This thesis describes a representation of gait appearance for the purpose of person identification and classification. This gait representation is based on simple localized image features such as moments extracted from orthogonal view video silhouettes of human walking motion. A suite of time-integration methods, spanning a range of coarseness of time aggregation and modeling of feature distributions, are applied to these image features to create a suite of gait sequence representations. Despite their simplicity, the resulting feature vectors contain enough information to perform well on human identification and gender classification tasks. We demonstrate the accuracy of recognition on gait video sequences collected over different days and times and under varying lighting environments. Each of the integration methods are investigated for their advantages and disadvantages. An improved gait representation is built based on our experiences with the initial set of gait representations. In addition, we show gender classification results using our gait appearance features, the effect of our heuristic feature selection method, and the significance of individual features.

Feature extraction is the most critical step in any human gait recognition system. Although gait is a dynamic process yet the static body parameters also play an important role in characterizing human gait. A few studies were performed in the past to assess the comparative relevance of static and dynamic gait features. There is, however, a lack of work in comparative performance analysis of dynamic gait features from different parts of the silhouettes in an appearance based setup. This dissertation presents a comparative study of dynamic features extracted from legs, arms and shoulders for gait recognition. Our study partially supports the general notion of leg motion being the most important determining factor in gait recognition. But it is also observed that features extracted from upper arm and shoulder area become more significant in some databases. The usefulness of the study hinges on the fact that lower parts of the leg are generally more noisy due to a variety of variations such as walking surface, occlusion and shadows. Dynamic features extracted from the upper part of the silhouettes posses significantly higher discriminatory power in such situations. In other situations these features can play a complementary role in the gait recognition process. We also propose two new feature extraction methods for gait recognition. The new methods use silhouette area signals which are easy and simple to extract. A significant performance increase is achieved by using the new features over the benchmark method and recognition results compare well to the other current techniques. The simplicity and compactness of the proposed gait features is their major advantage because it entails low computational overhead.

Feature extraction is the most critical step in any human gait recognition system. Although gait is a dynamic process yet the static body parameters also play an important role in characterizing human gait. A few studies were performed in the past to assess the comparative relevance of static and dynamic gait features. There is, however, a lack of work in comparative performance analysis of dynamic gait features from different parts of the silhouettes in an appearance based setup. This dissertation presents a comparative study of dynamic features extracted from legs, arms and shoulders for gait recognition. Our study partially supports the general notion of leg motion being the most important determining factor in gait recognition. But it is also observed that features extracted from upper arm and shoulder area become more significant in some databases. The usefulness of the study hinges on the fact that lower parts of the leg are generally more noisy due to a variety of variations such as walking surface, occlusion and shadows. Dynamic features extracted from the upper part of the silhouettes posses significantly higher discriminatory power in such situations. In other situations these features can play a complementary role in the gait recognition process. We also propose two new feature extraction methods for gait recognition. The new methods use silhouette area signals which are easy and simple to extract. A significant performance increase is achieved by using the new features over the benchmark method and recognition results compare well to the other current techniques. The simplicity and compactness of the proposed gait features is their major advantage because it entails low computational overhead.

Yes / Gait is a unique non-invasive biometric form that can be utilized to effectively recognize persons, even when they prove to be uncooperative. Computer-aided gait recognition systems usually use image sequences without considering covariates like clothing and possessions of carrier bags whilst on the move. Similarly, in gait recognition, there may exist unknown covariate conditions that may affect the training and testing conditions for a given individual. Consequently, common techniques for gait recognition and measurement require a degree of intervention leading to the introduction of unknown covariate conditions, and hence this significantly limits the practical use of the present gait recognition and analysis systems. To overcome these key issues, we propose a method of gait analysis accounting for both known and unknown covariate conditions. For this purpose, we propose two methods, i.e., a Convolutional Neural Network (CNN) based gait recognition and a discriminative features-based classification method for unknown covariate conditions. The first method can handle known covariate conditions efficiently while the second method focuses on identifying and selecting unique covariate invariant features from the gallery and probe sequences. The feature set utilized here includes Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG), and Haralick texture features. Furthermore, we utilize the Fisher Linear Discriminant Analysis for dimensionality reduction and selecting the most discriminant features. Three classifiers, namely Random Forest, Support Vector Machine (SVM), and Multilayer Perceptron are used for gait recognition under strict unknown covariate conditions. We evaluated our results using CASIA and OUR-ISIR datasets for both clothing and speed variations. As a result, we report that on average we obtain an accuracy of 90.32% for the CASIA dataset with unknown covariates and similarly performed excellently on the ISIR dataset. Therefore, our proposed method outperforms existing methods for gait recognition under known and unknown covariate conditions. / This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (NRF-2019R1F1A1060668).

