Tao, Chenjun. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2008. / Includes bibliographical references (leaves 89-97). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgements --- p.iii / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Window-oriented Retargeting --- p.1 / Chapter 1.2 --- Abstraction Rendering --- p.4 / Chapter 1.3 --- Thesis Outline --- p.6 / Chapter 2 --- Related Work --- p.7 / Chapter 2.1 --- Video Migration --- p.8 / Chapter 2.2 --- Video Synopsis --- p.9 / Chapter 2.3 --- Periodic Motion --- p.14 / Chapter 2.4 --- Video Tracking --- p.14 / Chapter 2.5 --- Video Stabilization --- p.15 / Chapter 2.6 --- Video Completion --- p.20 / Chapter 3 --- Active Window Oriented Video Retargeting --- p.21 / Chapter 3.1 --- System Model --- p.21 / Chapter 3.1.1 --- Foreground Extraction --- p.23 / Chapter 3.1.2 --- Optimizing Active Windows --- p.27 / Chapter 3.1.3 --- Initialization --- p.29 / Chapter 3.2 --- Experiments --- p.32 / Chapter 3.3 --- Summary --- p.37 / Chapter 4 --- Multi-Style Abstract Image Rendering --- p.39 / Chapter 4.1 --- Abstract Images --- p.39 / Chapter 4.2 --- Multi-Style Abstract Image Rendering --- p.42 / Chapter 4.2.1 --- Multi-style Processing --- p.45 / Chapter 4.2.2 --- Layer-based Rendering --- p.46 / Chapter 4.2.3 --- Abstraction --- p.47 / Chapter 4.3 --- Experimental Results --- p.49 / Chapter 4.4 --- Summary --- p.56 / Chapter 5 --- Interactive Abstract Videos --- p.58 / Chapter 5.1 --- Abstract Videos --- p.58 / Chapter 5.2 --- Multi-Style Abstract Video --- p.59 / Chapter 5.2.1 --- Abstract Images --- p.60 / Chapter 5.2.2 --- Video Morphing --- p.65 / Chapter 5.2.3 --- Interactive System --- p.69 / Chapter 5.3 --- Interactive Videos --- p.76 / Chapter 5.4 --- Summary --- p.77 / Chapter 6 --- Conclusions --- p.81 / Chapter A --- List of Publications --- p.83 / Chapter B --- Optical flow --- p.84 / Chapter C --- Belief Propagation --- p.86 / Bibliography --- p.89

A new algorithm is proposed which uses the Hough Transform to recognize two dimensional objects independent of their orientations, sizes and locations. The binary image of an object is represented by a set of straight lines. Features of the straight lines, namely the lengths and the angles of their normals, their lengths and the end point positions are extracted using the Hough Transform. A data structure for the extracted lines is constructed so that it is efficient to match the features of the lines of one object to those of another object, and determine if one object is a rotated and/or scaled version of the other. Finally a generalized Hough Transform is used to match the end points of the two sets of lines. The simulation experiments show good results for objects with significant linear features .

Image processing systems used in Vision Assisted Dimensional Inspection usually output a set of boundary pixels representing the part edges. This boundary information must be divided into several subsets representing the various edges of the actual object, so that comparisons with the nominal part can be made. The purpose of this project is to devise a method to divide the set of pixels obtained from the image processing system into subsets of pixels. Each of these subsets represent an edge in the contour of the actual object. This method must also detect transition points between the adjacent features. This project addresses only planar contours which are composed of straight and circular edges. Two new algorithms have been developed, the first algorithm detects the transition points involving straight edges and the second algorithm finds the transition points when circular features are involved. In addition, the measured features are also matched with their nominal counterparts. The performance of these algorithms are demonstrated by simulated as well as images from the vision system.

Image retrieval via a structured query is explored in Johnson, et al. [7]. The query is structured as a scene graph and a graphical model is generated from the scene graph's object, attribute, and relationship structure. Inference is performed on the graphical model with candidate images and the energy results are used to rank the best matches. In [7], scene graph objects that are not in the set of recognized objects are not represented in the graphical model. This work proposes and tests two approaches for modeling the unrecognized objects in order to leverage the attribute and relationship models to improve image retrieval performance.

The X Window System is an industry-standard software system which facilitates programmers to develop portable graphical user interfaces. This thesis describes an image processing tool developed under the X Window System. A multiwindow image display software with image editing and improvement functions is developed. The software has four modules: environment generation, image creation, image editing and image improvement. The environment generation module creates working windows, scrollbars, dialogbox and pulldown menu buttons, and tracks mouse cursor positions. The working windows are three adjacent windows allowing display of three different images simultaneously. The dialogbox provides an interface between the user and the program, such as input new image and parameters. The pulldown menus offer various selections of image processing functions. A pair of scrollbars are also added to allow users to move the magnified image up, down, left and right so that the full picture can be viewed. The image creation module can build colormap, load image data file, convert pixel values to screen color values, create image, and display image on the screen of a workstation. The program can read either sun.rasterfile format or a plain data file. If a plain data file is detected, the software can transform it to sun.rasterfile by adding an appropriate header and a colormap. There are two kinds file saving features: screen capture and store. The screen capture allows the user to save that part of image displayed on the screen. The store function saves the entire image which may be either the screen size or bigger size image (e.g. merged or zoomed image). The image editing module is equipped with the functions for zooming (in or out) , merging, rotating and restoring images. The merge function constructs a new image based on the user selected or input image from the dialogbox. The rotation center of an image can be any point selected by user's clicking mouse button, and the rotation angle is supplied by user in the dialogbox. The image improvement module consists of some image point transformation and image enhancement functions. This software package is easier to use than existing tools for image processing. It has been used in the image processing projects and related educational purposes. The software provides a framework and can be easily extended to other potential applications.

Abstract not available

For thesis abstract select View Thesis Title, Contents and Abstract

Abstract not available

Abstract not available

In Australia, in recent years there has been increasing demand for more streamlined lodgement of cadastral plans and for their later dissemination. There are a number of approaches to meeting this demand, one of which is developed in detail in this dissertation. The current status of digital lodgement and Digital Cadastral Databases (DCDB) throughout Australia and New Zealand is reviewed. Each of the states and territories in Australia and also New Zealand are examined, looking at the process involved in the lodgement of survey plans and the state of the DCDB in each jurisdiction. From this examination the key issues in digital lodgement and dissemination are extracted and a needs analysis for an Australia-wide generic system is carried out. This needs analysis is directed at technological change allied with sound cadastral principles. Extensible Markup Language (XML) is considered for the storage and transport of all the required data and to facilitate the dissemination of information over the Internet. The benefits of using XML are comprehensive, leading to its selection and the use of related technologies LandXML, Extensible Structured Query Language (XSQL) and Extensible Stylesheet Language (XSL). Vector graphics are introduced as the means to display plans and maps on the Internet. A number of vector standards and Web mapping solutions are compared to determine the most suitable for this project. A new standard developed by the World Wide Web Consortium (W3C), Scalable Vector Graphics (SVG), is chosen. A prototype Web interface and the underlying database and Web server were developed using Oracle as the database and Apache as the Web server. Each aspect of the development is described, starting with the installation and configuration of the database, the Web server and the XSQL servlet. Testing was undertaken using LandXML cadastral data and displaying plans using SVG. Both Internet Explorer and Mozilla were trialled as the Web browser, with Mozilla being chosen because of incompatibilities between Internet Explorer, LandXML and SVG. An operational pilot was created. At this stage it requires manual intervention to centre and maximise a plan in the display area. The result indicates that an automated system is feasible and this dissertation provides a basis for further development by Australian land administration organisations.