检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:白方铄 马骁[1] 杨永均[1] 巩人杰 BAI Fangshuo;MA Xiao;YANG Yongjun;GONG Renjie(Engineering Research Center for Mine Ecological Restoration of Ministry of Education,China University of Mining and Technology,Xuzhou 221116,China)
机构地区:[1]中国矿业大学矿山生态修复教育部工程研究中心,江苏徐州221116
出 处:《测绘与空间地理信息》2024年第5期27-30,共4页Geomatics & Spatial Information Technology
基 金:国家自然科学基金项目(41807515);内蒙古自治区重大科技计划专项项目(2020GG0008)资助。
摘 要:传统的单机遥感影像处理模式效率低,难以满足对全球任意地区矿山土地覆被快速分类的需求。本文基于遥感云计算平台,开发了三参数阈值分割分类方法,并选取全球9处露天矿山完成了验证。结果表明:1)NDVI、NDWI和NDBI 3个遥感指数是矿山土地覆被的敏感性指标,可有效区分矿山土地覆被类型;2)基于遥感云计算平台和三参数阈值分割方法可以实现全球任意矿山的土地覆被快速分类,三参数阈值分割方法的总体精度高于监督分类的总体精度;3)三参数阈值分割方法分类结果的边界清晰,分类准确度的排序为裸土>森林>水体>裸岩>灌草,分割阈值对不同地球气候带的矿山具有适应性。总体来看,该方法可以有效实现不同地区矿山土地覆被的快速分类,为实现全球矿山土地覆被整体监测提供一种新的方法。Thetraditional single-machine remote sensing image processing mode has low efficiency and is difficult to meet the demand of rapid classification of mine land cover in any region of the world.Based on the remote sensing cloud computing platform,this paper developed a three-parameters threshold segmentation and classification method,and selected 9 open-pit mines worldwide to complete the verification.The results show that:1)NDVI,NDWI and NDBI are sensitive indexes of mine land cover,which can effectively dis-tinguish mine land cover types.2)Based on remote sensing cloud computing platform and three-parameters threshold segmentation method,the rapid classification of land cover of mines across the world can be realized.The overall accuracy of three-parameters threshold segmentation method is higher than that of supervised classification.3)The classification results of the three-parameters threshold segmentation method have clear boundaries,and the classification accuracy order is bare soil>forest>water>bare rock>shrub.The segmentation threshold is adaptable to mines in different climatic zones of the earth.In general,the three-parameters threshold segmentation method based on remote sensing cloud computing platform can effectively realize the rapid classification of mine land cover in different regions,which can provide a new method for the global monitoring of mine land cover in the future.
分 类 号:P209[天文地球—测绘科学与技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.222