Application of random sets to model uncertainties of natural entities extracted from remote sensing images |
| |
Authors: | Xi Zhao Alfred Stein Xiaoling Chen |
| |
Institution: | (1) Earth Observation Science Department, International Institute for Geo-Information Science and Earth Observation (ITC), Hengelosestraat 99, 7500 AA Enschede, The Netherlands;(2) State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Luo Yu Road 129, Wuhan, 430079, China;(3) The Key Laboratory of Poyang Lake Wetland and Watershed Research, Jiangxi Normal University, Ziyang Road 99, Nanchang, China |
| |
Abstract: | Remotely sensed images as a major data source to observe the earth, have been extensively integrated into spatial-temporal
analysis in environmental research. Information on spatial distribution and spatial-temporal dynamic of natural entities recorded
by series of images, however, usually bears various kinds of uncertainties. To deepen our insight into the uncertainties that
are inherent in these observations of natural phenomena from images, a general data modeling methodology is developed to embrace
different kinds of uncertainties. The aim of this paper is to propose a random set method for uncertainty modeling of spatial
objects extracted from images in environmental study. Basic concepts of random set theory are introduced and primary random
spatial data types are defined based on them. The method has been applied to dynamic wetland monitoring in the Poyang Lake
national nature reserve in China. Four Landsat images have been used to monitor grassland and vegetation patches. Their broad
gradual boundaries are represented by random sets, and their statistical mean and median are estimated. Random sets are well
suited to estimate these boundaries. We conclude that our method based on random set theory has a potential to serve as a
general framework in uncertainty modeling and is applicable in a spatial environmental analysis. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|