3D Dynamic Scene Analysis

1. Front Matter

   Pages I-XI

   PDF

2. Introduction

   • Zhengyou Zhang, Olivier Faugeras

   Pages 1-8

3. Uncertainty Manipulation and Parameter Estimation

   • Zhengyou Zhang, Olivier Faugeras

   Pages 9-27

4. Reconstruction of 3D Line Segments

   • Zhengyou Zhang, Olivier Faugeras

   Pages 29-38

5. Representations of Geometric Objects

   • Zhengyou Zhang, Olivier Faugeras

   Pages 39-54

6. A Comparative Study of 3D Motion Estimation

   • Zhengyou Zhang, Olivier Faugeras

   Pages 55-80

7. Matching and Rigidity Constraints

   • Zhengyou Zhang, Olivier Faugeras

   Pages 81-98

8. Hypothesize-and-Verify Method for Two 3D View Motion Analysis

   • Zhengyou Zhang, Olivier Faugeras

   Pages 99-126

9. Further Considerations on Reducing Complexity

   • Zhengyou Zhang, Olivier Faugeras

   Pages 127-144

10. Multiple Object Motions

    • Zhengyou Zhang, Olivier Faugeras

    Pages 145-158

11. Object Recognition and Localization

    • Zhengyou Zhang, Olivier Faugeras

    Pages 159-168

12. Calibrating a Mobile Robot and Visual Navigation

    • Zhengyou Zhang, Olivier Faugeras

    Pages 169-186

13. Fusing Multiple 3D Frames

    • Zhengyou Zhang, Olivier Faugeras

    Pages 187-204

14. Solving the Motion Tracking Problem: A Framework

    • Zhengyou Zhang, Olivier Faugeras

    Pages 205-216

15. Modeling and Estimating Motion Kinematics

    • Zhengyou Zhang, Olivier Faugeras

    Pages 217-237

16. Implementation Details and Experimental Results

    • Zhengyou Zhang, Olivier Faugeras

    Pages 239-271

17. Conclusions and Perspectives

    • Zhengyou Zhang, Olivier Faugeras

    Pages 273-276

18. Back Matter

    Pages 277-300

    PDF

he problem of analyzing sequences of images to extract three-dimensional T motion and structure has been at the heart of the research in computer vi­ sion for many years. It is very important since its success or failure will determine whether or not vision can be used as a sensory process in reactive systems. The considerable research interest in this field has been motivated at least by the following two points: 1. The redundancy of information contained in time-varying images can over­ come several difficulties encountered in interpreting a single image. 2. There are a lot of important applications including automatic vehicle driv­ ing, traffic control, aerial surveillance, medical inspection and global model construction. However, there are many new problems which should be solved: how to effi­ ciently process the abundant information contained in time-varying images, how to model the change between images, how to model the uncertainty inherently associated with the imaging system and how to solve inverse problems which are generally ill-posed. There are of course many possibilities for attacking these problems and many more remain to be explored. We discuss a few of them in this book based on work carried out during the last five years in the Computer Vision and Robotics Group at INRIA (Institut National de Recherche en Informatique et en Automatique).

• Vision
• artificial intelligence
• computer vision
• image processing
• intelligence
• modeling
• motion estimation
• navigation
• noise
• robot
• robotics
• uncertainty
• complexity

• INRIA Sophia Antipolis, Sophia Antipolis Cedex, France

  Zhengyou Zhang, Olivier Faugeras

Policies and ethics