Gait Recognition Algorithm Research Articles

A Stable Gait Recognition Algorithm Under Multiview and Multiwear Using Millimeter-Wave Radar

A Stable Gait Recognition Algorithm Under Multiview and Multiwear Using Millimeter-Wave Radar

Enhancing gait recognition by multimodal fusion of mobilenetv1 and xception features via PCA for OaA-SVM classification

Gait recognition has become an increasingly promising area of research in the search for noninvasive and effective methods of person identification. Its potential applications in security systems and medical diagnosis make it an exciting field with wide-ranging implications. However, precisely recognizing and assessing gait patterns is difficult, particularly in changing situations or from multiple perspectives. In this study, we utilized the widely used CASIA-B dataset to observe the performance of our proposed gait recognition model, with the aim of addressing some of the existing limitations in this field. Fifty individuals are randomly selected from the dataset, and the resulting data are split evenly for training and testing purposes. We begin by excerpting features from gait photos using two well-known deep learning networks, MobileNetV1 and Xception. We then combined these features and reduced their dimensionality via principal component analysis (PCA) to improve the model's performance. We subsequently assessed the model using two distinct classifiers: a random forest and a one against all support vector machine (OaA-SVM). The findings indicate that the OaA-SVM classifier manifests superior performance compared to the others, with a mean accuracy of 98.77% over eleven different viewing angles. This study is conducive to the development of effective gait recognition algorithms that can be applied to heighten people’s security and promote their well-being.

Human Gait phases recognition based on multi-source data fusion and BILSTM attention neural network

A human gait recognition algorithm with deep learning based on multi-source data fusion is proposed to assist exoskeleton realizing complex human-exoskeleton cooperative motion. A lightweight gait acquisition device simultaneously acquires three different types of sensor signals, i.e., thigh surface electromyography (sEMG), ground reaction force (GRF) of human feet and two joints motion information. The sample data is obtained by many multi-scene gait experiments involving stand still, walk up/down stairs, and walk up/down slope, etc. The proposed algorithm recognizes multiple gait phases (27 classes) in different motion patterns by using short-time gait data, which has two typical advantages: (1) Based on multi-source sensor distributed in human body, this wearable device is constructed for ease of use to address several Subjects (different weights and heights) with low cost and light weight. (2) The critical features of gait data are identified by Bi-directional Long Short-Term Memory (BILSTM) attention neural network with higher recognition accuracy than other state-of-art recognition methods, especially in arbitrary gait switching durations.

Application of gaming robot based on gait recognition algorithm in sports training and assistance system

At present, game sports robots have become a new type of sports assistance technology, which can achieve more natural and smooth motion trajectory analysis under continuous training, and provide a gamified user experience for sports training. This article analyzes the application of game motion robots based on gait recognition algorithms in sports training and motion assistance systems, which can more accurately obtain information data of the athlete during the movement process and has good results in preventing sports injuries. We combine gait recognition algorithms with video feature aggregation to integrate high-level and low-level network features, achieving effective extraction of multi-level image features. Finally, complete action recognition, review, and analysis. Through experimental comparison, it can be seen that the feature aggregation modules designed in this article at different levels are very effective, and combined with gait recognition algorithms, they can effectively improve the accuracy of motion recognition and have excellent robustness. The motion assistance system designed in this article can automatically determine the movements during exercise, allowing athletes to self-evaluate their movements and correct incorrect movements without the need for professional guidance, achieving healthy and effective exercise results.

Optimization of Body Pressure Relief Support Wearable Devices Integrating 3D Printing and Gait Recognition Algorithms

Optimization of Body Pressure Relief Support Wearable Devices Integrating 3D Printing and Gait Recognition Algorithms

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.

