Integration of image segmentation and edge detection techniques for road extraction from high-resolution images

Pao Yue-kong Library Electronic Theses Database

Integration of image segmentation and edge detection techniques for road extraction from high-resolution images

 

Author: Sun, Bo
Title: Integration of image segmentation and edge detection techniques for road extraction from high-resolution images
Degree: M.Sc.
Year: 2008
Subject: Hong Kong Polytechnic University -- Dissertations.
Roads -- Location -- Remote sensing.
Image processing -- Digital techniques.
Geomatics.
Department: Dept. of Land Surveying and Geo-Informatics
Pages: x, 65 leaves : ill. (some col.) ; 30 cm.
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b2232332
URI: http://theses.lib.polyu.edu.hk/handle/200/3793
Abstract: As the development of remote sensing technologies, information extraction from high spatial resolution satellite images became research focus of data acquiring and image recognition areas. This dissertation looks back upon the previous methods of road extraction with analysis and comparison. Generalized the thoughts of seeds tracking and edge detection, it proposes a method which can obtain outlines of roads. First, some road seed points are chosen to extract crude roads. Then, according to result of edge detection, line detection and linear fitting methods are used to get the final result. The experimental tasks of this research include: 1. To analyze road characteristics in high spatial resolution images and preprocess images by contrast enhancement. 2. To study image clustering and seeds tracking method to get a crude road image, then improve the crude road image by post-processing. 3. On the basis of the crude road extraction, following tasks are to use edge detection algorithm to get the edges of roads, and to code for line detection and linear fitting algorithm which are based on Hough transform. According to the experiments, it is proved that the proposed integrated method is effective for extracting outlines of urban straight roads or main roads in high spatial resolution satellite images. The method can also be extended to extract nonlinear roads based on the concept of changing line detection algorithm to curve detection algorithm. The dissertation with the contents of research work is helpful and has great effect on the development of extracting road and other linear features semi-automatically or automatically from high-resolution satellite images.

Files in this item

Files Size Format
b22323326.pdf 3.718Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

     

Quick Search

Browse

More Information