Human Gait Identification Research Articles

Design and Development of Polymer-Based Optical Fiber Sensor for GAIT Analysis

In the present scenario like COVID-19 pandemic, to maintain physical distance, the gait-based biometric is a must. Human gait identification is a very difficult process, but it is a suitable distance biometric that also gives good results at low resolution conditions even with face features that are not clear. This study describes the construction of a smart carpet that measures ground response force (GRF) and spatio-temporal gait parameters (STGP) using a polymer optical fiber sensor (POFS). The suggested carpet contains two light detection units for acquiring signals. Each unit obtains response from 10 nearby sensors. There are 20 intensity deviation sensors on a fiber. Light-emitting diodes (LED) are triggered successively, using the multiplexing approach that is being employed. Multiplexing is dependent on coupling among the LED and POFS sections. Results of walking experiments performed on the smart carpet suggested that certain parameters, including step length, stride length, cadence, and stance time, might be used to estimate the GRF and STGP. The results enable the detection of gait, including the swing phase, stance, stance length, and double supporting periods. The suggested carpet is dependable, reasonably priced equipment for gait acquisition in a variety of applications. Using the sensor data, gait recognition is performed using genetic algorithm (GA) and particle swarm optimization (PSO) technique. GA- and PSO-based gait template analyses are performed to extract the features with respect to the gait signals obtained from polymer optical gait sensors (POGS). The techniques used for classification of the obtained signals are random forest (RF) and support vector machine (SVM). The accuracy, sensitivity, and specificity results are obtained using SVM classifier and RF classifier. The results obtained using both classifiers are compared.

Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models

Person identification is a problem that has received substantial attention, particularly in security domains. Gait recognition is one of the most convenient approaches enabling person identification at a distance without the need for high-quality images. There are several review studies addressing person identification such as the utilization of facial images, silhouette images, and wearable sensor. Despite skeleton-based person identification gaining popularity while overcoming the challenges of traditional approaches, existing survey studies lack the comprehensive review of skeleton-based approaches to gait identification. We present a detailed review of the human pose estimation and gait analysis that makes the skeleton-based approaches possible. The study covers various types of related datasets, tools, methodologies, and evaluation metrics with associated challenges, limitations, and application domains. Detailed comparisons are presented for each of these aspects with recommendations for potential research and alternatives. A common trend throughout this paper is the positive impact that deep learning techniques are beginning to have on topics such as human pose estimation and gait identification. The survey outcomes might be useful for the related research community and other stakeholders in terms of performance analysis of existing methodologies, potential research gaps, application domains, and possible contributions in the future.

Gait-based Biometric Identification System using Triangulated Skeletal Models (TSM)

Human gait identification is a behavioral biometric technology which can be used to monitor human beings without user interaction. Recent researches are more focused on investigating gait as one of the biometric traits. Further, gait recognition aims to analyze and identify human behavioral activities and may be implemented in different scenarios including access control and criminal analysis. However, using various techniques in relation to image processing and obtaining better accuracy are remaining challenges. In last decade, Microsoft has introduced the Kinect sensor as an innovative sensor to provide image characteristics, precisely. Therefore, this article uses a Kinect sensor to extract gait characteristics to be used in individual recognition. A set of Triangulated shape are generated as new feature vector and called Triangulated Skeletal Model (TSM). Nearest Neighbor technique is utilized to do the recognition issue based on leave-one-out strategy. The experimental outcomes indicated that the recommended technique provides significant results and outperforms other comparative similar techniques with accuracy of 93.46%.

Attention-based deep learning networks for identification of human gait using radar micro-Doppler spectrograms

AbstractIdentification of human individuals within a group of 39 persons using micro-Doppler (μ-D) features has been investigated. Deep convolutional neural networks with two different training procedures have been used to perform classification. Visualization of the inner network layers revealed the sections of the input image most relevant when determining the class label of the target. A convolutional block attention module is added to provide a weighted feature vector in the channel and feature dimension, highlighting the relevant μ-D feature-filled areas in the image and improving classification performance.

