Human Gait Research Articles

Multi-View Gait Recognition Based on a Siamese Vision Transformer

Although the vision transformer has been used in gait recognition, its application in multi-view gait recognition remains limited. Different views significantly affect the accuracy with which the characteristics of gait contour are extracted and identified. To address this issue, this paper proposes a Siamese mobile vision transformer (SMViT). This model not only focuses on the local characteristics of the human gait space, but also considers the characteristics of long-distance attention associations, which can extract multi-dimensional step status characteristics. In addition, it describes how different perspectives affect the gait characteristics and generates reliable features of perspective–relationship factors. The average recognition rate of SMViT for the CASIA B dataset reached 96.4%. The experimental results show that SMViT can attain a state-of-the-art performance when compared to advanced step-recognition models, such as GaitGAN, Multi_view GAN and Posegait.

HGRBOL2: Human gait recognition for biometric application using Bayesian optimization and extreme learning machine

The goal of gait recognition is to identify a person from a distance based on their walking style using a visual camera. However, the covariates such as a walk with carrying a bag and a change in clothes impact the recognition accuracy. This paper proposed a framework for human gait recognition based on deep learning and Bayesian optimization. The proposed framework includes both sequential and parallel steps. In the first step, optical flow-based motion regions are extracted and utilized to train the fine-tuned EfficentNet-B0 deep model. Simultaneously, we proposed a video frame enhancement technique. The same model is also separately trained on enhanced video frames. Instead of selecting static hyperparameters during the training process, Bayesian Optimization is employed in this work. Following that, two models have obtained: the motion frames model and the original frames model. Features are extracted from both models and fused using a proposed parallel approach named-Sq-Parallel Fusion (SqPF). The Tiger optimization algorithm was then improved and named Entropy controlled Tiger optimization (EVcTO). The best features are finally classified using an extreme learning machine (ELM) classifier. The experiment was carried out on two publicly available datasets, CASIA B and CASIA C, and yielded average accuracy of 92.04 and 94.97%, respectively. The proposed framework outperforms other deep learning-based networks in terms of accuracy.

Novel Feature Extraction and Locomotion Mode Classification Using Intelligent Lower-Limb Prosthesis

Intelligent lower-limb prosthesis appears in the public view due to its attractive and potential functions, which can help amputees restore mobility and return to normal life. To realize the natural transition of locomotion modes, locomotion mode classification is the top priority. There are mainly five steady-state and periodic motions, including LW (level walking), SA (stair ascent), SD (stair descent), RA (ramp ascent), and RD (ramp descent), while ST (standing) can also be regarded as one locomotion mode (at the start or end of walking). This paper mainly proposes four novel features, including TPDS (thigh phase diagram shape), KAT (knee angle trajectory), CPO (center position offset) and GRFPV (ground reaction force peak value) and designs ST classifier and artificial neural network (ANN) classifier by using a user-dependent dataset to classify six locomotion modes. Gaussian distributions are applied in those features to simulate the uncertainty and change of human gaits. An angular velocity threshold and GRFPV feature are used in the ST classifier, and the artificial neural network (ANN) classifier explores the mapping relation between our features and the locomotion modes. The results show that the proposed method can reach a high accuracy of 99.16% ± 0.38%. The proposed method can provide accurate motion intent of amputees to the controller and greatly improve the safety performance of intelligent lower-limb prostheses. The simple structure of ANN applied in this paper makes adaptive online learning algorithms possible in the future.

Markovian Transparency Control of an Exoskeleton Robot

In wearable robotics, certain applications require the robot to be transparent, i.e., imperceptible to the user. This is a very difficult cooperative control task due to the inherent coupling between human and robot, unpredictable human movements, and user-dependent behavior. In this letter, we propose a novel transparency controller based on discrete-time Markovian jump linear systems to minimize the human-robot interaction forces of an exoskeleton robot during walking. Our model-based stochastic control approach describes a gait cycle as an event-dependent Markov chain and uses a given transition matrix to switch between them. An IMU-based Kalman filter is used to perform real-time human state estimation and gait phase detection. The robustness and effectiveness of the proposed controller are demonstrated with experiments on a lower-limb exoskeleton driven by series elastic actuators.

