by Yip Pak Ching. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1992. / Includes bibliographical references (leaves 97-100). / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Background --- p.1 / Chapter 1.2 --- The Objective of Machine Vision --- p.3 / Chapter 1.3 --- Our Goal --- p.4 / Chapter 1.4 --- Previous Works and Current Research --- p.5 / Chapter 1.5 --- Organization of the Thesis --- p.8 / Chapter 2 --- Human Movement Perception --- p.11 / Chapter 2.1 --- Basic Mechanisms of Vision --- p.11 / Chapter 2.2 --- Functions of Movement Perception --- p.12 / Chapter 2.3 --- Five Ways to Make a Spot of Light Appear to Move --- p.14 / Chapter 2.4 --- Real Movement --- p.15 / Chapter 2.5 --- Mechanisms for the Perception of Real Movement --- p.16 / Chapter 2.6 --- Apparent Motion --- p.18 / Chapter 3 --- Machine Movement Perception --- p.21 / Chapter 3.1 --- Introduction --- p.21 / Chapter 3.2 --- Perspective Transformation --- p.21 / Chapter 3.3 --- Motion Detection by Difference Image --- p.22 / Chapter 3.4 --- Accumulative Difference --- p.24 / Chapter 3.5 --- Establishing a Reference Image --- p.26 / Chapter 3.6 --- Optical Flow --- p.27 / Chapter 4 --- Neural Networks for Machine Vision --- p.30 / Chapter 4.1 --- Introduction --- p.30 / Chapter 4.2 --- Perceptron --- p.30 / Chapter 4.3 --- The Back-Propagation Training Algorithm --- p.33 / Chapter 4.4 --- Object Identification --- p.34 / Chapter 4.5 --- Special Technique for Improving the Learning Time and Recognition Rate --- p.36 / Chapter 5 --- Neural Networks by Supervised Learning for Motion Detection --- p.39 / Chapter 5.1 --- Introduction --- p.39 / Chapter 5.2 --- Three-Level Network Architecture --- p.40 / Chapter 5.3 --- Four-Level Network Architecture --- p.45 / Chapter 6 --- Rough Motion Detection --- p.50 / Chapter 6.1 --- Introduction --- p.50 / Chapter 6.2 --- The Rough Motion Detection Network --- p.51 / Chapter 6.3 --- The Correlation Network --- p.54 / Chapter 6.4 --- Modified Rough Motion Detection Network --- p.56 / Chapter 7 --- Moving Object Extraction --- p.59 / Chapter 7.1 --- Introduction --- p.59 / Chapter 7.2 --- Three Types of Images for Moving Object Extraction --- p.59 / Chapter 7.3 --- Edge Enhancement Network --- p.62 / Chapter 7.4 --- Background Remover --- p.63 / Chapter 8 --- Motion Parameter Extraction --- p.66 / Chapter 8.1 --- Introduction --- p.66 / Chapter 8.2 --- 2-D Motion Detection --- p.66 / Chapter 8.3 --- Normalization Network --- p.67 / Chapter 8.4 --- 3-D Motion Parameter Extraction --- p.70 / Chapter 8.5 --- Object Identification --- p.70 / Chapter 9 --- Motion Parameter Extraction from Overlapped Object Images --- p.72 / Chapter 9.1 --- Introduction --- p.72 / Chapter 9.2 --- Decision Network --- p.72 / Chapter 9.3 --- Motion Direction Extraction from Overlapped Object Images by Three-Level Network Model with Supervised Learning --- p.75 / Chapter 9.4 --- Readjustment Network for Motion Parameter Extraction from Overlapped Object Images --- p.79 / Chapter 9.5 --- Reconstruction of the Overlapped object Image --- p.82 / Chapter 10 --- The Integrated Motion Detection System --- p.87 / Chapter 10.1 --- Introduction --- p.87 / Chapter 10.2 --- System Architecture --- p.88 / Chapter 10.3 --- Results and Concluding Remarks --- p.91 / Chapter 11 --- Conclusion --- p.93 / References --- p.97
| Identifer | oai:union.ndltd.org:cuhk.edu.hk/oai:cuhk-dr:cuhk_319007 |
| Date | January 1992 |
| Contributors | Yip, Pak Ching., Chinese University of Hong Kong Graduate School. Division of Computer Science. |
| Publisher | Chinese University of Hong Kong |
| Source Sets | The Chinese University of Hong Kong |
| Language | English |
| Detected Language | English |
| Type | Text, bibliography |
| Format | print, ii, 100 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 0.0111 seconds