Generation and Optimization of Local Shape Descriptors for Point Matching in 3-D Surfaces

Generation and Optimization of Local Shape Descriptors for Point Matching in 3-D Surfaces

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 th...

Full description

Bibliographic Details
Main Author: Taati, BABAK
Other Authors: Queen's University (Kingston, Ont.). Theses (Queen's University (Kingston, Ont.))
Format: Others
Language:en
en
Published: 2009
Subjects:
computer vision
range data
object recognition
tracking
local shape descriptor
point matching
pose estimation
pose acquisition
3-D
3D
point cloud
satellite tracking
optimization
range image processing
range image
RANSAC
registration
alignment
surface
computational geometry
detection
localization
model-based
object identification
point correspondence
feature selection
Variable-Dimensional Local Shape Descriptors
VD-LSD
LSD
genetic algorithm
simulated annealing
forward feature selection
multivariate features
subset selection
local properties
LIDAR
dense stereo
stereo
precision
feature matching
machine learning
training
learning phase
preprocessing
Online Access:http://hdl.handle.net/1974/5107

Internet

http://hdl.handle.net/1974/5107

Similar Items