Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/78595
Title: Land cover classification using satellite optical and radar image fusion
Authors: Liu, Yunwei
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Antennas, wave guides, microwaves, radar, radio
Issue Date: 2019
Abstract: Synthetic Aperture Radar (SAR) is an advanced radar imaging technology that is able to produce high-resolution imagery of the Earth's surface in all weather. Other systems such as optical camera could also provide high-resolution land mapping images, but they could be affected by adverse weather conditions, like clouds and haze. Compared to optical images, SAR images usually have lower resolution but better land type features. This project is to conduct an image fusion study to combine the good features of SAR images and optical images to produce a better imagery result with both land classification effects from SAR images and earth surface details from optical images. At the beginning, for the SAR image, K-means image segmentation method will be used. Because different segmentation methods, such as watershed segmentation, L*A*B segmentation, Chan-Vese segmentation and K-means segmentation, have been proved that K-means segmentation is the best choice for this project, through the similar projects done by professor. Moreover, after using K-means, another method called, K-nearest Neighbors algorithm (KNN), a kind of machine learning, has been used to compare these two methods. Secondly, image filtering method will be used in this project. There are also many filtering methods. For example, spatial filtering, Wiener filtering and morphological filtering. There comes a summary by other students’ projects that the morphological filtering will give a better display. At last, image fusion results for the segmented SAR image and optical image are analyzed.
URI: http://hdl.handle.net/10356/78595
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
MSc Dissertation (LIU Yunwei)_v7.pdf
  Restricted Access
9.88 MBAdobe PDFView/Open

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.