before they actually manifest through noticeable symptoms. This paper reviews selected gait analysis system technologies, trends, applications and discusses errors and precision in spatial and angular readings. Furthermore, we propose a novel test and calibration method using a biomimetic rig. To illustrate this, we conduct three tests on an optical single-camera gait analysis system based on a mobile android smart-phone with specially developed software.

Human gait is an important indicator of health, with applications ranging from diagnosis, monitoring, and rehabilitation. In practice, the use of gait analysis has been limited. Existing gait analysis systems are either expensive, intrusive, or require well-controlled environments such as a clinic or a laboratory. We present an accurate gait analysis system that is economical and non-intrusive. Our system is based on the Kinect sensor and thus can extract comprehensive gait information from all parts of the body. Beyond standard stride information, we also measure arm kinematics, demonstrating the wide range of parameters that can be extracted. We further improve over existing work by using information from the entire body to more accurately measure stride intervals. Our system requires no markers or battery-powered sensors, and instead relies on a single, inexpensive commodity 3D sensor with a large preexisting install base. We suggest that the proposed technique can be used for continuous gait tracking at home.