利用空间抽样理论的遥感影像分类结果精度评价方法.pdf

第 33卷 第 7 期 计算机应用与软件 Vol .33 No . 7 2016年 7 月 Computer Applications and Software Jul . 2016 利用空间抽样理论的遥感影像分类结果精度评价方法 黄 冬 梅 陈 珂 王 振 华 刘 爽 (上海海洋大学信息学院上海2〇136) 摘 要 遥感影像分类结果的准确性对于遥感信息的应用分析有着重要的影响。传统抽样方式下的遥感影像分类结果精度评价 方法受样本量及空间布局的影响，存在效率低和信息冗余等问题。利用空间数据的相关性，将空间抽样理论应用于遥感影像分类结 果的精度评价，通过与传统抽样方法比较，发现空间抽样方法应用于遥感影像分类结果的精度评价不仅降低了数据冗余，同时提高 了精度评价的检验效率和准确性。 关键词 遥感分类精度 评 价 抽 样 理 论 误 差 矩 阵 中图分类号 TP751.1 文献标识码 A D 01:10.3969/j. issn. 1000-386x .2016.07.044 A C C U R A C Y A S S E S S M E N T M E T H O D F O R R E M O T E S E N S I N G I M A G E C L A S S I F I C A T I O N R E S U L T S B A S E D O N S P A T I A L S A M P L I N G T H E O R Y Huang Dongmei Chen Ke Wang Zhenhua Liu Shuang (School of Information ，Shanghai Ocean University ，Shanghai 2 0 1 3 0 6 ，China) Abstract The accuracy of classification results of remote sensing images has an important effect on the application and analysis of remote sensing information. The accuracy assessment method of classification results of remote sensing image based on traditional sampling mode is affected by the sample size and spatial layout，and has the problems of lowefficiency and information redundancy ，etc. In this paper , by using the correlation of spatial data , we applied the spatial sampling theory to accuracy assessment sensing image，through comparison it with traditional sampling method，we found that the application of spatial sampling methods in accuracy assessment of the results not only reduces the data redundancy，it also improves the efficiency and accuracy of Keywords Remote sensing classification Accuracy assessment Sampling theory Error matrix