Identification of high temperature targets in remote sensing imagery based on factor analysis

摘要

Identification of high temperature targets has great significance to environmental monitoring, disaster warning, resources investigation, and so on. It is also an important basis for the temperature inversion of high temperature targets. Factor analysis starts from the similarity matrix of variables or samples. It sums the multiple variables or multiple samples up to a few factors via performing correlation analysis on them. It can extract information with the least amount of information loss. R-mode factor analysis is conducted to ETM+ remote sensing imagery to get the relationship among band variables. The fire factor, which has indicative significance for the high temperature targets, is confirmed on the basis of factor loading matrix. The mixture tuned matched filtering method is adopted in this article to use factor scores to realize high temperature target recognition. The identification precision reaches 95% in the field confirmation. (C) The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.