A Binocular-Camera-Assisted Sensor-to-Segment Alignment Method for Inertial Sensor-Based Human Gait Analysis

Lower limb joint angles are powerful clinical indicators for mobility assessment and gait rehabilitation training. Inertial motion capture (IMC), which is both accurate and convenient, is becoming an ideal method to estimate joint angles. Considering that the corresponding segment and sensor frame are usually misaligned, an alignment procedure is required to determine the orientation offset between the segment and the sensor frame. This article presents a binocular-camera-assisted alignment procedure to align the frames of segment and inertial sensor. This procedure uses a binocular camera to acquire lower limb segment’s initial orientations with image-based human pose algorithm and then estimates the joint angle with kinematic constraint. The alignment procedure requires only sitting posture and does not need any functional movement. Ten healthy participants were recruited for the validation experiments, which included stand-up, turn-around, and walking. The accuracy and effectiveness of our alignment procedure were validated against the optical motion capture (OMC). The mean root mean square errors (RMSEs) of hip, knee, and ankle angles were 1.6°, 2.9°, and 3.9°, respectively. The result demonstrates that our procedure performs well on joint angle estimation. The proposed alignment procedure did not require any complicated functional movement, but only sitting posture, which could enable more practical joint angle estimation for patient subjects in clinical applications.

Force Sharing Problem During Gait Using Inverse Optimal Control

Human gait patterns have been intensively studied, both from medical and engineering perspectives, to understand and compensate pathologies. However, the muscle-force sharing problem is still debated as acquiring individual muscle force measurements is challenging, requiring the use of invasive devices. Recent studies, using various objective functions, suggest muscle-force sharing may result from an optimization process. This study proposes using inverse optimal control to identify an objective function. Two popular methods of inverse optimal control, bilevel and inverse Karush-Kuhn-Tucker, were investigated. The identified objective functions were then used to predict muscle forces during gait, and their performances were compared to an exhaustive list of biological cost functions from the literature. The best prediction was achieved by the bilevel inverse optimal control method, with a root-mean-squared error of 176 N (162 N) and a correlation coefficient of 0.76 (0.68) for the stance (swing) phase of the gait cycle. These muscle force predictions were thereafter used to compute joint stiffness, exhibiting an average root-mean-square error of 42 Nm.rad <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{-1}$</tex-math></inline-formula> and a correlation coefficient of 0.90 when compared to the reference. The bilevel method's prevalence in terms of robustness over inverse Karush-Kuhn-Tucker was demonstrated on human data and explained on a toy example.

Stride-to-Stride Fluctuations of Human Gait Are Affected By Chronobiology: An Exploratory Study.

Physiological processes present daily oscillations of ≈24 h, called circadian rhythms. Motor performance, for example, reaches its peak in the afternoon, although this can be affected by chronotype. Certain motor activities, for example, walking, can also be affected by circadian rhythms. Healthy walking exhibits stride-to-stride fluctuations with a fractal-like structure that enables adaptability. While pathology and aging are shown to lead to random-like fluctuations; and, therefore, decreased adaptability; the influence of circadian rhythms remains unknown. This study investigates how these fluctuations present in healthy gait are affected by the time of day and chronotype. Eighteen young adults walk for 10 min every 2 h, from 8 a.m. to 6 p.m. Footswitches are used to determine heel-strike and calculate stride time. Then, detrended fluctuation analysis is used to calculate fractal scaling. A mixed-model Analysis of Varianceis used and followed by a backward stepwise elimination process. Tukey's tests are used for pairwise comparisons. The statistical model shows the effect of time during the day (12 p.m. exhibits a higher fractal scaling compared to 8 a.m.); and chronotype (evening-types exhibit higher fractal scaling compared to morning-types). This study reveals the influence of chronobiology on stride-to-stride fluctuations. These findings open new perspectives to integrate circadian medicine in biomechanics.

