Queen's University - Utility Bar

QSpace at Queen's University >
Graduate Theses, Dissertations and Projects >
Queen's Graduate Theses and Dissertations >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1974/5107

Title: Generation and Optimization of Local Shape Descriptors for Point Matching in 3-D Surfaces
Authors: Taati, BABAK

Files in This Item:

File Description SizeFormat
Taati_Babak_200908_PhD.pdf1.29 MBAdobe PDFView/Open
Keywords: computer vision
range data
object recognition
local shape descriptor
point matching
pose estimation
pose acquisition
point cloud
satellite tracking
range image processing
range image
computational geometry
object identification
point correspondence
feature selection
Variable-Dimensional Local Shape Descriptors
genetic algorithm
simulated annealing
forward feature selection
multivariate features
subset selection
local properties
dense stereo
feature matching
machine learning
learning phase
Issue Date: 2009
Series/Report no.: Canadian theses
Abstract: We formulate Local Shape Descriptor selection for model-based object recognition in range data as an optimization problem and offer a platform that facilitates a solution. The goal of object recognition is to identify and localize objects of interest in an image. Recognition is often performed in three phases: point matching, where correspondences are established between points on the 3-D surfaces of the models and the range image; hypothesis generation, where rough alignments are found between the image and the visible models; and pose refinement, where the accuracy of the initial alignments is improved. The overall efficiency and reliability of a recognition system is highly influenced by the effectiveness of the point matching phase. Local Shape Descriptors are used for establishing point correspondences by way of encapsulating local shape, such that similarity between two descriptors indicates geometric similarity between their respective neighbourhoods. We present a generalized platform for constructing local shape descriptors that subsumes a large class of existing methods and allows for tuning descriptors to the geometry of specific models and to sensor characteristics. Our descriptors, termed as Variable-Dimensional Local Shape Descriptors, are constructed as multivariate observations of several local properties and are represented as histograms. The optimal set of properties, which maximizes the performance of a recognition system, depend on the geometry of the objects of interest and the noise characteristics of range image acquisition devices and is selected through pre-processing the models and sample training images. Experimental analysis confirms the superiority of optimized descriptors over generic ones in recognition tasks in LIDAR and dense stereo range images.
Description: Thesis (Ph.D, Electrical & Computer Engineering) -- Queen's University, 2009-09-01 11:07:32.084
URI: http://hdl.handle.net/1974/5107
Appears in Collections:Queen's Graduate Theses and Dissertations
Department of Electrical and Computer Engineering Graduate Theses

Items in QSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


  DSpace Software Copyright © 2002-2008  The DSpace Foundation - TOP