Model Based Visual Tracking

This book has two main goals: to provide a unifed and structured overview of this growing field, as well as to propose a corresponding software framework, the OpenTL library, developed by the author and his working group at TUM-Informatik. The main objective of this work is to show, how most real-world application scenarios can be naturally cast into a common description vocabulary, and therefore implemented and tested in a fully modular and scalable way, through the defnition of a layered, object-oriented software architecture.The resulting architecture covers in a seamless way all processing levels, from raw data acquisition up to model-based object detection and sequential localization, and defines, at the application level, what we call the tracking pipeline. Within this framework, extensive use of graphics hardware (GPU computing) as well as distributed processing, allows real-time performances for complex models and sensory systems.

Monocular Model-Based 3D Tracking of Rigid Objects reviews the different techniques and approaches that have been developed by industry and research.

This book presents the state of the art in online visual tracking, including the motivations, practical algorithms, and experimental evaluations. Visual tracking remains a highly active area of research in Computer Vision and the performance under complex scenarios has substantially improved, driven by the high demand in connection with real-world applications and the recent advances in machine learning. A large variety of new algorithms have been proposed in the literature over the last two decades, with mixed success. Chapters 1 to 6 introduce readers to tracking methods based on online learning algorithms, including sparse representation, dictionary learning, hashing codes, local model, and model fusion. In Chapter 7, visual tracking is formulated as a foreground/background segmentation problem, and tracking methods based on superpixels and end-to-end deep networks are presented. In turn, Chapters 8 and 9 introduce the cutting-edge tracking methods based on correlation filter and deep learning. Chapter 10 summarizes the book and points out potential future research directions for visual tracking. The book is self-contained and suited for all researchers, professionals and postgraduate students working in the fields of computer vision, pattern recognition, and machine learning. It will help these readers grasp the insights provided by cutting-edge research, and benefit from the practical techniques available for designing effective visual tracking algorithms. Further, the source codes or results of most algorithms in the book are provided at an accompanying website.

This book covers the description of both conventional methods and advanced methods. In conventional methods, visual tracking techniques such as stochastic, deterministic, generative, and discriminative are discussed. The conventional techniques are further explored for multi-stage and collaborative frameworks. In advanced methods, various categories of deep learning-based trackers and correlation filter-based trackers are analyzed. The book also: Discusses potential performance metrics used for comparing the efficiency and effectiveness of various visual tracking methods Elaborates on the salient features of deep learning trackers along with traditional trackers, wherein the handcrafted features are fused to reduce computational complexity Illustrates various categories of correlation filter-based trackers suitable for superior and efficient performance under tedious tracking scenarios Explores the future research directions for visual tracking by analyzing the real-time applications The book comprehensively discusses various deep learning-based tracking architectures along with conventional tracking methods. It covers in-depth analysis of various feature extraction techniques, evaluation metrics and benchmark available for performance evaluation of tracking frameworks. The text is primarily written for senior undergraduates, graduate students, and academic researchers in the fields of electrical engineering, electronics and communication engineering, computer engineering, and information technology.

Visual tracking is one of the fundamental problems in computer vision. Its numerous applications include robotics, autonomous driving, augmented reality and 3D reconstruction. In essence, visual tracking can be described as the problem of estimating the trajectory of a target in a sequence of images. The target can be any image region or object of interest. While humans excel at this task, requiring little effort to perform accurate and robust visual tracking, it has proven difficult to automate. It has therefore remained one of the most active research topics in computer vision. In its most general form, no prior knowledge about the object of interest or environment is given, except for the initial target location. This general form of tracking is known as generic visual tracking. The unconstrained nature of this problem makes it particularly difficult, yet applicable to a wider range of scenarios. As no prior knowledge is given, the tracker must learn an appearance model of the target on-the-fly. Cast as a machine learning problem, it imposes several major challenges which are addressed in this thesis. The main purpose of this thesis is the study and advancement of the, so called, Discriminative Correlation Filter (DCF) framework, as it has shown to be particularly suitable for the tracking application. By utilizing properties of the Fourier transform, a correlation filter is discriminatively learned by efficiently minimizing a least-squares objective. The resulting filter is then applied to a new image in order to estimate the target location. This thesis contributes to the advancement of the DCF methodology in several aspects. The main contribution regards the learning of the appearance model: First, the problem of updating the appearance model with new training samples is covered. Efficient update rules and numerical solvers are investigated for this task. Second, the periodic assumption induced by the circular convolution in DCF is countered by proposing a spatial regularization component. Third, an adaptive model of the training set is proposed to alleviate the impact of corrupted or mislabeled training samples. Fourth, a continuous-space formulation of the DCF is introduced, enabling the fusion of multiresolution features and sub-pixel accurate predictions. Finally, the problems of computational complexity and overfitting are addressed by investigating dimensionality reduction techniques. As a second contribution, different feature representations for tracking are investigated. A particular focus is put on the analysis of color features, which had been largely overlooked in prior tracking research. This thesis also studies the use of deep features in DCF-based tracking. While many vision problems have greatly benefited from the advent of deep learning, it has proven difficult to harvest the power of such representations for tracking. In this thesis it is shown that both shallow and deep layers contribute positively. Furthermore, the problem of fusing their complementary properties is investigated. The final major contribution of this thesis regards the prediction of the target scale. In many applications, it is essential to track the scale, or size, of the target since it is strongly related to the relative distance. A thorough analysis of how to integrate scale estimation into the DCF framework is performed. A one-dimensional scale filter is proposed, enabling efficient and accurate scale estimation.

