By Topic

The use of high-resolution imagery for identification of urban climax forest species using traditional and rule-based classification approach

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

3 Author(s)
Sugumaran, R. ; Dept. of Geogr., Univ. of Northern Iowa, Cedar Falls, IA, USA ; Pavuluri, M.K. ; Zerr, D.

Columbia, Missouri, is one of the fastest growing cities in the United States. The rapid urbanization is jeopardizing the city's urban climax forests, which are defined as any woodland community of more than 7.53 ha dominated by plant species such as oak and hickory. The increasing urban pressure places heavy demands on city planners to seek better management approaches to ensure that these plant species, which are native to Missouri, are protected even when threatened by new developments. Traditionally, planners are identifying these areas by surveys, which are costly, time consuming, and conducted on an as-needed basis. The current study is to test the feasibility of high-resolution satellite and airborne imagery for the identification of these forests and to assist planners in preserving them. In order to identify these climax forests, 4-m multispectral IKONOS images for April and August 2000 and 25-cm and 1-m multispectral airborne photographs for September and November 2001 were acquired and used in this study. These images were classified using a traditional classifier [maximum likelihood (ML)] and a rule-based classifier [classification and regression tree (CART)]. Results show that the images taken in September using the ML classifier are more useful in identifying the tree species in the study area. Among the spatial resolutions used, 1-m images proved to be optimal in recognizing trees and at the same time minimizing shadows.

Published in:

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