面向对象的遥感影像分类研究  

作　　者：管珍[1] 曹广超[1] 易俊柱[1] 

机构地区：[1]青海师范大学,西宁810008

出　　处：《科技创新导报》2010年第34期8-10,12,共4页Science and Technology Innovation Herald

摘　　要：在基于传统的遥感影像分类方法的基础上,结合面向对象分析理论与方法,提出了面向对象的遥感影像的分类方法,通过实验分析探讨了面向对象影像分类的关键技术。包括多尺度的分割,分类器的建立,包括最近邻分类和模糊聚类分类。实验表明,面向对象的分类方法较传统基于像素分类法有较高的精度,具有很大的发展潜力。Based on the traditional method of remote image,composed with the analysis theories and method of object-oriented classification,this text pointed out and discussed the key skills of object-oriented classification by experimental analysis,which including multi-scale segmentation,the built of classification,the nearest neighbor classification and fuzzy clustering classification.Experiment claimed that,compared with the traditional image element-based analysis method,the object-oriented classification has a better accuracy and a potential developing future.

关 键 词：面向对象的影像分类 图像分割 分类器 尺度 

分 类 号：TP753[自动化与计算机技术—检测技术与自动化装置]