Development of a novel footwear based power harvesting system

Daily activities such as walking and running possess abundant amount of energy, which is usually wasted and have the potential to be harvested. Especially, the energy generated from footsteps, if tapped appropriately, may be useful for charging electronic devices such as cell phones, wearables, and medical devices. In this study, the kinetic energy from footsteps was captured using a novel six-layered compartmental insole design with embedded piezoelectric transducers. This system was fabricated using additive manufacturing techniques and evaluated for its capabilities to charge a battery while walking and running. The charging performance was estimated initially for 6000 walking steps and extended to approximately 67,000 simulated running steps to fully charge the battery. A range of transducer arrangements were tested, indicating better power generation from the parallel combinations compared to series. Across gait activities, running was observed to lead to better coordination between the piezoelectric transducers and generation of higher power, compared to in walking. While very high amount of electrical power was not realized, the device performance was found to be satisfactory to charge low power rated wearable lifestyle electronic or medical devices. The findings from this work is anticipated to provide novel insights for power harvesting from human gait.

Event-Triggered Sliding Mode Impulsive Control for Lower Limb Rehabilitation Exoskeleton Robot Gait Tracking

Lower limb rehabilitation exoskeleton robots (LLRERs) play an important role in lower limb rehabilitation training and assistance walking for patients with lower limb movement disorders. In order to reduce and eliminate adverse effects on the accuracy of human motion gait tracking during walking with an LLRER, which is caused by the gravity and friction, the periodic ground shock force, and the human–exoskeleton interaction force, this paper proposes a feedforward–feedback hybrid control strategy of sliding mode impulsive control with gravity and friction compensation, based on the event-triggered mechanism of Lyapunov function. Firstly, to realize high-precision gait tracking with bounded error, some constraints on controller parameters are deduced by analyzing the Lyapunov-based stability. Secondly, the Zeno behavior of impulsive event triggers is excluded by the analysis of three different cases of the triggering time sequence. Finally, the effectiveness of the proposed hybrid controller is verified by the numerical simulation of the LLRER human–exoskeleton integrated system based on a three-link simplified model. It shows that an event-triggered sliding mode impulsive control strategy with gravity and friction compensation can achieve complete gait tracking with bounded error and has excellent dynamic performance under the constraints.

A Non-Laboratory Gait Dataset of Full Body Kinematics and Egocentric Vision

In this manuscript, we describe a unique dataset of human locomotion captured in a variety of out-of-the-laboratory environments captured using Inertial Measurement Unit (IMU) based wearable motion capture. The data contain full-body kinematics for walking, with and without stops, stair ambulation, obstacle course navigation, dynamic movements intended to test agility, and negotiating common obstacles in public spaces such as chairs. The dataset contains 24.2 total hours of movement data from a college student population with an approximately equal split of males to females. In addition, for one of the activities, we captured the egocentric field of view and gaze of the subjects using an eye tracker. Finally, we provide some examples of applications using the dataset and discuss how it might open possibilities for new studies in human gait analysis.

Multi-speed transformer network for neurodegenerative disease assessment and activity recognition

Background and objectiveNeurodegenerative diseases are the most frequent age-related diseases. This type of disease, if not discovered in the initial stage, will compromise the quality of life of the affected subject. Thus, a timely diagnosis is of paramount importance. One of the most used tasks from neurologists to detect and determine the severity of the disease is analysing human gait. This work presents the dataset named “Beside Gait” containing timeseries of coordinates of extracted body joints of people with neurodegenerative diseases in various stages of the disease as well as control subjects. In addition, the novel Multi-Speed transformer technique will be presented and benchmarked against several other techniques making use of deep learning and Shallow Learning. The objective is to recognize subjects affected by some form of neurodegenerative disease in early stage using a computer vision technique making use of deep learning that can be integrated into a smartphone app for offline inference with the aim of promptly initiate investigations and treatment to improve the patient's quality of life. MethodsThe recorded videos were processed, and the skeleton of the person in the video was extracted using pose estimation. The raw time-series coordinates of the joints extracted by the pose estimation algorithm were tested against novel deep neural network architectures and Shallow Learning techniques. In this work, the proposed Multi-Speed Transformer is benchmarked against other deep neural networks such as Temporal Convolutional Neural Networks, Transformers, as well as Shallow Learning techniques making use of feature extraction and different classifiers such as Random Forests, K Nearest Neighbours, Ada Boost, Linear and RBF SVM. The proposed Multi-Speed Transformer architecture has been developed to learn short and long-term patterns to model the various pathological gaits. ResultsThe Multi-Speed Transformer outperformed all other existing models reaching an accuracy of 96.9%, a sensitivity of 96.9%, a precision of 97.7%, and a specificity of 97.1% in binary classification. The accuracy in multi-class classification for detecting the presence of the disease in various stages is 71.6%, the sensitivity is 67.7%, and the specificity is 71.8%. In addition, tests have also been conducted against two other different activity recognition datasets, namely SHREC and JHMDB, in the exact same conditions. Multi-Speed Transformer has demonstrated to beat always all other tested techniques as well as the techniques reviewed in the state-of-the-art with respectively of accuracy 91.8% and 74%. Having those datasets more than two classes, specificity was not computed. ConclusionsThe Multi-Speed Transformer is a valuable technique for neurodegenerative disease assessment through computer vision. In addition, the novel dataset “Beside Gait” here presented is an important starting point for future research work on automatic recognition of neurodegenerative diseases using gait analysis.

