Emerging Topics in Computer Vision

Series
Prentice Hall
Author
Gerard Medioni / Sing Bing Kang  
Publisher
Prentice Hall
Cover
Softcover
Edition
1
Language
English
Total pages
688
Pub.-date
July 2004
ISBN13
9780131013667
ISBN
0131013661
Related Titles


Product detail

Title no longer available

Description

The state-of-the art in computer vision: theory, applications, and programming

Whether you're a working engineer, developer, researcher, or student, this is your single authoritative source for today's key computer vision innovations. Gerard Medioni and Sing Bing Kang present advances in computer vision such as camera calibration, multi-view geometry, and face detection, and introduce important new topics such as vision for special effects and the tensor voting framework. They begin with the fundamentals, cover select applications in detail, and introduce two popular approaches to computer vision programming.

  • Camera calibration using 3D objects, 2D planes, 1D lines, and self-calibration
  • Extracting camera motion and scene structure from image sequences
  • Robust regression for model fitting using M-estimators, RANSAC, and Hough transforms
  • Image-based lighting for illuminating scenes and objects with real-world light images
  • Content-based image retrieval, covering queries, representation, indexing, search, learning, and more
  • Face detection, alignment, and recognition--with new solutions for key challenges
  • Perceptual interfaces for integrating vision, speech, and haptic modalities
  • Development with the Open Source Computer Vision Library (OpenCV)
  • The new SAI framework and patterns for architecting computer vision applications

Table of Contents

 Preface.

 Contributors.

1. Introduction.

I. FUNDAMENTALS IN COMPUTER VISION.  

2. Camera Calibration.

Zhengyou Zhang.

Introduction.

Notation and Problem Statement.

Camera Calibration with 3D Objects.

Camera Calibration with 2D Objects: Plane-Based Technique.

Solving Camera Calibration with 1D Objects.

Self-Calibration.

Conclusion.

Appendix: Estimating Homography Between Plane and Image.

Bibliography.

3. Multiple View Geometry. 

 Anders Heyden and Marc Pollefeys.

Introduction.

Projective Geometry.

Tensor Calculus.

Modeling Cameras.

Multiple View Geometry.

Structure and Motion I.

Structure and Motion II.

Autocalibration.

Dense Depth Estimation.

Visual Modeling.

Conclusion.

Bibliography. 

4. Robust Techniques for Computer Vision.

 

Peter Meer.

Robustness in Visual Tasks.

Models and Estimation Problems.

Location Estimation.

Robust Regression.

Conclusion.

Bibliography. 

5. The Tensor Voting Framework.

Gérard Medioni and Philippos Mordohai.

Introduction.

Related Work.

Tensor Voting in 2D.

Tensor Voting in 3D.

Tensor Voting in ND.

Application to Computer Vision Problems.

Conclusion and Future Work.

Acknowledgments.

Bibliography. 

II. APPLICATIONS IN COMPUTER VISION.

6. Image-Based Lighting. 

 Paul E. Debevec.

Basic Image-Based Lighting.

Advanced Image-Based Lighting.

Image-Based Relighting.

Conclusion.

Bibliography.

7. Computer Vision In Visual Effects. 

 Doug Roble.

Introduction.

Computer Vision Problems Unique to Film.

Feature Tracking.

Optical Flow.

Camera Tracking and Structure from Motion.

The Future.

Bibliography.

8. Content-Based Image Retrieval: An Overview.

Theo Gevers and Arnold W. M. Smeulders

Overview of Chapter.

Image Domains.

Image Features.

Representation and Indexing.

Similarity and Search.

Interaction and Learning.

Conclusion.

Bibliography.

  9. Face Detection, Alignment, and Recognition.

  Stan Z. Li and Juwei Lu.

Introduction.

Face Detection.

Face Alignment.

Face Recognition.

Bibliography. 

10. Perceptual Interfaces.

Matthew Turk and Mathias Kölsch

Introduction.

Perceptual Interfaces and HCI.

Multimodal Interfaces.

Vision-Based Interfaces.

Brain-Computer Interfaces.

Summary.

Bibliography. 

III. PROGRAMMING FOR COMPUTER VISION.

11. Open Source Computer Vision Library.

Gary Bradski.

Overview.

Functional Groups: What's Good for What.

Pictorial Tour.

Programming Examples Using C/C++.

Other Interfaces.

Appendix A.

Appendix B.

Bibliography.

12. Software Architecture For Computer Vision.

Alexandre R. J. François.

Introduction.

SAI: A Software Architecture Model.

MFSM: An Architectural Middleware.

Conclusion.

Acknowledgments.

Bibliography.

Index.

Back Cover

The state-of-the art in computer vision: theory, applications, and programming

Whether you're a working engineer, developer, researcher, or student, this is your single authoritative source for today's key computer vision innovations. Gerard Medioni and Sing Bing Kang present advances in computer vision such as camera calibration, multi-view geometry, and face detection, and introduce important new topics such as vision for special effects and the tensor voting framework. They begin with the fundamentals, cover select applications in detail, and introduce two popular approaches to computer vision programming.

  • Camera calibration using 3D objects, 2D planes, 1D lines, and self-calibration
  • Extracting camera motion and scene structure from image sequences
  • Robust regression for model fitting using M-estimators, RANSAC, and Hough transforms
  • Image-based lighting for illuminating scenes and objects with real-world light images
  • Content-based image retrieval, covering queries, representation, indexing, search, learning, and more
  • Face detection, alignment, and recognition--with new solutions for key challenges
  • Perceptual interfaces for integrating vision, speech, and haptic modalities
  • Development with the Open Source Computer Vision Library (OpenCV)
  • The new SAI framework and patterns for architecting computer vision applications


Author

GÉRARD MEDIONI chairs the Computer Science Department and is Professor at the Institute for Robotics and Intelligent Systems at the University of Southern California. His research interests include designing and implementing very reliable vision systems to accomplish difficult tasks and establishing bridges between computer vision and computer graphics. SING BING KANG is a member of the Interactive Visual Media Group at Microsoft Research, where he specializes in vision-based modeling. He recently co-edited Panoramic Vision: Sensors, Theory, and Applications, and has served on the technical committees of three major computer vision conferences. He holds 12 US patents.