TransferSense: towards environment independent and one-shot wifi sensing

WiFi has recently established itself as a powerful medium for radio frequency (RF) sensing due to its low cost and convenience. Many tasks, such as gesture recognition, activity recognition, and fall detection, can be implemented by measuring and calculating how the propagation of WiFi signals is affected by human activities. However, current WiFi-based sensing solutions have limited scales as they are designed for only a few activities and need to collect data and create training models in the same domain because the model established in a deployment environment is usually not applicable to new objects in the target domain. This paper presents TransferSense, an environment independent and one-shot WiFi sensing method based on deep learning. Firstly, amplitude and phase information of channel state information (CSI) are combined to increase the number of features to solve the problem of insufficient features due to single-source information. Secondly, TransferSense converts RF sensing tasks to image classification tasks and fuses low-level and high-level semantic features extracted from a pre-trained convolutional neural network to achieve an end-to-end high-precision sensing for activity recognition. Finally, TransferSense applies a transfer learning method with a small number of labeled samples in the target domain to perform high-precision cross-domain sensing, which can reduce the data collection cost in the target domain. We verified the effectiveness of TransferSense using two representative WiFi sensing applications, gait identification and sign recognition. In a single deployment environment, TransferSense achieved more than 97% human gait identification accuracy for 44 users and more than 81% sign language recognition for 100 isolated sign language words. In the case of new object recognition in the cross-domain sensing, TransferSense achieved more than 77% human gait identification accuracy for 10 new users, more than 88% sign language recognition for 10 new isolated sign language words, and more than 81% gesture identification for 2 new gestures.

Retraction: Analysis and identification of body features in Alzheimer’s patients for gait recognition and gait attractiveness (IOP Conf. Ser.: Mater. Sci. Eng. 1022 012009)

This article has been retracted by IOP Publishing following an allegation that this article may contain tortured phrases [1]. IOP Publishing has investigated in line with the COPE guidelines and have found tortured phrases to be masking overlap of other work [2-3] and agrees this work should be retracted. IOP Publishing wishes to credit PubPeer commenters [4] and the Problematic Paper Screener for bringing this issue to our attention. The authors have neither confirmed whether they agree or disagree to this retraction. 1. Cabanac G, Labbe C, Magazinov A, 2021, Tortured phrases: A dubious writing style emerging in science. Evidence of critical issues affecting established journals, arXiv:2107.06751vv1 2. Jie Hong, 2012, Human Gait Identification Thesis, Brunel University 3. Hong J, Kang J & Price ME, 2014, Extraction of bodily features for gait recognition and gait attractiveness evaluation. Multimed Tools Appl 71, 1999–2013 4. https://pubpeer.com/publications/C555DA27762FFD3284E9345F56FBCC Retraction published: 18 January 2023

Event-Stream Representation for Human Gaits Identification Using Deep Neural Networks.

Dynamic vision sensors (event cameras) have recently been introduced to solve a number of different vision tasks such as object recognition, activities recognition, tracking, etc. Compared with the traditional RGB sensors, the event cameras have many unique advantages such as ultra low resources consumption, high temporal resolution and much larger dynamic range. However, these cameras only produce noisy and asynchronous events of intensity changes, i.e., event-streams rather than frames, where conventional computer vision algorithms can't be directly applied. In our opinion the key challenge for improving the performance of event cameras in vision tasks is finding the appropriate representations of the event-streams so that cutting-edge learning approaches can be applied to fully uncover the spatio-temporal information contained in the event-streams. In this paper, we focus on the event-based human gait identification task and investigate the possible representations of the event-streams when deep neural networks are applied as the classifier. We propose new event-based gait recognition approaches basing on two different representations of the event-stream, i.e., graph and image-like representations, and use graph-based convolutional network (GCN) and convolutional neural networks (CNN) respectively to recognize gait from the event-streams. The two approaches are termed as EV-Gait-3DGraph and EV-Gait-IMG. To evaluate the performance of the proposed approaches, we collect two event-based gait datasets, one from real-world experiments and the other by converting the publicly available RGB gait recognition benchmark CASIA-B. Extensive experiments show that EV-Gait-3DGraph achieves significantly higher recognition accuracy than other competing methods when sufficient training samples are available. However, EV-Gait-IMG converges more quickly than graph-based approaches while training and shows good accuracy with only few number of training samples (less than ten). So image-like presentation is preferable when the amount of training data is limited.

