Repository logo
Log In(current)
  1. Home
  2. Colleges & Schools
  3. Graduate School
  4. Masters Theses
  5. Neural Network Processing of Satellite Imagery
Details

Neural Network Processing of Satellite Imagery

Date Issued
May 1996
Author(s)
Emge, Thomas
Advisor(s)
Grzegorz Kawiecki
Permanent URI
https://trace.tennessee.edu/handle/20.500.14382/60034
Abstract

In this study a neural computing approach is taken for the classification and land feature extraction of satellite imagery. The satellite data consists of multispectral Thematic Mapper recordings. The applied neural network is a three layer feedforward network with one hidden layer using the backpropagation learning paradigm. Several network configuration concerning data scaling and activation functions are examined. For a comparative study and validation of the neural network model, the maximum likelihood classifier and the k nearest neighbor classifier are used as statistical conventional classification techniques. The neural network is found to be superior in terms of overall performance to the conventional techniques. An accuracy assessment analyzes the classification results and gives a detailed picture about the advantages and weaknesses of each method.

 
Degree
Master of Science
Major
Aerospace Engineering
File(s)
Thumbnail Image
Name

Thesis96.E53.pdf

Size

11.94 MB

Format

Adobe PDF

Checksum (MD5)

fca35678b3f64b9fd1c4cb1da35aec50


University Libraries

1015 Volunteer Boulevard
Knoxville, TN 37996
865-974-4351

Map & Directions
Donate to the Libraries
  • About
  • John C. Hodges Society
  • Speaking Volumes magazine
  • Outreach
  • Directory
  • Employment
  • Policies
  • Library Intranet
University of Tennessee power T logo

The University of Tennessee, Knoxville
Knoxville, Tennessee 37996
865-974-1000

Events
A-Z
Apply
Privacy
Map
Directory
Give to UT
Accessibility

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science