Gait recognition is important for identifying suspects in criminal investigations. This study will study the potential of using models based on transfer learning for this purpose. Both supervised and unsupervised learning will be examined. For the supervised learning part, the data is labeled and we investigate how accurate the models can be, and the impact of different walking conditions. Unsupervised learning is when the data is unlabeled and this part will determine if clustering can be used to identify groups of individuals without knowing who it is. Two deep learning models, the InceptionV3 model and the ResNet50V2, model are utilized, and the Gait Energy image method is used as gait representation. After optimization analysis, the models achieved the highest prediction accuracy of 100 percent when only including normal walking conditions and 99.25 percent when including different walking conditions such as carrying a backpack and wearing a coat, making them applicable for use in real-world investigations, provided that the data is labeled. Due to the apparent sensitivity of the models to varying camera angles, the clustering part resulted in an accuracy of approximately 30 percent. For unsupervised learning on gait recognition to be applicable in the real world, additional enhancements are required.

No

In this work, we examine semi-supervised learning for Gait recognition with a limited number of labeled samples. Our research focus on two distinct aspects for limited labels, 1)closed-set: with limited labeled samples per individual, and 2) open-set: with limited labeled individuals. We find open-set poses greater challenge compared to closed-set thus, having more labeled ids is important for performance than having more labeled samples per id. Moreover, obtaining labeled samples for a large number of individuals is usually more challenging, therefore limited id setup (closed-setup) is more important to study where most of the training samples belong to unknown ids. We further analyze that existing semi-supervised learning approaches are not well suited for scenario where unlabeled samples belong to novel ids. We propose a simple prototypical self-training approach to solve this problem, where, we integrate semi-supervised learning for closed set setting with self-training which can effectively utilize unlabeled samples from unknown ids. To further alleviate the challenges of limited labeled samples, we explore the role of synthetic data where we utilize diffusion model to generate samples from both known and unknown ids. We perform our experiments on two different Gait recognition benchmarks, CASIA-B and OUMVLP, and provide a comprehensive evaluation of the proposed method. The proposed approach is effective and generalizable for both closed and open-set settings. With merely 20% of labeled samples, we were able to achieve performance competitive to supervised methods utilizing 100% labeled samples while outperforming existing semi-supervised methods.

Face and gait recognition problems are challenging due to largely varying appearances, highly complex pattern distributions, and insufficient training samples. This dissertation focuses on multilinear subspace learning for face and gait recognition, where low-dimensional representations are learned directly from tensorial face or gait objects. This research introduces a unifying multilinear subspace learning framework for systematic treatment of the multilinear subspace learning problem. Three multilinear projections are categorized according to the input-output space mapping as: vector-to-vector projection, tensor-to-tensor projection, and tensor-to-vector projection. Techniques for subspace learning from tensorial data are then proposed and analyzed. Multilinear principal component analysis (MPCA) seeks a tensor-to-tensor projection that maximizes the variation captured in the projected space, and it is further combined with linear discriminant analysis and boosting for better recognition performance. Uncorrelated MPCA (UMPCA) solves for a tensor-to-vector projection that maximizes the captured variation in the projected space while enforcing the zero-correlation constraint. Uncorrelated multilinear discriminant analysis (UMLDA) aims to produce uncorrelated features through a tensor-to-vector projection that maximizes a ratio of the between-class scatter over the within-class scatter defined in the projected space. Regularization and aggregation are incorporated in the UMLDA solution for enhanced performance. Experimental studies and comparative evaluations are presented and analyzed on the PIE and FERET face databases, and the USF gait database. The results indicate that the MPCA-based solution has achieved the best overall performance in various learning scenarios, the UMLDA-based solution has produced the most stable and competitive results with the same parameter setting, and the UMPCA algorithm is effective in unsupervised learning in low-dimensional subspace. Besides advancing the state-of-the-art of multilinear subspace learning for face and gait recognition, this dissertation also has potential impact in both the development of new multilinear subspace learning algorithms and other applications involving tensor objects.

