By Topic

Multitemporal land use and land cover classification of urbanized areas within sensitive coastal environments

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
O'Hara, C.G. ; Georesources Inst., Mississippi State Univ., MS, USA ; King, J.S. ; Cartwright, J.H. ; King, R.L.

In the presented methodology, multitemporal Landsat images were used to develop enhanced information about complex assemblages of vegetation and patterns of seasonal land cover variability, thereby facilitating improved land use and land cover (LULC) classification of urbanized areas among sensitive environments along the Mississippi Gulf Coast. For Landsat-5 and Landsat-7 images acquired for leaf-off and leaf-on conditions for 1991 and 2000, exploratory spectral analyses and field studies were conducted to detect and analyze patterns of spectral variability in land cover observed in the multitemporal image data. Patterns were identified of seasonal spectral data changes associated with seasonal vegetation changes for known land cover and land use types, thus characterizing patterns of seasonal LULC thematic change for the area. Detected seasonal variability for known land use and land cover types were used to develop formal classification rules based upon a thematic-change logic table. An image subset area based on United States Geological Survey (USGS) 1:24000 quadrangles was used to develop a class-learning area within which unsupervised classification results were grouped into thematic classes. Signature files from the unsupervised classification results were applied to classify the balance of the study area. Individual images were classified for leaf-off and leaf-on conditions and thematic-change analyses were conducted. The formal class rules based on thematic-change logic were applied resulting in a classification that provided a level one accuracy exceeding 90% and a level two accuracy exceeding 85%.

Published in:

Geoscience and Remote Sensing, IEEE Transactions on  (Volume:41 ,  Issue: 9 )