Human Gait Recognition Based on Deep Learning: A Review

Human gait recognition (HGR) has been employed as a biometric technique for security purposes over the last decade. Various factors, including clothing, carrying items, and walking surfaces, can influence the performance of gait recognition. Additionally, identifying individuals from different viewpoints presents a significant challenge in HGR. Numerous conventional and deep learning techniques have been introduced in the literature for HGR, but traditional methods are not well suited to handling large datasets. This research explores the effectiveness of four deep learning models for gait identification in the CASIA B dataset: the convolutional neural network (CNN), multi-layer perceptron (MLP), self-organizing map (SOMs), and transfer learning with EfficientNet. The selected deep learning techniques offer robust feature extraction and the efficient handling of large datasets, making them ideal in enhancing the accuracy of gait recognition. The collection includes gait sequences from 10 individuals, with a total of 92,596 images that have been reduced to 64 × 64 pixels for uniformity. A modified model was developed by integrating sequential convolutional layers for detailed spatial feature extraction, followed by dense layers for classification, optimized through rigorous hyperparameter tuning and regularization techniques, resulting in an accuracy of 97.12% for the test set. This work enhances our understanding of deep learning methods in gait analysis, offering significant insights for choosing optimal models in security and surveillance applications.

TS[formula omitted]HGRNet: A paradigm of two stream best deep learning feature fusion assisted framework for human gait analysis using controlled environment in smart cities

One of the rudimentary forms of human locomotion is Gait that roves the center of mass (COM) of the body in different directions. The human gait is comprised of details of the personals that consist of movements related to patterns and intentions. The detection of human gait is through either wearable sensors or an electromyography signal that shows the most promising potential as a therapeutic method. While analyzing Gait, a large number of gait parameters are required which are interdependent, and this makes it difficult to interpret as a large number of parameters have a large amount of data. These data are mostly collected from various clinical laboratories. The current paper discusses human gait and the recognition of these events based on various deep learning models. Adding to this, issues and challenges that are related to Gait are also elaborated with prominent techniques used in gait recognition.

Human Gait Recognition (HGR) is a biometric technique that has been utilized for security purposes for the last decade. The performance of gait recognition can be influenced by various factors such as wearing clothes, carrying a bag, and the walking surfaces. Furthermore, identification from differing views is a significant difficulty in HGR. Many techniques have been introduced in the literature for HGR using conventional and deep learning techniques. However, the traditional methods are not suitable for large datasets. Therefore, a new framework is proposed for human gait recognition using deep learning and best feature selection. The proposed framework includes data augmentation, feature extraction, feature selection, feature fusion, and classification. In the augmentation step, three flip operations were used. In the feature extraction step, two pre-trained models were employed, Inception-ResNet-V2 and NASNet Mobile. Both models were fine-tuned and trained using transfer learning on the CASIA B gait dataset. The features of the selected deep models were optimized using a modified three-step whale optimization algorithm and the best features were chosen. The selected best features were fused using the modified mean absolute deviation extended serial fusion (MDeSF) approach. Then, the final classification was performed using several classification algorithms. The experimental process was conducted on the entire CASIA B dataset and achieved an average accuracy of 89.0. Comparison with existing techniques showed an improvement in accuracy, recall rate, and computational time.

This paper proposes certain features for human gait cycle detection and recognition. The features cover both the categories of holistic and model-based approaches for human gait recognition. A unique feature vector is formed from the spatial-temporal silhouettes and Support Vector Machine (SVM) classifier is used for the identification of individuals through their gait. The present work is concerned with the efficiency of the extracted features. Experimentation on the silhouette samples of publicly available CASIA database has given furnishes promising results.