Human gait identification using two dimensional multi-resolution analysis

Application of wearable devices like as inertial sensors has grown rapidly in various daily living applications such as, in wearable gait analysis due to several factors, such as being easy-to-use and low-cost. Many methods have been suggested to extract various heuristic and high-level features of motion sensor data to identify discriminative gait signatures to distinguish the target individual from others. In this study, we propose an identification method for human gait identification using spectro-temporal two dimensional (2D) expansion of human gait cycles, and then implement a 2D multi-resolution analysis to decompose the expanded 2D space to different levels of resolution. We propose a systematic methodology for processing motion signals for the purpose of human gait identification by first extracting the Gait cycles. Then, we perform 2D spectro-temporal representation of each cycle. After that, we conduct multi-resolution decomposition and analysis of the 2D spectrograms to extract useful information for the predictive task. We collect raw motion data from five inertial sensors placed on the chest, lower back, right hand wrist, right knee and right ankle. After pre-processing the raw recordings, we propose an effective heuristic segmentation method to extract the gait cycles from the processed data. Spectro-temporal features are extracted by merging key instantaneous spectral descriptors in a gait cycle that characterize the non-stationarities in each gait cycle inertial data in two dimensions. The 2D spectro-temporal expansion of the gait cycles extracted from inertial sensor data from a population of 10 subjects are decomposed to several levels of resolutions. Based on the extracted features from each level of decomposed space, the identification task is accomplished. Based on our experimental results, 93.36% subject identification accuracy was achieved.

Functional inference on rotational curves under sample‐specific group actions and identification of human gait

AbstractInspired by the problem of gait reproducibility (reidentifying individuals across doctor's visits) we develop two‐sample permutation tests under a sample‐specific group action on Lie groups with a bi‐invariant Riemannian metric. These tests rely on consistent estimators and pairwise curve alignment. To this end, we propose Gaussian perturbation models and for the special case of curves on the group of 3D rotations we provide asymptotic consistency and, employing a quaternion point of view, fast spatial alignment of pointwise extrinsic mean curves. In our application to rotations of the tibia versus the femur at the knee joint under the spatial action of marker placement and the temporal action of different walking speeds, obtained from an experiment, we solve the problem of gait reproducibility.

Quaternion statistics applied to the classification of motion capture data

Unit quaternions give quite new possibilities in an analysis of motion capture data. They provide a compact, holistic axis-angle representation of 3D rotations. An application of descriptive statistics – measures of location and dispersion – is common in numerous problems related to an assessment of joint movements. For those reasons, the paper proposes new approaches to the extraction of motion descriptors on the basis of descriptive statistics of 3D rotations represented by unit quaternions as well as the appropriate classification schemes operating on motion descriptors. Mean and median values and standard deviations are calculated for time series with raw rotational data as well as angular velocities and accelerations. The problem of human gait identification is addressed in the numerical validation of the introduced methods and highly precise marker-based motion capture data are utilized. The results obtained – the accuracy of gait recognition – are compared to the ones achieved by descriptive statistics calculated for time series of Euler angles. The general conclusion is that unit quaternions are effective in the calculation of descriptive statistics. They preserve robust discriminative features of joint movements and they can be applied in numerous challenges of expert and intelligent systems.

Human Identification System Based on Spatial and Temporal Features in the Video Surveillance System

Human identification is the most significant topic in the bioinformatics field. Various human gait identification methods are available to identify humans, but detecting the objects based on the human gait is still a challenging task in the video surveillance system. Thus, an effective hybrid Bayesian approach is proposed for identifying the humans. The proposed hybrid Bayesian approach involves two stages as follows: the first stage is the human identification based on the object features, and the second stage is the human identification based on the spatial features. Initially, the videos are fed into the first stage, where the object detection is performed using the Viola Jones algorithm. Once the objects are detected, the feature extraction process is carried out by using a hierarchical skeleton to effectively extract the selective features. The object skeleton provides an effective and intuitive abstraction, which offers object recognition and object matching. The Bayesian network is adapted in the object-based features to identify humans. In the spatial-based human identification stage, only the spatial features are extracted and are passed into the gait-based Bayesian network to identify the humans. Finally, the resulted output is obtained using the fuzzy holoentropy for identifying the humans. The experimentation of the proposed hybrid Bayesian approach is performed using the dataset named UCF-Crime, and the performance is evaluated by considering the average value of the metrics, namely F1-score, precision, and recall which acquired 0.8820, 0.8770, and 0.9203, respectively.

