by Man-lee Liu. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1998. / Includes bibliographical references (leaves 143-151). / LIST OF TABLES --- p.vi / LIST OF FIGURES --- p.xii / CHAPTER / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Model-based Motion Analysis --- p.2 / Chapter 1.1.1 --- With 3D-to-3D Point Correspondences --- p.4 / Chapter 1.1.2 --- With 2D-to-3D Point Correspondences --- p.5 / Chapter 1.1.3 --- With 2D-to-2D Point Correspondences --- p.6 / Chapter 1.2 --- Motion-based Segmentation --- p.7 / Chapter 1.3 --- 3D Object Recognition --- p.8 / Chapter 1.4 --- Organization of the Thesis --- p.8 / Chapter 2 --- Literature Review and Summary of Contributions --- p.10 / Chapter 2.1 --- Model-based Motion Analysis --- p.10 / Chapter 2.1.1 --- With 3D-to-3D Point Correspondences --- p.10 / Chapter 2.1.2 --- With 2D-to-3D Point Correspondences --- p.13 / Chapter 2.1.2.1 --- An Iterative Approach: Lowe's Algorithm --- p.18 / Chapter 2.1.2.2 --- A Linear Approach: Faugeras's Algorithm --- p.19 / Chapter 2.1.3 --- With 2D-to-2D Point Correspondences --- p.22 / Chapter 2.2 --- Motion-based Segmentation --- p.27 / Chapter 2.3 --- 3D Object Recognition --- p.28 / Chapter 2.4 --- Summary of Contributions --- p.30 / Chapter 3 --- Model-based Motion Analysis with 2D-to-3D Point Correspondences --- p.34 / Chapter 3.1 --- A new Iterative Algorithm for the Perspective-4-point Problem: TL-algorithm --- p.34 / Chapter 3.1.1 --- Algorithm --- p.35 / Chapter 3.1.2 --- Experiment --- p.37 / Chapter 3.1.2.1 --- Experiment using Synthetic Data --- p.38 / Chapter 3.1.2.2 --- Experiment using Real Data --- p.42 / Chapter 3.2 --- An Enhancement of Faugeras's Algorithm --- p.42 / Chapter 3.2.1 --- Experimental Comparison between the Original Faugeras's Algorithm and the Modified One --- p.44 / Chapter 3.2.1.1 --- Experiment One: Fixed Motion --- p.44 / Chapter 3.2.1.2 --- Experiment Two: Using Motion Generated Ran- domly --- p.50 / Chapter 3.2.2 --- Discussion --- p.54 / Chapter 3.3 --- A new Linear Algorithm for the Model-based Motion Analysis: Six-point Algorithm --- p.55 / Chapter 3.3.1 --- General Information of the Six-point Algorithm --- p.55 / Chapter 3.3.2 --- Original Version of the Six-point Algorithm --- p.56 / Chapter 3.3.2.1 --- Linear Solution Part --- p.56 / Chapter 3.3.2.2 --- Constraint Satisfaction --- p.58 / Use of Representation of Rotations by Quaternion --- p.62 / Use of Singular Value Decomposition --- p.62 / Determination of the translational matrix --- p.63 / Chapter 3.3.3 --- Second Version of the Six-point Algorithm --- p.64 / Chapter 3.3.4 --- Experiment --- p.65 / Chapter 3.3.4.1 --- With Synthetic Data --- p.66 / Experiment One: With Fixed Motion --- p.66 / Experiment Two: With Motion Generated Randomly --- p.77 / Chapter 3.3.4.2 --- With Real Data --- p.93 / Chapter 3.3.5 --- Summary of the Six-Point Algorithm --- p.93 / Chapter 3.3.6 --- A Visual Tracking System by using Six-point Algorithm --- p.95 / Chapter 3.4 --- Comparison between TL-algorithm and Six-point Algorithm developed --- p.97 / Chapter 3.5 --- Summary --- p.102 / Chapter 4 --- Motion-based Segmentation --- p.104 / Chapter 4.1 --- A new Approach with 3D-to-3D Point Correspondences --- p.104 / Chapter 4.1.1 --- Algorithm --- p.105 / Chapter 4.1.2 --- Experiment --- p.109 / Chapter 4.2 --- A new Approach with 2D-to-3D Point Correspondences --- p.112 / Chapter 4.2.1 --- Algorithm --- p.112 / Chapter 4.2.2 --- Experiment --- p.116 / Chapter 4.2.2.1 --- Experiment using synthetic data --- p.116 / Chapter 4.2.2.2 --- Experiment using real image sequence --- p.119 / Chapter 4.3 --- Summary --- p.119 / Chapter 5 --- 3D Object Recognition --- p.121 / Chapter 5.1 --- Proposed Algorithm for the 3D Object Recognition --- p.122 / Chapter 5.1.1 --- Hypothesis step --- p.122 / Chapter 5.1.2 --- Verification step --- p.124 / Chapter 5.2 --- 3D Object Recognition System --- p.125 / Chapter 5.2.1 --- System in Matlab: --- p.126 / Chapter 5.2.2 --- System in Visual C++ --- p.129 / Chapter 5.3 --- Experiment --- p.131 / Chapter 5.3.1 --- System in Matlab --- p.132 / Chapter 5.3.2 --- System in Visual C++ --- p.136 / Chapter 5.4 --- Summary --- p.139 / Chapter 6 --- Conclusions --- p.140 / REFERENCES --- p.142 / APPENDIX / Chapter A --- Representation of Rotations by Quaternion --- p.152 / Chapter B --- Constrained Optimization --- p.154
| Identifer | oai:union.ndltd.org:cuhk.edu.hk/oai:cuhk-dr:cuhk_322211 |
| Date | January 1998 |
| Contributors | Liu, Man-lee., Chinese University of Hong Kong Graduate School. Division of Computer Science and Engineering. |
| Source Sets | The Chinese University of Hong Kong |
| Language | English |
| Detected Language | English |
| Type | Text, bibliography |
| Format | print, xv, 155 leaves : ill. ; 30 cm. |
| Rights | Use of this resource is governed by the terms and conditions of the Creative Commons “Attribution-NonCommercial-NoDerivatives 4.0 International” License (http://creativecommons.org/licenses/by-nc-nd/4.0/) |
Page generated in 0.002 seconds