Gait recognition algorithm in dense occlusion scene

æ­¥æ€è¯†åˆ«ç®—æ³•ä¸»è¦ä¾èµ–è¡Œäººç›®æ ‡çš„æ—¶åºè½®å»“è¿›è¡Œç‰¹å¾æå–å’Œåˆ¤åˆ«ã€‚åœ¨å®žé™ åº”ç”¨ä¸­è¡Œäººå ·æœ‰ç»“ä¼´è¡Œèµ°çš„ç‰¹ç‚¹ï¼Œè½®å»“æå–æ˜“å—åˆ°å ¶ä»–è¡Œäººçš„é®æŒ¡å’Œå¹²æ‰°ï¼Œå¤§å¹ é™ä½Žäº†æ­¥æ€è¯†åˆ«ç®—æ³•çš„ç²¾åº¦ã€‚ä¸ºæé«˜äººå‘˜å¯†é›†é®æŒ¡ä¸¥é‡çš„åœºæ™¯ä¸‹æ­¥æ€è¯†åˆ«ç®—æ³•çš„é²æ£’æ€§ï¼Œæå‡ºä¸€ç§åŸºäºŽæ— åºåºåˆ—çš„æ·±åº¦æ­¥æ€è¯†åˆ«ç®—æ³•ã€‚é¦–å ˆåœ¨Casia-Bæ•°æ®é›†çš„åŸºç¡€ä¸Šè¿›è¡Œä»¿çœŸï¼Œå»ºç«‹é®æŒ¡æƒ å†µä¸‹çš„ç›®æ ‡è½®å»“ä»¿çœŸæ•°æ®é›†ï¼Œç”¨äºŽå¯¹ç®—æ³•è¿›è¡Œé®æŒ¡é²æ£’æ€§éªŒè¯ï¼›å ¶æ¬¡ï¼Œæå‡ºåŸºäºŽéšæœºäºŒå€¼è†¨èƒ€çš„æ•°æ®å¢žå¹¿æ–¹æ³•ï¼ŒåŒæ—¶é€šè¿‡ç†è®ºå’Œå®žéªŒè®ºè¯äº†HPP（Horizontal Pyramid Pooling）结构在步态识别问题中的局限性，提出退化水平金字塔结构DHPP，利用DHPP结构、CoordConvæ–¹æ³•å’Œè”åˆè®­ç»ƒè£å‰ªæ–¹æ³•çš„é åˆï¼Œåœ¨æ·±åº¦ç‰¹å¾ä¸­å¢žå¼ºç»å¯¹ä½ç½®ä¿¡æ¯çš„æ„ŸçŸ¥èƒ½åŠ›ï¼Œæå‡ç®—æ³•é®æŒ¡é²æ£’æ€§çš„åŒæ—¶å‡å°‘ç›®æ ‡ç‰¹å¾è¡¨è¾¾ç»´åº¦ã€‚å®žéªŒç»“æžœè¡¨æ˜Žï¼Œæ‰€ææ–¹æ³•å¯¹äºŽæ­¥æ€è¯†åˆ«çš„é²æ£’æ€§æå‡æ•ˆæžœæ˜Žæ˜¾ã€‚

Evaluation Algorithm of Fencing Athletes’ Strength Distribution Characteristics Based on Gait Tracking

Human motion capturing techniques are used in various fields such as surveillance, healthcare, and sports to analyze, understand, and synthesize kinematic and kinetic data. Among the mentioned application areas of motion recognition techniques, sport is an essential sector in which it is extensively used. The dynamic and kinematic performance of the three joints of the lower limbs in lunge movement is the main factor affecting the lunge speed of the fencers. Fencing is an open-skill combat sport in which complicated body movements and effective game techniques are required. The extremely nonlinear human movements, muscle dynamics, and foot-ground contact make athletic gait analysis a difficult topic in biomechanics. At present, there are no comprehensive and systematic research results on the impact of the dynamic and kinematic performance of the ankle, knee, and hip joints of lower limbs on the lunge speed. Based on the gait tracking algorithm, this study compares and analyzes the dynamic and kinematic performance of lower limbs ankle, knee, and hip joints in the lunge of fencing athletes at different levels and discusses the influence of the dynamic and kinematic performance of the three lower limbs joints of fencing athletes on the lunge speed. This study mainly focuses on, (1) exploring the dynamic and kinematic influencing factors of the peak horizontal speed of the center of gravity of fencing athletes’ lunge movement, (2) to verify whether there is a difference in the lunge speed of fencing athletes at different levels and analyzes the reasons for the differences, (3) to explore the ankle, knee, and the differences of hip joint dynamics and kinematics, the causes of the differences, and to analyze the influence of the differences on the lunge speed. In this paper, we have used a gait tracking algorithm that evaluates the fencing athletes’ strength distribution characteristics. With the help of gait recognition algorithm based on artificial intelligence (AI) technology, the movement posture and gait of fencers can be recognized automatically in real time which is helpful to realize the automatic evaluation of power distribution. The experimental results prove the significance of the proposed model.

