TY - CONF
T1 - Classification of Landsat remote sensing images by a fuzzy unsupervised clustering algorithm
AU - Shih, Frank Y.
AU - Chen, Gwotsong P.
N1 - Funding Information:
During the last three decades, the geographic information system (GIS) has been greatly developed in many areas such as urban planning, environmental supervising, water resources \[8, 10\], wildlife habitat protection \[6\], and land property management \[12\].I n the past, researchers working on the GIS spent a great deal of time collecting geographic data, and then converting the data into a computer point by point by using a digitizer. The procedures are subjective and time-consuming. As new hardware and This work was supported by the New Jersey Institute of Technology under Grant 421770.
Copyright:
Copyright 2008 Elsevier B.V., All rights reserved.
PY - 1992
Y1 - 1992
N2 - Due to the low resolution of Landsat images and the multiplicity of the terrain, it is improper to classify each pixel in a Landsat image to one of land cover types by using the conventional remote sensing classification methods. The concept of fuzzy sets provides a flexible approach to resolve this problem. This paper presents a new two-pass mode unsupervised clustering algorithm incorporated with the underlying fuzzy theory. In the first pass the mean vectors representing the geographic attributes or the land cover types are derived. The second pass is based on the fuzzy theory. That is the mean vectors obtained are used to generate a membership function. The grade of memberships for each pixel with respect to various land cover types is computed according to the distance from the pixel to all the clusters' mean vector.
AB - Due to the low resolution of Landsat images and the multiplicity of the terrain, it is improper to classify each pixel in a Landsat image to one of land cover types by using the conventional remote sensing classification methods. The concept of fuzzy sets provides a flexible approach to resolve this problem. This paper presents a new two-pass mode unsupervised clustering algorithm incorporated with the underlying fuzzy theory. In the first pass the mean vectors representing the geographic attributes or the land cover types are derived. The second pass is based on the fuzzy theory. That is the mean vectors obtained are used to generate a membership function. The grade of memberships for each pixel with respect to various land cover types is computed according to the distance from the pixel to all the clusters' mean vector.
UR - http://www.scopus.com/inward/record.url?scp=1842453092&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=1842453092&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:1842453092
SP - 314
T2 - First International Conference on Fuzzy Theory and Technology Proceedings, Abstracts and Summaries
Y2 - 14 October 1992 through 18 October 1992
ER -