论文部分内容阅读
影像分割是面向对象的分类思想应用于遥感影像信息自动提取的基础,纹理是影像的基本特征,是影像分析、理解和识别的重要信息,纹理特性的有效表达和抽取,是基于纹理影像分割的前提。本文系统概述了近年来各类文献中使用频率较高的基于纹理的遥感影像分割方法,并以基于统计的方法、基于纹理结构的方法、基于模型的方法和基于空间/频率的方法四种基本类型为主线,对每一类分割方法的特点进行了分析和总结,在此基础上指出了基于纹理特征遥感影像分割的研究趋势。
Image segmentation is the basis of object-oriented classification theory applied to the automatic extraction of remote sensing image information. Texture is the basic feature of image, which is the important information of image analysis, understanding and recognition. The effective expression and extraction of texture features is based on texture image segmentation premise. This paper systematically summarizes the texture-based remote sensing image segmentation methods which are frequently used in various literatures in recent years, and systematically summarizes the four basic methods based on statistical methods, texture-based methods, model-based methods and spatial / frequency based methods Type of the main line, the characteristics of each class of segmentation methods were analyzed and summarized, based on this, pointed out the texture features of remote sensing image segmentation research trends.