Autoencoder-guided GAN for minority-class cloth-changing gait data generation

In the gait recognition task, cloth-changing data (e.g., CL-class data in the CASIA-B dataset) account for a very low proportion of the gait dataset, which brings serious recognition accuracy degradation to gait recognition algorithm in clothes changing scenarios. One way to solve this problem is to use data generation algorithms to expand the cloth-changing data. When facing the generation of minority-class data, the existing GAN-based image data expansion algorithms require a large amount of data to ensure the convergence, while mode collapse can occur due to the conflict between the true-false discriminant loss and the classification loss. In order to solve the above problems, we propose an autoencoder-guided GAN for cloth-changing gait data generation, which uses the autoencoder with embedding layer to extract the data features of the entire data set, rather than only extracting the features of the required CL data. Then the labeled latent vector (representing the extracted data features) in the autoencoder is taken as the input of the GAN, solving the problem that GAN convergence requires a lot of training data. The GAN has the same topology as the autoencoder and uses the parameter matrix of the autoencoder as the initial weights. Secondly, the true classification in GAN is canceled, and only the false classification is retained, which solves the problem of the collision of the loss function between the true-false discrimination and the classification discrimination. In the cloth-changing data generation experiments, compared with other GAN data expansion algorithms, our method generates clothes changing data with high quality, and ensures the diversity of the generated data. When using the CASIA-B dataset expanded by our algorithm, several gait recognition algorithms all show significant improvement, especially in the clothes changing scenario.

TRAINING METHOD OF SPORTS ATHLETES USING THE NONLINEAR SYSTEM OF MOVING HUMAN BODY COMPETITIVE ABILITY

The purpose is to optimize the training methods of athletes and improve their competitive ability. First, the corresponding research model is established by analyzing the influencing factors of the athlete training system and combining with the dynamic nonlinear theory. Next, based on the deterministic learning theory, the dynamic nonlinear state identification model of athletes is established to obtain the state information of athletes in the process of competitive sports training and competition. Then, based on the established nonlinear state model, the nonlinear staged athlete training mode is designed. The experimental results show that the designed gait recognition algorithm based on deterministic learning can effectively collect the nonlinear signals generated by the movement process; the accuracy of gait recognition is about 90%, and it is less affected by the training and test datasets. The nonlinear staged training mode can effectively improve the overall index of maximum strength and strength endurance of tennis players, and effectively improve the training effect of players. This exploration provides a reference for the study of nonlinear competitive ability training mode of sports athletes.

Digital Twins by Physical Education Teaching Practice in Visual Sensing Training System

The paper expects to improve the efficiency and intelligence of somatosensory recognition technology in the application of physical education teaching practice. Firstly, the combination of induction recognition technology and the Internet is used. Secondly, through the Kinect sensor, bone data are acquired. Finally, the hidden Markov model (HMM) is used to simulate the experimental data. On the simulation results, a gait recognition algorithm is proposed. The gait recognition algorithm is used to identify the motion behaviour, and the results are displayed in the Web (World Wide Web) end built by the cloud server. Meantime, in view of the existing problems in the practice of physical education, combined with the establishment and operation of the Digital Twins (DTs) system, the camera source recognition architecture is carried out since the twin network and the two network branches share weights. This paper analyses these problems since the application of somatosensory recognition technology and puts forward the improvement methods. For the single problem of equipment in physical education, this paper puts forward the monitoring and identification function of the cloud server. It is to transmit data through Hypertext Transfer Protocol (HTTP) and locate and collect data through a monitoring terminal. For the lack of comprehensiveness and balance of sports plans, this paper proposes a scientific training plan and process customization based on Body Mass Index (BMI), analyses real-time data in the cloud, and makes scientific customization plans according to different students’ physical conditions. Moreover, 25 participants are invited to carry out the exercise detection and analysis experiment, and the joint monitoring of their daily movements is tested. This process has completed the design of a feasible and accurate platform for information collection and processing, which is convenient for managers and educators to comprehensively and scientifically master and manage the physical level and training of college students. The proposed method improves the recognition rate of the camera source to some extent and has important exploration significance in the field of action recognition.