Non-Contact Human Gait Identification Through IR-UWB Edge-Based Monitoring Sensor

Non-contact sensors are negating the use of wearables or cameras and providing a rewarding and accepting environment to assist in biomedical applications, such as physiological examinations, physiotherapy, home assistance, rehabilitation success determination, compliance, and health diagnostics. In this paper, physiological parameter identification of human gait has been demonstrated through an edge-based sensor and a heuristic approach. Impulse radio ultra-wide band (IR-UWB) pulsed Doppler radar has been employed with a focus on understanding human walking patterns. This paper extracts an individual’s gait trait from the associated biomechanical activity and differentiates lower limb movement patterns from other body areas via a radar transceiver. It is observed that Doppler shifts alone are not reliable to detect human gait because of frequency shifts taking place across the entire body (including breathing, heartbeat, and arm movements) where movement occurs. Thus, a heuristic spherical trigonometrical approach has been proposed to augment radar principles and short-term Fourier transformation (STFT) to identify the gait trait. The experiment presented includes data gathering from a number of male and female participants in both ideal and real environments. Subsequently, the proposed gait identification and parameter characterization has been analyzed, tested, and validated against popularly accepted smartphone applications where the variations are less than 5%.

Gait analysis for early Parkinson’s disease detection based on deep learning

Abstract Better handling of neurological or neurodegenerative disorders such as Parkinson’s Disease (PD) is only possible with an early identification of relevant symptoms. Although the entire disease can’t be treated but the effects of the disease can be delayed with proper care and treatment. Due to this fact, early identification of symptoms for the PD plays a key role. Recent studies state that gait abnormalities are clearly evident while performing dual cognitive tasks by people suffering with PD. Researches also proved that the early identification of the abnormal gaits leads to the identification of PD in advance. Novel technologies provide many options for the identification and analysis of human gait. These technologies can be broadly classified as wearable and non-wearable technologies. As PD is more prominent in elderly people, wearable sensors may hinder the natural persons movement and is considered out of scope of this paper. Non-wearable technologies especially Image Processing (IP) approaches captures data of the person’s gait through optic sensors Existing IP approaches which perform gait analysis is restricted with the parameters such as angle of view, background and occlusions due to objects or due to own body movements. Till date there exists no researcher in terms of analyzing gait through 3D pose estimation. As deep leaning has proven efficient in 2D pose estimation, we propose an 3D pose estimation along with proper dataset. This paper outlines the advantages and disadvantages of the state-of-the-art methods in application of gait analysis for early PD identification. Furthermore, the importance of extracting the gait parameters from 3D pose estimation using deep learning is outlined.

IMU-Based Gait Recognition Using Convolutional Neural Networks and Multi-Sensor Fusion.

The wide spread usage of wearable sensors such as in smart watches has provided continuous access to valuable user generated data such as human motion that could be used to identify an individual based on his/her motion patterns such as, gait. Several methods have been suggested to extract various heuristic and high-level features from gait motion data to identify discriminative gait signatures and distinguish the target individual from others. However, the manual and hand crafted feature extraction is error prone and subjective. Furthermore, the motion data collected from inertial sensors have complex structure and the detachment between manual feature extraction module and the predictive learning models might limit the generalization capabilities. In this paper, we propose a novel approach for human gait identification using time-frequency (TF) expansion of human gait cycles in order to capture joint 2 dimensional (2D) spectral and temporal patterns of gait cycles. Then, we design a deep convolutional neural network (DCNN) learning to extract discriminative features from the 2D expanded gait cycles and jointly optimize the identification model and the spectro-temporal features in a discriminative fashion. We collect raw motion data from five inertial sensors placed at the chest, lower-back, right hand wrist, right knee, and right ankle of each human subject synchronously in order to investigate the impact of sensor location on the gait identification performance. We then present two methods for early (input level) and late (decision score level) multi-sensor fusion to improve the gait identification generalization performance. We specifically propose the minimum error score fusion (MESF) method that discriminatively learns the linear fusion weights of individual DCNN scores at the decision level by minimizing the error rate on the training data in an iterative manner. 10 subjects participated in this study and hence, the problem is a 10-class identification task. Based on our experimental results, 91% subject identification accuracy was achieved using the best individual IMU and 2DTF-DCNN. We then investigated our proposed early and late sensor fusion approaches, which improved the gait identification accuracy of the system to 93.36% and 97.06%, respectively.