The paper explores the challenge of human identification through gait recognition within biometric identification systems. Itoutlines the essential criteria for human biometric features, discusses primary biometric characteristics, and their application in biometric identification systems. The paper also examines the feasibility of utilizing gait as a biometric identifier, emphasizing its advantages, such as not requiring the upfront provision of personal biometric information and specialized equipment.The authors conduct an analysis of existing scientific literature in the field of gait recognition, categorizing gait recognition methodsinto template-based and non-template-based approaches. Throughout their research, they identify the key issues and challenges that researchers face in this domain, along with the prevailing trends in human gait recognition within biometric identification systems.Additionally, the paper introduces a method for person identification based on gait, utilizing the Histogram of Oriented Gradients and the Sum Variance Haralick texture features. It involves transforming input video into a series of images depicting the gait silhouette, creating a Gait Energy Image (GEI) by combining these gait silhouettes throughout a gait cycle, and translating the GEI into the Gait Gradient Magnitude Image (GGMI). The subsequent step involves extracting recommended gait characteristics from the GGMIs of participants included in a dataset.To preprocess the collected characteristics, Principal Component Analysis (PCA) is applied, reducing the dimensions that may negatively impact classification robustness, thereby enhancing overall performance. In the final step, a K-Nearest Neighbors (KNN) classifier is employed to categorize the characteristics obtained from a specific dataset.The proposed novel feature vector in the paper demonstrates increased reliability and effectively captures spatial variations in gait patterns. Notably, it reduces the dimensionality of the feature vector from 3780×1 to 63×1, resulting in decreased computational complexity in the gait recognition system. Experimental evaluations on the CASIA A and CASIA B datasets reveal that the proposed approach outperforms other HOG-based methods in most scenarios, with the exception of situations involving frontal images.

Gait recognition has become popular due to the rising demand for nonintrusive biometrics. At its nascent stage of development, gait recognition faces a number of challenges. The performance of a gait recognition system is sensitive towards factors like viewing angle, clothing, shoe type, load carriage and speed changes. In this paper, the problems of gait are formulated on the Grassmann manifold. It is not difficult to obtain multiple snapshots of a walking subjects with the wide availability of camera networks. These sets of images can be modelled as low-dimensional subspaces, which can be realized naturally as points on the Grassmann manifold. Modelling image sets as low-dimensional subspaces provides not only possible clue of one’s gait, but also the common patterns of variation in the set. We present a method called Localized Grassmann Mean Representatives with Partial Least Squares Regression (LoGPLS) to infer a low-dimensional Euclidean approximation of the manifold. The notion of local mean representatives is introduced to construct multiple tangent spaces to better approximate the topological structure of the manifold. As the properties of the tangent spaces allows the Grassmann points to be evaluated in the vector space, partial least squares is applied to allow a more accurate classification of the points in a reduced space. Experiments have been conducted on four different publicly available gait databases. Empirical evidences demonstrate the effectiveness of the proposed approach in solving the various covariates in gait recognition.

Gait recognition is usually referred to signify the human identification by the style/way people walk in image sequences. Our aim is to implement the traditional gait recognition algorithm and to show the variation in gait recognition when subject is observed parallel to camera under three conditions- walking normal, carrying a bag and wearing a coat. However in this case, the work devises a novel method for the purpose of similarity computation rather than the traditional recognition where the overall recognition rate of 78.57 percent was obtained.

We have been working on the application of Machining Learning in Metabolomics, Drug-Drug Interaction Discovery and Human Gait Recognition [1-5], profiling large data sets. Extraction of vital information about 1) plant metabolomics that can improve the environment and food quality, 2) in vitro neuronal network behavior patterns for various drugs that can be used to characterize drugs for brain deceases and 3) human gait patterns that can reveal various diseases were among these applications. We have demonstrated with considerable success in using unsupervised clustering techniques to analyze genetic and metabolomic data. This includes analysis of drought resistance in wheat [4] and microbial metagenomes [5].We introduced two methods: Near Unsupervised Learning (NUL) and Sub-sample Error Graphs (SEGs) [5] to analyze large amount of data. Self Organizing Map (SOM), which is one of the widely used Unsupervised Neural Networks, has been used as a data-mining tool due to its ability to map high dimensional data into a two dimensional feature map, which is expected to be topology preserving allowing users to visually identify clusters by their topological relationships in terms of their proximity on the map. The Growing Self Organizing Maps (GSOM) further allows the map size to be determined by the algorithm, which relies upon a user set parameter called Spread Factor (SF) [6]. The wide availability of GPUs for affordable prices allows faster comparison of various SOMs with different maps sizes taking away some of the advantages GSOM claimed. Further development of GSOM into a Dynamic SOM Tree exploits the possibility of varying SF to obtain multiple GSOMs from a small number of compact clusters to a large number of sparse clusters [7]. NUL methods can be applied on GSOM using a small number of labels that should be available for every class. This is however not realistic in some applications where the number of classes cannot be explicitly known. We propose a new method call Deep Near Unsupervised Learning (D-NUL), where Dynamic SOM tree is used instead of GSOM and the number of classes are not assumed to be known. The implementation of Dynamic SOM tree methods with varying SF on GPUs will make the computation with D-NUL possible for many problems in big data analytics.

