摘要
文章以遥感技术为基础,对某矿区1998年、2008年和2018年的遥感影像数据进行处理,将经过大气校正、几何校正、辐射校正、裁剪等预处理后的遥感影像导入ENVI软件中,采用最大似然法对其进行监督分类,并采用混淆矩阵对分类结果进行精度评定,得出的总体分类精度和Kappa系数表明本次分类结果精度较高,可用于该矿区土地复垦生态评估。对分类结果进行遥感动态监测,结果表明1998年至2008年间矿区土地破坏较为严重,2008年至2018年间被破坏土地逐渐恢复为耕地和居住用地,生态环境得到了较大改善,土地复垦工作效果较好,符合该矿区实际情况。
Based on remote sensing technology,this paper processes the remote sensing image data of a mining area in 1998,2008 and 2018,and imports the remote sensing image preprocessed by atmospheric correction,geometric correction,radiation correction,and cropping into ENVI software.The maximum likelihood device is used to supervise the classification,and the confusion matrix is used to evaluate the accuracy of the classification results.The overall classification accuracy and Kappa coefficient indicate that the classification results have high accurate and can be used for ecological assessment of land reclamation in this mining area.The remote sensing dynamic detection of the classification results showed that the land damage in the mining area was serious from 1998 to 2008,and the damaged land was gradually restored to cultivated land and residential land from 2008 to 2018.Meanwhile,the ecological environment has been greatly improved,and the effect of land reclamation is good,which is in line with the actual situation of the mining area.
作者
朱权
ZHU Quan(Shanghai Geotechnical Engineering Detecting Centre,Shanghai 200436,China)
出处
《地矿测绘》
2021年第2期7-11,共5页
Surveying and Mapping of Geology and Mineral Resources
关键词
遥感影像
数据预处理
监督分类
土地利用类型
remote sensing image
data preprocessing
supervised classification
land use type
