华东平原区居民地遥感特征分析及提取方法研究  被引量:2

Research on Remote Sensing Feature Analysis and Extraction of Residential Area in the East China Plain

在线阅读下载全文

作  者:苑惠丽[1] 余艳玲 李吉英[3] 陈文君 Yuan Huili;Yu Yanling;Li Jiying;Chen Wenjun(Architectural Engineering Institute,Jinling Institute of Technology,Nanjing 211169,China;Guangxi Key Laboratory of Aquatic Genetic Breeding and Healthy Aquaculture,Guangxi Institute of Fisheries,Nanning 530021,China;Department of architectural Engineering,Binzhou University,Binzhou 256603,China)

机构地区:[1]金陵科技学院建筑工程学院,江苏南京211169 [2]广西水产科学研究院广西重点实验室,广西南宁530021 [3]滨州学院建筑工程系,山东滨州256600

出  处:《城市勘测》2021年第1期94-100,共7页Urban Geotechnical Investigation & Surveying

基  金:江苏省自然科学基金青年基金项目(BK20170117)。

摘  要:针对单纯基于光谱知识的居民地信息提取易受混合像元、同物异谱和异物同谱现象引起“椒盐现象”的问题,采用面向对象的影像分析方法。该方法通过最佳指示因子和最大面积法确定分割波段及分割尺度,综合利用居民地的光谱和几何特征,构建了平原区居民地信息的提取模式。基于安徽省涡阳县和江苏省盐都区居民地信息提取结果表明:该方法可以快速有效地提取出遥感影像上的居民地信息,还能够有效避免了“椒盐现象”,研究结果对于准确地确定华东平原区居民地面积及其分布情况具有重要的实际应用价值。In order to solve the problem of“pepper and salt phenomenon”caused by mixed pixel,different spectrum in same object and same spectrum in different objects in extracting residential information only based on spectral knowledge,an object-oriented image analysis method was adopted.In this method,the optimal indicator factor and the maximum area method were used to determine the segmentation bands and the segmentation scale.The results of residential information extraction of Woyang County in Anhui Province and Yandu District in Jiangsu Province show that the method can quickly and efficiently be used to extract the residents of remote sensing image information,which also can effectively avoid the“salt and pepper phenomenon”.The study has an important practical application value to accurately determine the distribution of residents in east China area.

关 键 词:内陆居民地 沿海居民地 遥感 提取 

分 类 号:P236[天文地球—摄影测量与遥感] TP753[天文地球—测绘科学与技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象