Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/13713
Title: Extraction of man-made features from high resolution satellite imagery
Authors: SOWMYA SELVARAJAN
Keywords: remote sensing, image processing, wavelets, IKONOS
Issue Date: 20-Feb-2004
Source: SOWMYA SELVARAJAN (2004-02-20). Extraction of man-made features from high resolution satellite imagery. ScholarBank@NUS Repository.
Abstract: This thesis presents a study on an application-based remote sensing technique for the extraction of man-made features from high spatial resolution satellite imagery. The need to detect man-made features from imagery is necessary of the day in order to detect the change in an urban-environment and much research has been done to identify man-made features both automatically and semi-automatically. Local changes or variations of the intensity of the imagery (such as edges and corners) are important in image processing and pattern recognition to identify object boundaries. This research combines the use of several image processing techniques to better identify man-made features. Wavelet analysis is employed to help enhance the local intensity variation. The Canny edge detector, with its double thresholding algorithm is used in conjunction with wavelet analysis to form edge-maps. Shape matching plays an important role in identifying objects of interest in the edge maps. It is found that a simple but efficient template matching approach can successfully extract the target object from the edge maps The proposed technique is applied on a one-meter panchromatic IKONOS image of the part of the highly urbanized Singapore city.
URI: http://scholarbank.nus.edu.sg/handle/10635/13713
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
SelvarajanS.pdf1.09 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

286
checked on Dec 11, 2017

Download(s)

204
checked on Dec 11, 2017

Google ScholarTM

Check


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