Li Markov Random Field Modeling in Computer Vision

Erscheinungsjahr 2012
ISBN: 978-4-431-66933-3
Verlag: Springer Tokyo
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 264 Seiten, eBook

Reihe: Computer Science Workbench

Markov random field (MRF) modeling provides a basis for the characterization of contextual constraints on visual interpretation and enables us to develop optimal vision algorithms systematically based on sound principles. This book presents a comprehensive study on using MRFs to solve computer vision problems, covering the following parts essential to the subject: introduction to fundamental theories, formulations of various vision models in the MRF framework, MRF parameter estimation, and optimization algorithms. Various MRF vision models are presented in a unified form, including image restoration and reconstruction, edge and region segmentation, texture, stereo and motion, object matching and recognition, and pose estimation. This book is an excellent reference for researchers working in computer vision, image processing, pattern recognition and applications of MRFs. It is also suitable as a text for advanced courses in the subject.

Zielgruppe

Research

Autoren/Hrsg.

Li, S.Z.

Inhaltsverzeichnis

1 Introduction.- 1.1 Visual Labeling.- 1.2 Markov Random Fields and Gibbs Distributions.- 1.3 Useful MRF Models.- 1.4 Optimization-Based Vision.- 1.5 Bayes Labeling of MRFs.- 2 Low Level MRF Models.- 2.1 Observation Models.- 2.2 Image Restoration and Reconstruction.- 2.3 Edge Detection.- 2.4 Texture Synthesis and Analysis.- 2.5 Optical Flow.- 3 Discontinuities in MRFs.- 3.1 Smoothness, Regularization and Discontinuities.- 3.2 The Discontinuity Adaptive MRF Model.- 3.3 Computation of DA Solutions.- 3.4 Conclusion.- 4 Discontinuity-Adaptivity Model and Robust Estimation.- 4.1 The DA Prior and Robust Statistics.- 4.2 Experimental Comparison.- 5 High Level MRF Models.- 5.1 Matching under Relational Constraints.- 5.2 MRF-Based Matching.- 5.3 Pose Computation.- 6 MRF Parameter Estimation.- 6.1 Supervised Estimation with Labeled Data.- 6.2 Unsupervised Estimation with Unlabeled Data.- 6.3 Further Issues.- 7 Parameter Estimation in Optimal Object Recognition.- 7.1 Motivation.- 7.2 Theory of Parameter Estimation for Recognition.- 7.3 Application in MRF Object Recognition.- 7.4 Experiments.- 7.5 Conclusion.- 8 Minimization — Local Methods.- 8.1 Classical Minimization with Continuous Labels.- 8.2 Minimization with Discrete Labels.- 8.3 Constrained Minimization.- 9 Minimization — Global Methods.- 9.1 Simulated Annealing.- 9.2 Mean Field Annealing.- 9.3 Graduated Non-Convexity.- 9.4 Genetic Algorithms.- 9.5 Experimental Comparison.- 9.6 Accelerating Computation.- 9.7 Model Debugging.- References.- List of Notation.