Gait Biometrics Research Articles

GRLN: Gait Refined Lateral Network for gait recognition

Gait recognition aims to identify individuals at a distance based on their biometric gait patterns. While offering flexibility in network input, existing set-based methods often overlook the potential of fine-grained local feature by solely utilizing global gait feature and fail to fully exploit the communication between silhouette-level and set-level features. To alleviate this issue, we propose Gait Refined Lateral Network(GRLN), featuring plug-and-play Adaptive Feature Refinement modules (AFR) that extract discriminative features progressively from silhouette-level and set-level representations in a coarse-to-fine manner at various network depths. AFR can be widely applied in set-based gait recognition models to substantially enhance their gait recognition performance. To align with the extracted refined features, we introduce Horizontal Stable Mapping (HSM), a novel mapping technique that reduces model parameters while improving experimental results. To demonstrate the effectiveness of our method, we evaluate GRLN on two gait datasets, achieving the highest recognition rate among all set-based methods. Specifically, GRLN demonstrates an average improvement of 1.15% over the state-of-the-art set-based method on CASIA-B. Especially in the coat-wearing condition, GRLN exhibits a 5% improvement in performance compared to the contrast method GLN.

User gait biometrics in smart ambient applications through wearable accelerometer signals: an analysis of the influence of training setup on recognition accuracy

Gait recognition can exploit the signals from wearables, e.g., the accelerometers embedded in smart devices. At present, this kind of recognition mostly underlies subject verification: the incoming probe is compared only with the templates in the system gallery that belong to the claimed identity. For instance, several proposals tackle the continuous recognition of the device owner to detect possible theft or loss. In this case, assuming a short time between the gallery template acquisition and the probe is reasonable. This work rather investigates the viability of a wider range of applications including identification (comparison with a whole system gallery) in the medium-long term. The first contribution is a procedure for extraction and two-phase selection of the most relevant aggregate features from a gait signal. A model is trained for each identity using Logistic Regression. The second contribution is the experiments investigating the effect of the variability of the gait pattern in time. In particular, the recognition performance is influenced by the benchmark partition into training and testing sets when more acquisition sessions are available, like in the exploited ZJU-gaitacc dataset. When close-in-time acquisition data is only available, the results seem to suggest re-identification (short time among captures) as the most promising application for this kind of recognition. The exclusive use of different dataset sessions for training and testing can rather better highlight the dramatic effect of trait variability on the measured performance. This suggests acquiring enrollment data in more sessions when the intended use is in medium-long term applications of smart ambient intelligence.

Industrially Scalable Textile Sensing Interfaces for Extended Artificial Tactile and Human Motion Monitoring without Compromising Comfort.

Smart wearables with the capability for continuous monitoring, perceiving, and understanding human tactile and motion signals, while ensuring comfort, are highly sought after for intelligent healthcare and smart life systems. However, concurrently achieving high-performance tactile sensing, long-lasting wearing comfort, and industrialized fabrication by a low-cost strategy remains a great challenge. This is primarily due to critical research gaps in novel textile structure design for seamless integration with sensing elements. Here, an all-in-one biaxial insertion knit architecture is reported to topologically integrate sensing units within double-knit loops for the fabrication of a large-scale tactile sensing textile by using low-cost industrial manufacturing routes. High sensitivity, stability, and low hysteresis of arrayed sensing units are achieved through engineering of fractal structures of hierarchically patterned piezoresistive yarns via blistering and twisting processing. The as-prepared tactile sensing textiles show desirable sensing performance and robust mechanical property, while ensuring excellent conformability, tailorability, breathability (288 mm s-1), and moisture permeability (3591 g m-2 per day) for minimizing the effect on wearing comfort. The multifunctional applications of tactile sensing textiles are demonstrated in continuously monitoring human motions, tactile interactions with the environment, and recognizing biometric gait. Moreover, we also demonstrate that machine learning-assisted sensing textiles can accurately predict body postures, which holds great promise in advancing the development of personalized healthcare robotics, prosthetics, and intelligent interaction devices.

