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。
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 low efficiency and information redundancy,etc. In this paper,by using the correlation of spatial data,we applied the spatial sampling theory to accuracy assessment of the classification results of remote 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 the test as well.
出处
《计算机应用与软件》
CSCD
2016年第7期190-194,242,共6页
Computer Applications and Software
基金
国家自然科学基金项目(61272098)
国家重点基础研究发展计划项目(2012CB316200)
上海市自然科学基金项目(13ZR1455800)
上海高校优秀青年培养项目(B-5409-11-0012)
海洋赤潮灾害立体监测技术与应用国家海洋局重点实验室开放研究基金课题(MATHAB201307)
关键词
遥感分类
精度评价
抽样理论
误差矩阵
Remote sensing classification
Accuracy assessment
Sampling theory
Error matrix