Gait-based Human identification using acoustic sensor and deep neural network

This paper proposes a simple, fast and low-cost gait-based human identification system jointly employing an acoustic sensor system and a deep neural network (DNN) based algorithm to process acoustic data for human identification. The acoustic sensor system is employed to detect and acquire individuals’ gait signatures. Compared with the conventional radar based and video/image based human gait identification technologies, our acoustic sensor system is low-cost and feasible in some special cases, such as in private rooms/hotels or in the night time. We perform identification using a DNN which consists of an auto-encoder and a feed-forward neural network. The experimental results demonstrate that the integrated system of acoustic sensor and DNN considerably improves the system’s performance, which achieves an excellent accuracy rate of 97% for human identification. Aside from the high accuracy of the gait-based human identification, the novel system we developed is also capable of identifying human actions (walk, jog, run, jump, etc.) and the human number which has not been addressed in the literature, thereby significantly enhancing the wide adaptability of our identification system in various applications. Additionally, to better enhance the performance of the proposed human identification method, a large feature set, variable-length frame size and variable-dimension feature vectors are exploited in our identification system. The presented work provides prospects in developing high-performance identification system for large-scale security applications via a simple and efficient technique.

Human Gait identification System

Few biometrics can be used to recognize a person from distance without need for direct sharing or cooperation of that person, gait (walking behavior) is one of them. Walking behavior (gait) recognition includes specifying person identity by analyzing his walking style (walking manner). In this paper, a human gait identification system depending on extracted features, which are vertical hip, horizontal hip angle and slop of thigh. The first step of the proposed system is detecting the binary silhouette of a walking individual from the uploaded videos. Then, the gait cycle is allocated using aspect ratio method. Finally, the required features from each frame in gait cycle are extracted. Different image processing operation have been performed to extract the required features. The outcome of the proposal system reflects flexibility in term of inserting, searching, updating, deleting and matching. The proposed system is tested in terms of offered functions, human recognition and noise effects. The obtained results show the efficient performance of the system and high ability of covering the error caused by surrounding conditions. The system is evaluated using the matching rate with the threshold of 70%. The adding noise can degrade the matching rate, particularly for high variance values. This is because of the increasing of noise values that might be the reason of moving the object irregularly while capturing or unexpected changing in the effected surrounding conditions.

Open source hardware based sensor platform suitable for human gait identification

Most initiatives about embedded sensing capabilities in computational systems lead to devise an ad hoc sensor platform, usually poorly reusable, as a first stage to prepare a data corpus or production prototype. In this paper, an open source hardware platform for sensing is described. This platform was intended to be used in data acquisition for gait identification, and is designed in a way general enough so many other projects could reuse the design to accelerate prototyping. The platform is based on popular open source hardware and software like Arduino and Raspberry Pi using well known languages and libraries. Some experimental results about the throughput of the overall system are reported showing the feasibility of acquiring data from up to 6 sensors with a sampling frequency no less than 118 Hz.

Human Identification by Gait Using Time Delay Neural Networks

<p>This paper proposed human identification method by gait. Human gait is a type of biometric features and related to the physiological and behavioral features of a human. In this paper, a feature vector of gait motion parameters is extracted from each frame using image segmentation methods, and categorized into different categories. Two of these categories were used to form the gait motion trajectories; Category one: Gait angle velocity: angle velocity hip, angle velocity knee, angle velocity thigh and angle velocity shank. Category two: Gait angle acceleration: angle acceleration hip, angle acceleration knee, angle acceleration thigh and angle acceleration shank for each image sequence. Finally, the TDNN method with different training algorithms is used for recognition purpose. This experiment is done on our own database. This research developed a method which achieves a higher recognition rate in the training set 100% and in the testing set 83%. Also, category one establishes gait motion features to be used in human gait identification applications using different training algorithms, While category two achieved a higher recognition rate by trainrb algorithm.</p>

Identification of Human Gait from Point-Lights Display of Walker

Identification of Human Gait from Point-Lights Display of Walker

Human gait identification from extremely low‐quality videos: an enhanced classifier ensemble method

Nowadays, surveillance cameras are widely installed in public places for security and law enforcement, but the video quality may be low because of the limited transmission bandwidth and storage capacity. In this study, the authors proposed a gait recognition method for extremely low-quality videos, which have a frame-rate at one frame per second (1 fps) and resolution of 32 × 22 pixels. Different from popular temporal reconstruction-based methods, the proposed method uses the average gait image (AGI) over the whole sequence as the appearance-based feature description. Based on the AGI description, the authors employed a large number of weak classifiers to reduce the generalisation errors. The performance can be further improved by incorporating the model-based information into the classifier ensemble. The authors found that the performance improvement is directly proportional to the average disagreement level of weak classifiers (i.e. diversity), which can be increased by using the model-based information. The authors evaluated the proposed method on both indoor and outdoor databases (i.e. the low-quality versions of OU-ISIR-D and USF databases), and the results suggest that our method is more general and effective than other state-of-the-art algorithms.