By Topic

Pixel unmixing for urban environment monitoring using multi-temporal satellite images

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
$33 $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)
Yindi Zhao ; School of Environment Science & Spatial Informatics, China University of Mining and Technology, Xuzhou, China ; Huijian Du ; Peijun Du ; Yan Cai

Urban environment monitoring is one of the most important applications of Remote Sensing. In this paper, two images, acquired by Landsat-7 ETM+ on 14 September 2000 and Landsat-5 TM on 12 August 2005 respectively, are used to learn land-cover changes. The study area is within the round-city highway of Xuzhou city, China. Firstly, image registration and haze removal are performed. Then four endmembers, including vegetation, impervious surface, soil and water, are determined in the maximum noise fraction feature space. The spectral mixture analysis is conducted to the pre-processed images of two periods by means of Back-Propagation Neural Network algorithm, and the corresponding fraction images for each endmember are generated. Finally, the image differencing method is applied to the multi-temporal fraction images for monitoring urban land-cover changes according to defined suitable threshold values. The experimental results indicate that spectral mixture analysis algorithm is great potential for urban land-cover change detection.

Published in:

2010 18th International Conference on Geoinformatics

Date of Conference:

18-20 June 2010