One of the most distinctive characteristics of human beings is an ability to walk erect (bipedalism). However, this fact has not been much taken into consideration in designing user-interfaces. In this paper we present real-time recognition of human gait captured by a floor mat device. Two-dimensional continuous dynamic programming, 2DCDP, which is a powerful object recognition algorithm is adapted so that it fits to demands for real-time human gait recognition. Experiments showed that the system is promising towards realization of invisible user interfaces.

Gait recognition is an appealing biometric modality which aims to identify individuals based on the way they walk. Deep learning has reshaped the research landscape in this area since 2015 through the ability to automatically learn discriminative representations. Gait recognition methods based on deep learning now dominate the state-of-the-art in the field and have fostered real-world applications. In this paper, we present a comprehensive overview of breakthroughs and recent developments in gait recognition with deep learning, and cover broad topics including datasets, test protocols, state-of-the-art solutions, challenges, and future research directions. We first review the commonly used gait datasets along with the principles designed for evaluating them. We then propose a novel taxonomy made up of four separate dimensions namely body representation, temporal representation, feature representation, and neural architecture, to help characterize and organize the research landscape and literature in this area. Following our proposed taxonomy, a comprehensive survey of gait recognition methods using deep learning is presented with discussions on their performances, characteristics, advantages, and limitations. We conclude this survey with a discussion on current challenges and mention a number of promising directions for future research in gait recognition.

Biometric recognition of human gait is a promising, non-invasive method for the identification of people that does not require their engagement. Existing solutions mainly focus on the identification effectiveness under laboratory conditions, frequently overlooking factors that disrupt the gait of test subjects. The present work considers the issue of identifying a person on the basis of ground reaction forces in cases where their gait is disrupted through asymmetric loading. This paper proposes a solution based on ensemble classifiers utilizing various types of deep neural networks as base classifiers. To further increase the ability to generalize base models, data augmentation was used. The proposed solution was tested on a sample of 215 people (7351 gait cycles) and two strategies for combining classifier decisions. The accuracy results obtained, ranging between 99.8, 98.55, and 98.85% correct recognitions depending on the scenario analyzed, are very good and significantly exceed other methods presented in the literature to date.

View-independent human motion classification using image-based reconstruction

A system for automatic gait recognition without segmentation of particular body parts is described. Eigenspace transformation (EST) has already proved useful for several tasks including face recognition, gait analysis, etc; it is optimal in dimensionality reduction by maximising the total scatter of all classes but is not optimal for class separability. A statistical approach that combines EST with canonical space transformation (CST) is proposed for gait recognition using temporal templates from a gait sequence as features. This method can be used to reduce data dimensionality and to optimise the class separability of different gait sequences simultaneously. Incorporating temporal information from optical-flow changes between two consecutive spatial templates, each temporal template extracted from computation of optical flow is projected from a high-dimensional image space to a single point in a low-dimensional canonical space. Using template matching, recognition of human gait becomes much faster and simpler in this new space. As such, the combination of EST and CST is shown to be of considerable potential in an emerging new biometric.

Gait recognition is a biometric recognition technology that supports long-distance, multi-target recognition with resistance to partial occlusions and does not require active user cooperation; thus, it is more suitable than other technologies for individual identification in mass video surveillance systems. Gait recognition based on deep learning has become the mainstream technology in this field because of its strong self-learning and model prediction abilities. However, there is still a lack of research focusing on actual scenes and application requirements for gait recognition, such as multi-target, real-time, and robust recognition. Therefore, this paper analyzes the basic tasks of deep gait recognition methods and encapsulates the application scope of deep gait recognition. Subsequently, this paper investigates the methods of large-space deep gait recognition from three aspects: image preprocessing, gait feature extraction with deep learning, and classifier and evaluation. In particular, the study investigated and analyzed the gait input templates often used in mass surveillance, auto encoder with deep learning, and performance evaluation indexes for the first time. Finally, the unresolved issues in deep gait recognition are summarized, and suggestions and directions for future research are presented.