GAIT analysis based on GENDER detection using pre-trained models and tune parameters

In past several decades, gait biometrics has emerged as a viable alternative to traditional identification methods, offering advancements in surveillance, monitoring, and analysis techniques. However, determining gender based on gait remains a challenge, particularly in computer vision applications. This study proposes a robust and adaptable approach to address this issue by leveraging gait analysis. There is a growing need for datasets tailored to gait analysis and recognition to facilitate the extraction of relevant data. While most existing research relies on image-based gait datasets, this study utilizes the OULP-Age dataset from OU-ISIR, representing gait through gait energy images (GEIs). The methodology involves feature extraction from GEIs using pre-trained models, followed by classification with the XGBoost classifier. Gender prediction is enhanced through parameter fine-tuning of the XGBoost classifier. Comparative analysis of 11 pre-trained models for feature extraction reveals that DenseNet models, combined with optimized XGBoost parameters, demonstrate promising results for gender prediction. This study contributes to advancing gender prediction based on gait analysis and underscores the efficacy of integrating deep learning models with traditional classifiers for improved accuracy and reliability.

Identifying stress scores from gait biometrics captured using a camera: A cross-sectional study

BackgroundStress is a critical risk factor for various health issues, but an objective, non-intrusive and effective measurement approach for stress has not yet been established. Gait, the pattern of movements in human locomotion, has been proven to be a valid behavioral indicator for recognizing various mental states in a convenient manner. Research QuestionThis study aims to identify the severity of stress by assessing human gait recorded through an objective, non-intrusive measurement approach. MethodsOne hundred and fifty-two participants with an average age of 23 years old (SD = 1.07) were recruited. The Chinese version of the Perceived Stress Scale with 10 items (PSS-10) was used to assess participants’ stress levels. The participants were then required to walk naturally while being recorded with a regular camera. A total of 1320 time-domain and 1152 frequency-domain gait features were extracted from the videos. The top 40 contributing features, confirmed by dimensionality reduction, were input into models consisting of four machine-learning regression algorithms (i.e., Gaussian Process Regressor, Linear Regression, Random Forest Regressor, and Support Vector regression), to assess stress levels. ResultsThe models that combined time- and frequency-domain features performed best, with the lowest RMSE (4.972) and highest validation (r = 0.533). The Gaussian Process Regressor and Linear Regression outperformed the others. The greatest contribution to model performance was derived from gait features of the waist, hands, and legs. SignificanceThe severity of stress can be accurately detected by machine learning models using two-dimensional (2D) video-based gait data. The machine learning models used for assessing perceived stress were reliable. Waist, hand, and leg movements were found to be critical indicator in detecting stress.

GaitMPL: Gait Recognition With Memory-Augmented Progressive Learning.

Gait recognition aims at identifying the pedestrians at a long distance by their biometric gait patterns. It is inherently challenging due to the various covariates and the properties of silhouettes (textureless and colorless), which result in two kinds of pair-wise hard samples: the same pedestrian could have distinct silhouettes (intra-class diversity) and different pedestrians could have similar silhouettes (inter-class similarity). In this work, we propose to solve the hard sample issue with a Memory-augmented Progressive Learning network (GaitMPL), including Dynamic Reweighting Progressive Learning module (DRPL) and Global Structure-Aligned Memory bank (GSAM). Specifically, DRPL reduces the learning difficulty of hard samples by easy-to-hard progressive learning. GSAM further augments DRPL with a structure-aligned memory mechanism, which maintains and models the feature distribution of each ID. Experiments on two commonly used datasets, CASIA-B and OU-MVLP, demonstrate the effectiveness of GaitMPL. On CASIA-B, we achieve the state-of-the-art performance, i.e., 88.0% on the most challenging condition (Clothing) and 93.3% on the average condition, which outperforms the other methods by at least 3.8% and 1.4%, respectively. Code will be available at https://github.com/WhiteDOU/GaitMPL https://github.com/WhiteDOU/GaitMPL.

Advancements in artificial intelligence for biometrics: A deep dive into model-based gait recognition techniques

Over the past decade, Deep Learning (DL) pipelines have undergone significant evolution and demonstrated effectiveness in addressing complex challenges within artificial intelligence domains. The construction of tailored DL pipelines for specific applications necessitates a solid grasp of deep learning principles and the range of intermediary layers at one’s disposal. Crafting a DL pipeline involves leveraging appropriate datasets for the intended application and iteratively refining the pipeline by navigating through intermediary layers. The process of selecting and validating configurations demands substantial time and meticulous consideration, making it intricate to identify an optimal and resilient DL pipeline that excels across pertinent datasets. This article seeks to support researchers in comprehending diverse gait sensing technologies while establishing a foundational understanding of deep learning concepts to expedite problem-solving. A comprehensive overview of gait biometrics tailored for surveillance applications is presented herein. The fundamental aspects of deep learning pipelines are expounded upon, encompassing their selection criteria and implications for specific problems. Recent pivotal research on deep learning models is surveyed, encompassing their performance across varying application datasets. By elucidating the merits and limitations of these approaches, this work guides the derivation of an optimized pipeline achieved through a fusion of existing alternatives. The ultimate objective is to attain swifter yet precise outcomes for a given problem.

