Structured Computer Vision

Structured Computer Vision

Structured Learning and Prediction in Computer Vision introduces the reader to the most popular classes of structured models in computer vision.

Provides comprehensive coverage of theory and hands-on implementation of computer vision-based sensors for structural health monitoring This book is the first to fill the gap between scientific research of computer vision and its practical applications for structural health monitoring (SHM). It provides a complete, state-of-the-art review of the collective experience that the SHM community has gained in recent years. It also extensively explores the potentials of the vision sensor as a fast and cost-effective tool for solving SHM problems based on both time and frequency domain analytics, broadening the application of emerging computer vision sensor technology in not only scientific research but also engineering practice. Computer Vision for Structural Dynamics and Health Monitoring presents fundamental knowledge, important issues, and practical techniques critical to successful development of vision-based sensors in detail, including robustness of template matching techniques for tracking targets; coordinate conversion methods for determining calibration factors to convert image pixel displacements to physical displacements; sensing by tracking artificial targets vs. natural targets; measurements in real time vs. by post-processing; and field measurement error sources and mitigation methods. The book also features a wide range of tests conducted in both controlled laboratory and complex field environments in order to evaluate the sensor accuracy and demonstrate the unique features and merits of computer vision-based structural displacement measurement. Offers comprehensive understanding of the principles and applications of computer vision for structural dynamics and health monitoring Helps broaden the application of the emerging computer vision sensor technology from scientific research to engineering practice such as field condition assessment of civil engineering structures and infrastructure systems Includes a wide range of laboratory and field testing examples, as well as practical techniques for field application Provides MATLAB code for most of the issues discussed including that of image processing, structural dynamics, and SHM applications Computer Vision for Structural Dynamics and Health Monitoring is ideal for graduate students, researchers, and practicing engineers who are interested in learning about this emerging sensor technology and advancing their applications in SHM and other engineering problems. It will also benefit those in civil and aerospace engineering, energy, and computer science.

This book constitutes the thoroughly refereed post-proceedings of the First International Workshop on Deep Structure, Singularities, and Computer Vision, DSSCV 2005, held in Maastricht, The Netherlands in June 2005. The 14 revised full papers and 8 revised poster papers presented were carefully reviewed and selected for inclusion in the book. They represent the current state-of-the-art in understanding the relation between structural, topological information represented by singularities and metric information of signals, shapes, images, and colors.

Probabilistic Graphical Models for Computer Vision introduces probabilistic graphical models (PGMs) for computer vision problems and teaches how to develop the PGM model from training data. This book discusses PGMs and their significance in the context of solving computer vision problems, giving the basic concepts, definitions and properties. It also provides a comprehensive introduction to well-established theories for different types of PGMs, including both directed and undirected PGMs, such as Bayesian Networks, Markov Networks and their variants. Discusses PGM theories and techniques with computer vision examples Focuses on well-established PGM theories that are accompanied by corresponding pseudocode for computer vision Includes an extensive list of references, online resources and a list of publicly available and commercial software Covers computer vision tasks, including feature extraction and image segmentation, object and facial recognition, human activity recognition, object tracking and 3D reconstruction

A modern treatment focusing on learning and inference, with minimal prerequisites, real-world examples and implementable algorithms.

Computer vision deals with the problem of manipulating information contained in large quantities of sensory data, where raw data emerge from the transducing 6 7 sensors at rates between 10 to 10 pixels per second. Conventional general purpose computers are unable to achieve the computation rates required to op erate in real time or even in near real time, so massively parallel systems have been used since their conception in this important practical application area. The development of massively parallel computers was initially character ized by efforts to reach a speedup factor equal to the number of processing elements (linear scaling assumption). This behavior pattern can nearly be achieved only when there is a perfect match between the computational struc ture or data structure and the system architecture. The theory of hierarchical modular systems (HMSs) has shown that even a small number of hierarchical levels can sizably increase the effectiveness of very large systems. In fact, in the last decade several hierarchical architectures that support capabilities which can overcome performances gained with the assumption of linear scaling have been proposed. Of these architectures, the most commonly considered in com puter vision is the one based on a very large number of processing elements (PEs) embedded in a pyramidal structure. Pyramidal architectures supply the same image at different resolution lev els, thus ensuring the use of the most appropriate resolution for the operation, task, and image at hand.