Human Gait Activity Recognition Machine Learning Methods.

Human gait activity recognition is an emerging field of motion analysis that can be applied in various application domains. One of the most attractive applications includes monitoring of gait disorder patients, tracking their disease progression and the modification/evaluation of drugs. This paper proposes a robust, wearable gait motion data acquisition system that allows either the classification of recorded gait data into desirable activities or the identification of common risk factors, thus enhancing the subject's quality of life. Gait motion information was acquired using accelerometers and gyroscopes mounted on the lower limbs, where the sensors were exposed to inertial forces during gait. Additionally, leg muscle activity was measured using strain gauge sensors. As a matter of fact, we wanted to identify different gait activities within each gait recording by utilizing Machine Learning algorithms. In line with this, various Machine Learning methods were tested and compared to establish the best-performing algorithm for the classification of the recorded gait information. The combination of attention-based convolutional and recurrent neural networks algorithms outperformed the other tested algorithms and was individually tested further on the datasets of five subjects and delivered the following averaged results of classification: 98.9% accuracy, 96.8% precision, 97.8% sensitivity, 99.1% specificity and 97.3% F1-score. Moreover, the algorithm's robustness was also verified with the successful detection of freezing gait episodes in a Parkinson's disease patient. The results of this study indicate a feasible gait event classification method capable of complete algorithm personalization.

Joint torques estimation in human gait based on Gaussian process.

Human gait involves activities in nervous and musculoskeletal dynamics to modulate joint torques with time continuously for adapting to varieties of walking conditions. The goal of this paper is to estimate the joint torques of lower limbs in human gait based on Gaussian process. The potential uses of this study include optimization of exoskeleton assistance, control of the active prostheses, and modulating the joint torque for human-like robots. To achieve this, Gaussian process (GP) based data fusion algorithm is established with joint angles as the inputs. The statistic nature of the proposed model can explore the correlations between joint angles and joint torques, and enable accurate joint-torque estimations. Experiments were conducted for 5 subjects at three walking speed (0.8 m/s, 1.2 m/s, 1.6m/s). The results show that it is possible to estimate the joint torques at different scenarios.

A Large-Scale Synthetic Gait Dataset Towards in-the-Wild Simulation and Comparison Study

Gait recognition has a rapid development in recent years. However, current gait recognition focuses primarily on ideal laboratory scenes, leaving the gait in the wild unexplored. One of the main reasons is the difficulty of collecting in-the-wild gait datasets, which must ensure diversity of both intrinsic and extrinsic human gait factors. To remedy this problem, we propose to construct a large-scale gait dataset with the help of controllable computer simulation. In detail, to diversify the intrinsic factors of gait, we generate numerous characters with diverse attributes and associate them with various types of walking styles. To diversify the extrinsic factors of gait, we build a complicated scene with a dense camera layout. Then we design an automatic generation toolkit under Unity3D for simulating the walking scenarios and capturing the gait data. As a result, we obtain a dataset simulating towards the in-the-wild scenario, called VersatileGait, which has more than one million silhouette sequences of 10,000 subjects with diverse scenarios. VersatileGait possesses several nice properties, including huge dataset size, diverse pedestrian attributes, complicated camera layout, high-quality annotations, small domain gap with the real one, good scalability for new demands, and no privacy issues. By conducting a series of experiments, we first explore the effects of different factors on gait recognition. We further illustrate the effectiveness of using our dataset to pre-train models, which obtain considerable performance gain on CASIA-B, OU-MVLP, and CASIA-E. Besides, we show the great potential of the fine-grained labels other than the ID label in improving the efficiency and effectiveness of models. Our dataset and its corresponding generation toolkit are available at https://github.com/peterzpy/VersatileGait.