Learning a deep-feature clustering model for gait-based individual identification

Gait biometrics which concern with recognizing individuals by the way they walk are of a paramount importance these days. Human gait is a candidate pathway for such identification tasks since other mechanisms can be concealed. Most common methodologies rely on analyzing 2D/3D images captured by surveillance cameras. Thus, the performance of such methods depends heavily on the quality of the images and the appearance variations of individuals. In this study, we describe how gait biometrics could be used in individuals' identification using a deep feature learning and inertial measurement unit (IMU) technology. We propose a model that recognizes the biological and physical characteristics of individuals, such as gender, age, height, and weight, by examining high-level representations constructed during its learning process. The effectiveness of the proposed model has been demonstrated by a set of experiments with a new gait dataset generated using a shoe-type based on a gait analysis sensor system. The experimental results show that the proposed model can achieve better identification accuracy than existing models, while also demonstrating more stable predictive performance across different classes. This makes the proposed model a promising alternative to current image-based modeling.

Real-time gait biometrics for surveillance applications: A review

Deep learning (DL) pipelines have evolved for over a decade now and are efficient at solving many challenging problems of image and signal processing applications. Designing deep learning pipelines for a particular application requires a good understanding of deep learning and various intermediate layers available. To develop a DL pipeline, one uses available dataset(s) suitable for an application, and the pipeline is refined by iterating over intermediate layers. A large amount of time and extensive thinking goes into these selections and validating the performance of each configuration. Thus, it is hard to choose the correct and robust DL pipeline that performs well on all relevant datasets. This review aims to aid researchers in understanding different gait sensing technologies and provide foundational knowledge of the deep learning concepts for faster solutions for a given problem. Gait recognition is more recent since it hasn’t yet been used in a real-world situation. This article provides a comprehensive overview of gait biometrics suited to real-time surveillance applications. All the important parameters of deep learning pipelines are explained, along with their selection and implication for a given problem. Authors have reviewed important research articles recently on deep learning models and how these perform across different application datasets. The benefits and drawbacks of the approaches are elucidated to help arrive at the optimized pipeline derived from a fusion of available pipelines to achieve faster but accurate results for a given problem.

M-GaitFormer: Mobile biometric gait verification using Transformers

Mobile devices such as smartphones and smartwatches are part of our everyday life, acquiring large amount of personal information that needs to be properly secured. Among the different authentication techniques, behavioural biometrics has become a very popular method as it allows authentication in a non-intrusive and continuous way. This study proposes M-GaitFormer, a novel mobile biometric gait verification system based on Transformer architectures. This biometric system only considers the accelerometer and gyroscope data acquired by the mobile device. A complete analysis of the proposed M-GaitFormer is carried out using the popular available databases whuGAIT and OU-ISIR. M-GaitFormer achieves Equal Error Rate (EER) values of 3.42% and 2.90% on whuGAIT and OU-ISIR, respectively, outperforming other state-of-the-art approaches based on popular Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs).

A Self‐Powered Body Motion Sensing Network Integrated with Multiple Triboelectric Fabrics for Biometric Gait Recognition and Auxiliary Rehabilitation Training

AbstractGait analysis provides a convenient strategy for the diagnosis and rehabilitation assessment of diseases of skeletal, muscular, and neurological systems. However, challenges remain in current gait recognition methods due to the drawbacks of complex systems, high cost, affecting natural gait, and one‐size‐fits‐all model. Here, a highly integrated gait recognition system composed of a self‐powered multi‐point body motion sensing network (SMN) based on full textile structure is demonstrated. By combining of newly developed energy harvesting technology of triboelectric nanogenerator (TENG) and traditional textile manufacturing process, SMN not only ensures high pressure response sensitivity up to 1.5 V kPa−1, but also is endowed with several good properties, such as full flexibility, excellent breathability (165 mm s−1), and good moisture permeability (318 g m−2 h−1). By using machine learning to analyze periodic signals and dynamic parameters of limbs swing, the gait recognition system exhibits a high accuracy of 96.7% of five pathological gaits. In addition, a customizable auxiliary rehabilitation exercise system that monitors the extent of the patient's rehabilitation exercise is developed to observe the patient's condition and instruct timely recovery training. The machine learning‐assisted SMN can provide a feasible solution for disease diagnosis and personalized rehabilitation of the patients.