Dual branch feature fusion network based gait recognition algorithm

Dual branch feature fusion network based gait recognition algorithm

Three-dimensional gait estimation and prediction using particle filters

This paper introduces a newly proposed gait recognition algorithm and demonstrates its feasibility. The purpose of this study is to solve the problems existing in existing recognition methods and to analyze the motion of a pedestrian in a non-contact and relatively simple way. As a result, the proposed model was formed by modeling the user's torso and both legs and estimating their respective center points. A distance sensor was used as the measurement device, and some of the problems of existing recognition methods were taken into account. In addition, by forming the model, the posture during walking can also be recognized, enabling more accurate recognition. From this point on, the improvement is aimed at how to improve recognition and to show the effectiveness of the model for walking. The developed interface, when combined with actual welfare equipment such as a walker, will contribute to ease of use and the ability to adapt to each individual's gait.

Athlete Rehabilitation Evaluation System Based on Internet of Health Things and Human Gait Analysis Algorithm

In order to improve the effect of athlete’s injury recognition and rehabilitation evaluation, this paper studies the traditional rehabilitation evaluation method and proposes a new athlete rehabilitation evaluation system combining the Internet of Health Things technology and human gait analysis algorithm. Moreover, this paper combines sports characteristics to improve the algorithm of human gait analysis. In addition, through the study of the athlete’s human body modeling and movement process, a human gait analysis algorithm that can be applied to multiple sports is proposed, and the gait parameter analysis and algorithm reliability research are carried out through simulation analysis. After confirming that the algorithm is effective, this paper combines the Internet of Health Things technology to construct a system model, obtains the system function module architecture with the support of the Internet of Health Things technology, and conducts experiments to verify the system performance. From the experimental research, it can be seen that the model constructed in this paper meets the theoretical and practical needs, and the system in this paper can be applied to practice in the future. The human gait recognition algorithm constructed in this article has a good effect and can play an important role in sports rehabilitation of athletes. At the same time, the system constructed in this article has certain advantages over traditional sports rehabilitation systems with the support of algorithms.

Gait recognition based on sparse linear subspace

Gait recognition has broad application prospects in intelligent security monitoring. However, due to the variability of human walking states and the complexity of external conditions during sample collection, gait recognition is still facing many challenges. Among them, gait recognition algorithms based on shallow learning are hard to achieve the correct recognition rate required by many applications, while the amount of gait training data cannot meet the needs of model training based on deep learning. To solve the above problem, this paper presents a novel gait recognition scheme based on sparse linear subspace. First, frame-by-frame gait energy images (ffGEIs) are extracted as primary gait features and sparse linear subspace technology is used to represent them for dimension reduction. Second, a new gait classification algorithm based on support vector machine is presented, which adopts Gaussian radial basis function (RBF) kernels to achieve cross-view gait recognition. Finally, the proposed gait recognition approach is evaluated on two open-accessed gait databases to demonstrate its performance.

Gait recognition in the presence of co-variate conditions

Gait recognition is a biometric technology used to identify people from their walking patterns. Most traditional Computer Vision-based gait recognition approaches have been tested to work satisfactorily given similar training and test conditions. However, there may be situations where the two conditions differ due to the presence of co-variate conditions like bag, coat, and/or others. The presence of co-variate conditions alters the silhouette shape of an individual which affects the performance of the gait recognition algorithms. In this work, we develop an automated approach to perform gait recognition satisfactorily even in the presence of co-variate conditions. First, we determine a set of generic unique poses in a gait cycle, following which we compute gait features corresponding to these poses, which we term as the Dynamic Gait Energy Image (DGEI). Next, a Generative Adversarial Network (GAN) model is employed to predict the corresponding DGEI images without the co-variates. These final gait features are readily comparable with the gallery sequences and, hence, the final recognition is performed using the GAN-generated DGEI images. Extensive experimental studies using the publicly available CASIA B, TUM-GAID, and OU-ISIR TreadMill B data sets verify the effectiveness of the proposed approach and its superiority over the state-of-the-art techniques.

