遥感应用分析中影像分割方法

影像分割是数字图像模式识别的基础, 是实现从影像上进行目标计算机自动提取的第一步工作, 在遥感应用分析中具有重要意义。近年来, 随着大量的高质量的高分辨率遥感影像出现, 其相关应用迫切需要有效的、考虑其高分辨率影像特点的影像分割方法。但由于高分辨率遥感影像本身的一些特点, 遥感应用分析中传统常用的分割方法难以达到满意的效果。对遥感应用分析中的影像分割方法进行了总结和分析, 并结合高分辨率遥感影像的特点, 分析了高分辨率遥感影像分割的技术难点, 说明了基于像素的传统影像分割方法的局限性, 着重阐述了数学形态学、面向对象分析等方法能更充分地利用影像中目标的色调、纹理、几何等属性, 因此在高分辨率遥感影像分割方面更具有优势。最后, 探讨了遥感应用分析中影像分割方法的发展趋势。

The Methods of Image Segmentation on Application and Analysis of Remote Sensing Images

Image segmentation is the basis of pattern recognition and the first step for extracting the objects automatically from image using computer.This is significant for the application and analysis of remote sensing images.These years,with an increasing amount of high resolution imagery of high quality provided,some effective segmentation methods are required for the related geoscience applications of high resolution images.However,for the unique characteristics of high resolution image,classic image segmentation methods cannot be satisfied.The methods for segmentation using in the application and analysis of remote sensing images are overviewed and analyzed.Considering the characteristics of high resolution image,the technical difficulties of segmentation for high resolution remote sensing image are analyzed,and the problems of the traditional pixel-based methods are given.Afterward,mathematic morphology method,OOA(Object Oriented Analysis) and some other methods are illustrated.These methods,which have more advantages for high resolution image segmentation,can make good use of the objects' attributes such as tone,texture and geometry.Finally,the future development of image segmentation technology using in application and analysis of remote sensing images is put forward.