Ensemble of Heterogeneous Base Classifiers for Human Gait Recognition.

Human gait recognition is one of the most interesting issues within the subject of behavioral biometrics. The most significant problems connected with the practical application of biometric systems include their accuracy as well as the speed at which they operate, understood both as the time needed to recognize a particular person as well as the time necessary to create and train a biometric system. The present study made use of an ensemble of heterogeneous base classifiers to address these issues. A Heterogeneous ensemble is a group of classification models trained using various algorithms and combined to output an effective recognition A group of parameters identified on the basis of ground reaction forces was accepted as input signals. The proposed solution was tested on a sample of 322 people (5980 gait cycles). Results concerning the accuracy of recognition (meaning the Correct Classification Rate quality at 99.65%), as well as operation time (meaning the time of model construction at <12.5 min and the time needed to recognize a person at <0.1 s), should be considered as very good and exceed in quality other methods so far described in the literature.

Modeling biological individuality using machine learning: A study on human gait

Human gait is a complex and unique biological process that can offer valuable insights into an individual’s health and well-being. In this work, we leverage a machine learning-based approach to model individual gait signatures and identify factors contributing to inter-individual variability in gait patterns. We provide a comprehensive analysis of gait individuality by (1) demonstrating the uniqueness of gait signatures in a large-scale dataset and (2) highlighting the gait characteristics that are most distinctive to each individual. We utilized the data from three publicly available datasets comprising 5368 bilateral ground reaction force recordings during level overground walking from 671 distinct healthy individuals. Our results show that individuals can be identified with a prediction accuracy of 99.3% by using the bilateral signals of all three ground reaction force components, with only 10 out of 1342 recordings in our test data being misclassified. This indicates that the combination of bilateral ground reaction force signals with all three components provides a more comprehensive and accurate representation of an individual’s gait signature. The highest accuracy was achieved by (linear) Support Vector Machines (99.3%), followed by Random Forests (98.7%), Convolutional Neural Networks (95.8%), and Decision Trees (82.8%). The proposed approach provides a powerful tool to better understand biological individuality and has potential applications in personalized healthcare, clinical diagnosis, and therapeutic interventions.

Spatiotemporal Parameters of Gait in terms of Symmetry in Asymptomatic Individuals

Context: Human gait, or the way people walk, is a complicated motor activity involving coordinated movements of different parts of the body. It is crucial in everyday activities and is influenced by a variety of factors such as age, health status, and musculoskeletal and neurological disorders. Understanding the many characteristics of gait, especially symmetry and asymmetry, is critical for getting insights into normal locomotion patterns and recognising potential deviations associated with certain conditions. Aims: The current study aims to understand the different aspects of gait such as symmetry and asymmetry of gait to develop a deeper understanding of the underpinnings of human gait. Settings and Design: Convenience sampling was used. This was a cross-sectional observational study. Subjects and Methods: A cross-sectional study was done on 72 healthy adults between the age group of 20 and 80 according to the criteria. Convenience sampling was used. Subjects were divided into six groups having 12 subjects in each group. Gait analysis was done using GAITRite. Subjects were asked to walk three times on the walkway at their preferred speed. Since all the variables are continuous, all the data have been processed in terms of the mean. Statistical Analysis: The Statistical Software, namely Jamovi 0.9.5.12 (jamovi.org), was used for statistical analysis. Results: It was observed that step time and cycle time can be considered parameters representing symmetry and parameters such as step length, stride length, H-H base of support, swing (% of gait cycle) stance (% of gait cycle), single support (% of gait cycle), and double support (% of gait cycle) represent gait asymmetry. Conclusions: This study establishes the asymmetric parameters of gait across the age span the minimum detectable difference in all the parameters were calculated.