One Step of Gait Information From Sensing Walking Surface for Personal Identification

The accuracy of gait sensing detection and identification determines the usability and acceptability in field applications. Four inertial measurement units (IMUs) recorded from heel contact to toe-off as a footstep in gait. The 1400 footsteps from 70 participants were collected, and the 13 footsteps from each were randomly selected for the Siamese convolutional neural network (SCNN) model training. The inputs in the SCNN model were a matrix of 4 (sensor) <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times150$ </tex-math></inline-formula> (sample) with six channels, which were associated with three axes of acceleration and gyroscopes of one footstep. Subsequently, different numbers of enrolled people were used in the training model, and different footsteps were set as a threshold for ingroup or imposter detections. Even in the smallest number of enrolled people dataset in ingroup detection, the performance of the SCNN was significantly better than the long short-term memory (LSTM). The highest accuracy rate of ingroup detection was 96.33% in ten enrolled people, and the highest for imposter detection was 81.93% in 60 enrolled people under the 13 footsteps threshold. The best accuracy rate was in 30 enrolled people when employed ingroup and imposter detections together, significantly higher than the other enrolled numbers. The present study highlighted two contributions of an embedded IMU surface measurement system in gait information collection. First, only 13 steps of each participant were required in training, which was considered a minimal data input. Second, only one footstep achieved very promising personal identification for each person in the ingroup population and imposter detection, making our system highly applicable to gait biometrics.

Synthesizing 3D Gait Data with Personalized Walking Style and Appearance

Extracting gait biometrics from videos has been receiving rocketing attention given its applications, such as person re-identification. Although deep learning arises as a promising solution to improve the accuracy of most gait recognition algorithms, the lack of enough training data becomes a bottleneck. One of the solutions to address data deficiency is to generate synthetic data. However, gait data synthesis is particularly challenging as the inter-subject and intra-subject variations of walking style need to be carefully balanced. In this paper, we propose a complete 3D framework to synthesize unlimited, realistic, and diverse motion data. In addition to walking speed and lighting conditions, we emphasize two key factors: 3D gait motion style and character appearance. Benefiting from its 3D nature, our system can provide various gait-related data, such as accelerometer data and depth map, not limited to silhouettes. We conducted various experiments using the off-the-shelf gait recognition algorithm and draw the following conclusions: (1) the real-to-virtual gap can be closed when adding a small portion of real-world data to a synthetically trained recognizer; (2) the amount of real training data needed to train competitive gait recognition systems can be reduced significantly; (3) the rich variations in gait data are helpful for investigating algorithm performance under different conditions. The synthetic data generator, as well as all experiments, will be made publicly available.

Deep learning pipelines for recognition of gait biometrics with covariates: a comprehensive review

Deep learning pipelines for recognition of gait biometrics with covariates: a comprehensive review

A New Post-Processing Proposal for Improving Biometric Gait Recognition Using Wearable Devices.

In this work, a novel Window Score Fusion post-processing technique for biometric gait recognition is proposed and successfully tested. We show that the use of this technique allows recognition rates to be greatly improved, independently of the configuration for the previous stages of the system. For this, a strict biometric evaluation protocol has been followed, using a biometric database composed of data acquired from 38 subjects by means of a commercial smartwatch in two different sessions. A cross-session test (where training and testing data were acquired in different days) was performed. Following the state of the art, the proposal was tested with different configurations in the acquisition, pre-processing, feature extraction and classification stages, achieving improvements in all of the scenarios; improvements of 100% (0% error) were even reached in some cases. This shows the advantages of including the proposed technique, whatever the system.