Pedestrian inertial navigation based on CNN-SVM gait recognition algorithm

Pedestrian inertial navigation technology based on inertial measurement unit (IMU) has been widely used in indoor and outdoor applications in recent years. But the IMU has a relatively low measurement accuracy that leads to error accumulation. Zero speed update algorithms (ZUPT) are often used to suppress the accumulation of errors. The key to the zero-speed update algorithm is to accurately find the stance phase in the pedestrian gait cycle. In this paper, an adaptive zero-speed detection algorithm based on CNN-SVM gait recognition is proposed for pedestrian positioning. First, the CNN-SVM algorithm is used to distinguish six gaits and find the optimal detection threshold according to different gaits. At the same time, it is proposed to use the zero-angle velocity update algorithm (ZARU) to correct the angle error, and to improve the accuracy of positioning by combining the information of zero-speed update and zero-angle velocity update through Kalman filter. Finally, the validity of the proposed algorithm is verified by experiments.

Graph-optimized coupled discriminant projections for cross-view gait recognition

Graph-Embedding is a widely used learning technique in pattern recognition. However, it is difficult to construct an inter-view graph for cross-view gait samples. To remedy it, in this paper, we propose a novel cross-view gait recognition algorithm named Graph-optimized Coupled Discriminant Projections (GoCDP), which seeks coupled projections based on adaptive graph learning. Regarding the embedding graphs as variables rather than predefined constants, we integrate inter-view graph construction with projection optimization process into a unified framework. By an alternate iteration algorithm, we can ultimately obtain the optimal coupled projections. Moreover, we extend GoCDP to multi-view case called Graph-optimized Multiview Discriminant Projections (GoMDP) for multi-view subspace learning. Experimental results on two benchmark gait datasets, CASIA-B and OU-ISIR, demonstrate the effectiveness of the proposed methods.

Research on Recognition Technology of Amur Tiger Gait Features Based on Video

With the continuous advancement of technology, people are paying more and more attention to the living environment of wild animals. Located at the top of the food chain of the forest ecosystem, the Siberian tiger is a flagship species and umbrella species for biodiversity protection. The effective protection and sustainable survival of its population has far-reaching natural and social significance for China’s ecological security1. At present, the research on the Siberian tiger is mainly concentrated in the biological fields such as genes and heredity. Only a small amount of research on the detection of Siberian tigers and their footprints in static images. Research on the behavior recognition of Siberian tigers in videos is currently in its infancy. In the field of computer vision, as an independent research object, more and more researchers pay attention to the automatic recognition of gait. Based on the human gait model, a standard database for evaluating the performance of gait recognition algorithms has been established to promote the research of gait recognition. development of. This article will use deep neural convolutional networks and feature subspace learning algorithms to extract the gait features of the Siberian tiger from video images and establish a gait model of the Siberian tiger. This will lay the foundation for the identification of Siberian tigers and further research on their health status, and provide a foundation for the wild Provide theoretical support for animal protection.

Human Gait Recognition Based on Multiple Feature Combination and Parameter Optimization Algorithms.

Accuracy is a key index of human gait recognition. In this paper, we propose an improved gait recognition algorithm, which combines multiple feature combination and artificial bee colony for optimizing the support vector machine (ABC-SVM). Firstly, considering the complexity characteristics of surface electromyography (sEMG) signals, four types of features are extracted from the denoised sEMG signals, including the time-domain features of integral of absolute value (IAV), variance (VAR), and number of zero-crossing (ZC) points, frequency-domain features of mean power frequency (MPF) and median frequency (MF), and wavelet features and fuzzy entropy features. Secondly, the classifiers of SVM, linear discriminant analysis (LDA), and extreme learning machine (ELM) are employed to recognize the gait with obtained features, including singe-class features, multiple combination features, and optimized features of dimension reduction by principal component analysis (PCA). Thirdly, the penalty coefficient and kernel function parameter of the SVM classifier are optimized by the ABC algorithm, and the influence of different features and classifiers on the recognition results is studied. Finally, the feature samples selected to construct the SVM classifier are trained and recognized. Results show that the classification performance of the ABC-SVM classifier is significantly better than that of the nonoptimized SVM classifier, and the average recognition rate is increased by 3.18%. In addition, the combined feature samples (time-domain, frequency-domain, wavelet, and fuzzy entropy features) not only improve the gait classification accuracy but also enhance the recognition stability.