| Description |
1 online resource (xvi, 260 pages) : illustrations (some color) |
|
text txt rdacontent |
|
computer c rdamedia |
|
online resource cr rdacarrier |
| Summary |
This book represents a summary of the research we have been conducting since the early 1990s, and describes a conceptual framework which addresses some current shortcomings, and proposes a unified approach for a broad class of problems. While the framework is defined, our research continues, and some of the elements presented here will no doubt evolve in the coming years. It is organized in eight chapters. In the Introduction chapter, we present the definition of the problems, and give an overview of the proposed approach and its implementation. In particular, we illustrate the limitations of the 2.5D sketch, and motivate the use of a representation in terms of layers instead. In chapter 2, we review some of the relevant research in the literature. The discussion focuses on general computational approaches for early vision, and individual methods are only cited as references. Chapter 3 is the fundamental chapter, as it presents the elements of our salient feature inference engine, and their interaction. It introduced tensors as a way to represent information, tensor fields as a way to encode both constraints and results, and tensor voting as the communication scheme. Chapter 4 describes the feature extraction steps, given the computations performed by the engine described earlier. In chapter 5, we apply the generic framework to the inference of regions, curves, and junctions in 2-D. The input may take the form of 2-D points, with or without orientation. We illustrate the approach on a number of examples, both basic and advanced. In chapter 6, we apply the framework to the inference of surfaces, curves and junctions in 3-D. Here, the input consists of a set of 3-D points, with or without as associated normal or tangent direction. We show a number of illustrative examples, and also point to some applications of the approach. In chapter 7, we use our framework to tackle 3 early vision problems, shape from shading, stereo matching, and optical flow computation. In chapter 8, we conclude this book with a few remarks, and discuss future research directions. We include 3 appendices, one on Tensor Calculus, one dealing with proofs and details of the Feature Extraction process, and one dealing with the companion software packages. |
| Bibliography |
Includes bibliographical references and index. |
| Note |
Print version record. |
| Contents |
Cover -- Table of Contents -- List of Figures -- Preface -- Acknowledgements -- Chapter 1. Introduction -- 1.1 Motivation and Goals -- 1.2 Our Approach -- 1.3 Overview of the Proposed Method -- 1.4 Contribution of this book -- 1.5 Notations -- Chapter 2. Previous Work -- 2.1 Regularization -- 2.2 Consistent Labeling -- 2.3 Clustering and Robust Methods -- 2.4 Artificial Neural Network Approach -- 2.5 Novelty of Our Approach -- Chapter 3. The Salient Feature Inference Engine -- 3.1 Overview of the Salient Inference Engine -- 3.2 Representation -- 3.3 Communication through Tensor Voting -- 3.4 Derivation and Properties of the Fundamental Voting Field -- 3.5 Implementation of Tensor Voting -- 3.6 Feature Extraction -- 3.7 Complexity -- 3.8 Summary -- Chapter 4. Feature Extraction -- 4.1 Extremal Curves in 2-D -- 4.2 Extremal Surfaces in 3-D -- 4.3 Extremal Curves in 3-D -- 4.4 Complexity -- 4.5 Summary -- Chapter 5. Feature Inference in 2-D -- 5.1 Related work -- 5.2 Inference of junctions and curves from oriented data -- 5.3 Inference of junctions and curves from non-oriented data -- 5.4 Interesting properties -- 5.5 End-point grouping -- 5.6 Detection of curve end-points and region boundaries -- 5.7 Integrated feature extraction in 2-D -- 5.8 Applications -- 5.9 Summary -- Chapter 6. Feature Inference in 3-D -- 6.1 Related Work -- 6.2 Feature inference from oriented and non-oriented data -- 6.3 Feature inference from oriented data -- 6.4 Feature inference from non-oriented data -- 6.5 Examples -- 6.6 Integrated feature inference in 3-D -- 6.7 Experiments -- 6.8 Applications -- 6.9 Summary -- Chapter 7. Application to Early Vision Problems -- 7.1 Shape from Shading -- 7.2 Shape from Stereo -- 7.3 Accurate Motion Flow Estimation with Discontinuities -- Chapter 8. Conclusion -- 8.1 Summary -- 8.2 Future Research -- Appendix A: Tensor analysis -- Appendix B: Details of the Marching Algorithms -- Appendix C: Software Systems -- References -- Author Index -- Index -- Color Plate Section -- Last Page. |
| Subject |
Computer vision.
|
|
Calculus of tensors.
|
|
Vision par ordinateur.
|
|
Calcul tensoriel.
|
|
COMPUTERS -- Computer Vision & Pattern Recognition.
|
|
Calculus of tensors
|
|
Computer vision
|
| Added Author |
Lee, Mi-Suen.
|
|
Tang, Chi-Keung.
|
| Other Form: |
Print version: Medioni, Gérard. Computational framework for segmentation and grouping. Amsterdam ; New York : Elsevier, 2000 0444503536 9780444503534 (DLC) 00023205 (OCoLC)43481750 |
| ISBN |
9780444503534 |
|
0444503536 |
|
9780080529486 (electronic bk.) |
|
0080529488 (electronic bk.) |
| Standard No. |
AU@ 000050492006 |
|
AU@ 000062579236 |
|
AU@ 000069137136 |
|
CHNEW 001006548 |
|
DEBBG BV041119706 |
|
DEBBG BV042307530 |
|
DEBSZ 396675891 |
|
DEBSZ 405309155 |
|
DEBSZ 434184829 |
|
GBVCP 78536532X |
|
NZ1 12435095 |
|
