Cart (Loading....) | Create Account
Close category search window
 

Forest Cover Classification With MODIS Images in Northeastern Asia

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)
Anmin Fu ; State Key Lab. of Remote Sensing Sci., Beijing Normal Univ., Beijing, China ; Guoqing Sun ; Zhifeng Guo ; Dianzhong Wang

The forest ecosystem in the Northeastern Asia (NEA) has been undergoing dramatic changes because of forest fires and massive logging. MODIS (Moderate Resolution Imaging Spectroradiometer) vegetation indexes product MOD13A1 from 2000 to 2006 were re-composited for forest mapping circa year 2000 in the region. The study region was divided into four sub-regions with distinct natural climate regimes, and a TM/ETM+ scene was selected as a test site for each of the sub-regions. The process of mapping forest from MODIS data consists of two steps that follow the logic sequence of class definition. First, a 2-D Feature Space Grid Split (FSGS) algorithm was developed to identify forested areas by use of its dark object attributes. The producer and user accuracies of forest/non-forest mapping reached over 90% at test sites, and 72.22% and 88.26% comparing with the national LCLU map in the areas within China. The forested areas were then stratified into four forest types by a decision tree classifier from temporal MODIS data for each of the sub-regions. The forest classification was validated for pure forests using the results from TM/ETM+ classification. The comparison showed high producer and user accuracies: 86.78% and 91.14% for evergreen needle forest, 90.6% and 92.4% for deciduous needle forest, and 82.99% and 97.19% for deciduous broadleaf forest, although confusion existed between mixed forest and deciduous broadleaf forest. The forest map was also compared with MODIS land cover and Global Land Cover 2000 (GLC2000) products.

Published in:

Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of  (Volume:3 ,  Issue: 2 )

Date of Publication:

June 2010

Need Help?


IEEE Advancing Technology for Humanity About IEEE Xplore | Contact | Help | Terms of Use | Nondiscrimination Policy | Site Map | Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest professional association for the advancement of technology.
© Copyright 2014 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.