摘要
有效利用TM影像中云层的光谱和形状特征,提出了一种基于最大类间方差的云层自动检测方法。该方法首先利用云层和雪区的波谱特性差异,基于最大类间方差法实现云层的阈值化分割;然后利用粗分云层的形状特征做进一步判定分析,最终实现云层的提取。实验表明,与传统的人工阈值方法相比,本方法可以有效地从TM影像中检测出云层,降低人工参与程度。
In this paper we propose a method for automatic cloud detection, which employs both spectral and shape features. This method includes two main steps. First, based on the different spectral features of clouds and snow, an otsu-based method is used for threshold segmentation of a TM Image. Then, clouds are successfully extracted by discriminant analysis using the shape feature. Experiments indicate that as compared to the traditional threshold-based methods, the proposed method can effec tively detect clouds with an improved automatization level.
出处
《武汉大学学报（信息科学版）》
EI
CSCD
北大核心
2014年第2期234-238,共5页
Geomatics and Information Science of Wuhan University
基金
国家科技支撑计划资助项目(2011BAK07B02)
山东理工大学自主科研基金资助项目(103282)~~