Welcome to the proceedings of the 8th European Conference on Computer - sion! Following a very successful ECCV 2002, the response to our call for papers was almost equally strong – 555 papers were submitted. We accepted 41 papers for oral and 149 papers for poster presentation. Several innovations were introduced into the review process. First, the n- ber of program committee members was increased to reduce their review load. We managed to assign to program committee members no more than 12 papers. Second, we adopted a paper ranking system. Program committee members were asked to rank all the papers assigned to them, even those that were reviewed by additional reviewers. Third, we allowed authors to respond to the reviews consolidated in a discussion involving the area chair and the reviewers. Fourth, thereports,thereviews,andtheresponsesweremadeavailabletotheauthorsas well as to the program committee members. Our aim was to provide the authors with maximal feedback and to let the program committee members know how authors reacted to their reviews and how their reviews were or were not re?ected in the ?nal decision. Finally, we reduced the length of reviewed papers from 15 to 12 pages. ThepreparationofECCV2004wentsmoothlythankstothee?ortsofthe- ganizing committee, the area chairs, the program committee, and the reviewers. We are indebted to Anders Heyden, Mads Nielsen, and Henrik J. Nielsen for passing on ECCV traditions and to Dominique Asselineau from ENST/TSI who kindly provided his GestRFIA conference software. We thank Jan-Olof Eklundh and Andrew Zisserman for encouraging us to organize ECCV 2004 in Prague.

This book covers the description of both conventional methods and advanced methods. In conventional methods, visual tracking techniques such as stochastic, deterministic, generative, and discriminative are discussed. The conventional techniques are further explored for multi-stage and collaborative frameworks. In advanced methods, various categories of deep learning-based trackers and correlation filter-based trackers are analyzed. The book also: Discusses potential performance metrics used for comparing the efficiency and effectiveness of various visual tracking methods. Elaborates on the salient features of deep learning trackers along with traditional trackers, wherein the handcrafted features are fused to reduce computational complexity. Illustrates various categories of correlation filter-based trackers suitable for superior and efficient performance under tedious tracking scenarios. Explores the future research directions for visual tracking by analyzing the real-time applications. The book comprehensively discusses various deep learning-based tracking architectures along with conventional tracking methods. It covers in-depth analysis of various feature extraction techniques, evaluation metrics and benchmark available for performance evaluation of tracking frameworks. The text is primarily written for senior undergraduates, graduate students, and academic researchers in the fields of electrical engineering, electronics and communication engineering, computer engineering, and information technology.

The book focuses on visual object tracking systems and approaches based on correlation filter and deep learning. Both foundations and implementations have been addressed. The algorithm, system design and performance evaluation have been explored for three kinds of tracking methods including correlation filter based methods, correlation filter with deep feature based methods, and deep learning based methods. Firstly, context aware and multi-scale strategy are presented in correlation filter based trackers; then, long-short term correlation filter, context aware correlation filter and auxiliary relocation in SiamFC framework are proposed for combining correlation filter and deep learning in visual object tracking; finally, improvements in deep learning based trackers including Siamese network, GAN and reinforcement learning are designed. The goal of this book is to bring, in a timely fashion, the latest advances and developments in visual object tracking, especially correlation filter and deep learning based methods, which is particularly suited for readers who are interested in the research and technology innovation in visual object tracking and related fields.

Leading scientists describe how advances in computer vision can change how we interact with computers.