| | |
Summary: SEGMENTATION OF RANGE IMAGES FOR
MODELING OF LARGE OUTDOOR SCENES
Project in Lieu of Thesis
For
Masters Degree
The University of Tennessee, Knoxville
Hari Kishan Iddamsetty
December 2003
1
Abstract
In analysis of the objects in images it is essential that we can distinguish between the
objects of interest and "the rest." This latter group is also referred to as the background.
The techniques that are used to find the objects of interest are usually referred to as
segmentation techniques - segmenting the foreground from background. In this paper we
propose to develop a set of data processing algorithms for segmenting vertical 2D range
scans obtained while driving on public roads under normal traffic conditions. The aim in
doing this project is to explore different techniques used for segmenting the range images,
the most common being the thresholding technique. It is important to understand that
there is no universally acceptable segmentation technique that will work on all images
and that no segmentation technique is perfect. The goal however is to come up with a
|