Modulation of Arm Swing Frequency and Gait Using Rhythmic Tactile Feedback.

Due to the neural coupling between upper and lower limbs and the importance of interlimb coordination in human gait, focusing on appropriate arm swing should be a part of gait rehabilitation in individuals with walking impairments. Despite its vital importance, there is a lack of effective methods to exploit the potential of arm swing inclusion for gait rehabilitation. In this work, we present a lightweight and wireless haptic feedback system that provides highly synchronized vibrotactile cues to the arms to manipulate arm swing and investigate the effects of this manipulation on the subjects' gait in a study with 12 participants (20-44 years). We found the developed system effectively adjusted the subjects' arm swing and stride cycle times by significantly reducing and increasing those parameters by up to 20% and 35%, respectively, compared to their baseline values during normal walking with no feedback. Particularly, the reduction of arms' and legs' cycle times translated into a substantial increase of up to 19.3% (on average) in walking speed. The response of the subjects to the feedback was also quantified in both transient and steady-state walking. The analysis of settling times from the transient responses revealed a fast and similar adaptation of both arms' and legs' movements to the feedback for reducing cycle time (i.e., increasing speed). Conversely, larger settling times and the time differences between arms' and legs' responses were observed due to feedback for increasing cycle times (i.e., reducing speed). The results clearly demonstrate the potential of the developed system to induce different arm-swing patterns as well as the ability of the proposed method to modulate key gait parameters through leveraging the interlimb neural coupling, with implications for gait training.

GaitFi: Robust Device-Free Human Identification via WiFi and Vision Multimodal Learning

As an important biomarker for human identification, human gait can be collected at a distance by passive sensors without subject cooperation, which plays an essential role in crime prevention, security detection, and other human identification applications. Presently, most research works are based on cameras and computer vision techniques to perform gait recognition. However, vision-based methods are not reliable when confronting poor illuminations, leading to degrading performances. In this article, we propose a novel multimodal gait recognition method, namely, GaitFi, which leverages WiFi signals and videos for human identification. In GaitFi, channel state information (CSI) that reflects the multipath propagation of WiFi is collected to capture human gaits, while videos are captured by cameras. To learn robust gait information, we propose a lightweight residual convolution network (LRCN) as the backbone network and further propose the two-stream GaitFi by integrating WiFi and vision features for the gait retrieval task. The GaitFi is trained by the triplet loss and classification loss on different levels of features. Extensive experiments are conducted in the real world, which demonstrates that the GaitFi outperforms state-of-the-art gait recognition methods based on single WiFi or camera, achieving 94.2% for human identification tasks of 12 subjects.

On Predicting Transitions to Compliant Surfaces in Human Gait via Neural and Kinematic Signals.

Walking surfaces of varying compliance are encountered frequently in everyday life C, and transitions between them are usually not a challenging task for most people. The human brain, based on feedback from the environment, as well as previous experience, controls the lower limb dynamics to transition to new surfaces ensuring stability and safety. However, this is not always possible for people with lower limb impairments, especially those using wearable (orthotic) or prosthetic devices. Current control methodologies for lower limb wearables and powered ankle prostheses have successfully replicated conditions for walking on rigid surfaces. However, agility and walking stability on non-flat and compliant surfaces remain a significant challenge for individuals with gait disabilities. C There is therefore the need to incorporate the human wearer in the loop and proactively adjust their control to transition to surfaces of different compliance. This work proposes a subject-specific pattern recognition (PR) and classification strategy using kinematic data and surface electromyographic (EMG) signals to recognize user intent to transition from a rigid to a compliant surface. Using a k-Nearest Neighbors (k-NN) methodology in combination with an Artificial Neural Network (ANN), our strategy can accurately predict upcoming surface stiffness transitions C in real time. C This would allow for a fast parameter control of the prosthesis C or wearable device and for adaptation to the new terrain. Classification results after employing the proposed strategy reach a prediction accuracy of up to 87.5%, proving that C predicting transitions to compliant surfaces in real time is feasible and efficient. The proposed framework can lead to increased robustness and safety of lower-limb prosthetic C or wearable devices that will eventually improve the quality of life of individuals living with C a lower limb impairment.