Computational Intelligence Approach for Biometric Gait Identification

Gait recognition has gained significant attention in recent years due to its potential applications in various fields, including surveillance, security, and healthcare. Biometric gait identification, which involves recognizing individuals based on their walking patterns, is a challenging task due to the inherent variations in gait caused by factors such as clothing, footwear, and walking speed. In this paper, we propose a computational intelligence approach for biometric gait identification. Specifically, we integrate an intelligent convolutional model to identify human gaits based on the inertial sensory data captured from the body movement during the human walk. Extensive experiments on two datasets demonstrated that the efficiency of the proposed approach outperforms the existing methods. Our approach has the potential to be used in real-world applications such as surveillance systems and healthcare monitoring, where accurate and efficient identification of individuals based on their gait is crucial.

Face and gait biometrics authentication system based on simplified deep neural networks

Face and gait biometrics authentication system based on simplified deep neural networks

Unsupervised Domain Adaptation for Disguised-Gait-Based Person Identification on Micro-Doppler Signatures

In recent years, gait-based person identification has gained significant interest for a variety of applications, including security systems and public security forensics. Meanwhile, this task is faced with the challenge of disguised gaits. When a human subject changes what he or she is wearing or carrying, it becomes challenging to reliably identify the subject’s identity using gait data. In this paper, we propose an unsupervised domain adaptation (UDA) model, named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Guided Subspace Alignment under the Class-aware</i> condition (G-SAC), to recognize human subjects based on their disguised gait data by fully exploiting the intrinsic information in gait biometrics. To accomplish this, we employ neighbourhood component analysis (NCA) to create an intrinsic feature subspace from which we can obtain similarities between normal and disguised gaits. With the aid of a proposed constraint for adaptive class-aware alignment, the class-level discriminative feature representation can be learned guided by this subspace. Our experimental results on a measured micro-Doppler radar dataset demonstrate the effectiveness of our approach. The comparison results with several state-of-the-art methods indicate that our work provides a promising domain adaptation solution for the concerned problem, even in cases where the disguised pattern differs significantly from the normal gaits. Additionally, we extend our approach to more complex multi-target domain adaptation (MTDA) challenge and video-based gait recognition tasks, the superior results demonstrate that the proposed model has a great deal of potential for tackling increasingly difficult problems.

GaitPrivacyON: Privacy-preserving mobile gait biometrics using unsupervised learning

• Mobile behavioural biometrics allow the user authentication in a passive way. • The data acquired can contain a large amount of personal and sensitive information. • We present GaitPrivacyON, a privacy-preserving mobile gait verification approach. • GaitPrivacyON automatically removes the sensitive data using unsupervised learning. Numerous studies in the literature have already shown the potential of biometrics on mobile devices for authentication purposes. However, it has been shown that, the learning processes associated to biometric systems might expose sensitive personal information about the subjects. This study proposes GaitPrivacyON, a novel mobile gait biometrics verification approach that provides accurate authentication results while preserving the sensitive information of the subject. It comprises two modules: i) two convolutional Autoencoders with shared weights that transform attributes of the biometric raw data, such as the gender or the activity being performed, into a new privacy-preserving representation; and ii) a mobile gait verification system based on the combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) with a Siamese architecture. The main advantage of GaitPrivacyON is that the first module (convolutional Autoencoders) is trained in an unsupervised way, without specifying the sensitive attributes of the subject to protect. Two experimental studies have been examinated: i) MotionSense and MobiAct databases; and ii) OU-ISIR database. The experimental results achieved suggest the potential of GaitPrivacyON to significantly improve the privacy of the subject while keeping user authentication results higher than 96.6% Area Under the Curve (AUC). To the best of our knowledge, this is the first mobile gait verification approach that considers privacy-preserving methods trained in an unsupervised way.

Dual-Biometric Human Identification Using Radar Deep Transfer Learning.

Accurate human identification using radar has a variety of potential applications, such as surveillance, access control and security checkpoints. Nevertheless, radar-based human identification has been limited to a few motion-based biometrics that are solely reliant on micro-Doppler signatures. This paper proposes for the first time the use of combined radar-based heart sound and gait signals as biometrics for human identification. The proposed methodology starts by converting the extracted biometric signatures collected from 18 subjects to images, and then an image augmentation technique is applied and the deep transfer learning is used to classify each subject. A validation accuracy of 58.7% and 96% is reported for the heart sound and gait biometrics, respectively. Next, the identification results of the two biometrics are combined using the joint probability mass function (PMF) method to report a 98% identification accuracy. To the best of our knowledge, this is the highest reported in the literature to date. Lastly, the trained networks are tested in an actual scenario while being used in an office access control platform to identify different human subjects. We report an accuracy of 76.25%.