Face and gait recognition problems are challenging due to largely varying appearances, highly complex pattern distributions, and insufficient training samples. This dissertation focuses on multilinear subspace learning for face and gait recognition, where low-dimensional representations are learned directly from tensorial face or gait objects. This research introduces a unifying multilinear subspace learning framework for systematic treatment of the multilinear subspace learning problem. Three multilinear projections are categorized according to the input-output space mapping as: vector-to-vector projection, tensor-to-tensor projection, and tensor-to-vector projection. Techniques for subspace learning from tensorial data are then proposed and analyzed. Multilinear principal component analysis (MPCA) seeks a tensor-to-tensor projection that maximizes the variation captured in the projected space, and it is further combined with linear discriminant analysis and boosting for better recognition performance. Uncorrelated MPCA (UMPCA) solves for a tensor-to-vector projection that maximizes the captured variation in the projected space while enforcing the zero-correlation constraint. Uncorrelated multilinear discriminant analysis (UMLDA) aims to produce uncorrelated features through a tensor-to-vector projection that maximizes a ratio of the between-class scatter over the within-class scatter defined in the projected space. Regularization and aggregation are incorporated in the UMLDA solution for enhanced performance. Experimental studies and comparative evaluations are presented and analyzed on the PIE and FERET face databases, and the USF gait database. The results indicate that the MPCA-based solution has achieved the best overall performance in various learning scenarios, the UMLDA-based solution has produced the most stable and competitive results with the same parameter setting, and the UMPCA algorithm is effective in unsupervised learning in low-dimensional subspace. Besides advancing the state-of-the-art of multilinear subspace learning for face and gait recognition, this dissertation also has potential impact in both the development of new multilinear subspace learning algorithms and other applications involving tensor objects.

Biometrics is a unique physical or behavioral characteristic of a person. This unique attribute, such as fingerprints or gait, can be used for identification or verification purposes. Gait is an emerging biometrics with great potential. Gait recognition is based on recognizing a person by the manner in which they walk. Its potential lays in that it can be captured at a distance and does not require the cooperation of the subject. This advantage makes it a very attractive tool for forensic cases and applications, where it can assist in identifying a suspect when other evidence such as DNA, fingerprints, or a face were not attainable. Gait can be used for recognition in a direct manner when the two samples are shot from similar camera resolution, position, and conditions. Yet in some cases, the only sample available is of an incomplete gait cycle, low resolution, low frame rate, a partially visible subject, or a single static image. Most of these conditions have one thing in common: static measurements. A gait signature is usually formed from a number of dynamic and static features. Static features are physical measurements of height, length, or build; while dynamic features are representations of joint rotations or trajectories. The aim of this thesis is to study the potential of predicting dynamic features from static features. In this thesis, we have created a database that utilizes a 3D laser scanner for capturing accurate shape and volumes of a person, and a motion capture system to accurately record motion data. The first analysis focused on analyzing the correlation between twenty-one 2D static features and eight dynamic features. Eleven pairs of features were regarded as significant with the criterion of a P-value less than 0.05. Other features also showed a strong correlation that indicated the potential of their predictive power. The second analysis focused on 3D static and dynamic features. Through the correlation analysis, 1196 pairs of features were found to be significantly correlated. Based on these results, a linear regression analysis was used to predict a dynamic gait signature. The predictors chosen were based on two adaptive methods that were developed in this thesis: "the top-x" method and the "mixed method". The predictions were assessed for both for their accuracy and their classification potential that would be used for gait recognition. The top results produced a 59.21% mean matching percentile. This result will act as baseline for future research in predicting a dynamic gait signature from static features. The results of this thesis bare potential for applications in biomechanics, biometrics, forensics, and 3D animation.