基于RapidEye影像的农村居民地遥感监测——以江西省泰和县为例

发布时间：2018-12-15 06:57

【摘要】：农村居民地遥感信息获取对于监测农村居民地时空变化、服务"三农"和国土资源管理具有重要意义。以Rapid Eye卫星影像数据为数据源,江西省泰和县为研究区,利用最大似然法进行居民地等土地覆盖类别的分类提取与精度评价及分析。结果表明:分类总体精度达到84.33%,其中农村居民地的制图精度和用户精度分别为76.01%和82.28%,与第二次全国土地调查中的居民地数据对比,其一致性达到71.0%。结合实地验证,对本分类精度的误差原因进行分析。本研究表明利用5 m分辨率的Rapid Eye影像进行县级农村居民地监测是可行的,可为后续同类研究提供技术参考。
[Abstract]:The acquisition of remote sensing information for rural residents is of great significance in monitoring the spatial and temporal changes of rural residents, serving the "three rural areas, farmers" and land and resources management. Taking Rapid Eye satellite image data as data source and Taihe County in Jiangxi Province as the research area, the classification, extraction, accuracy evaluation and analysis of land cover categories such as land cover were carried out by using maximum likelihood method. The results show that the overall accuracy of classification is 84.33, and the mapping accuracy and user accuracy of rural land are 76.01% and 82.28% respectively, which are compared with the data of the second national land survey. The consistency reached 71.0. Combined with field verification, the error causes of the classification accuracy are analyzed. This study shows that it is feasible to use 5 m resolution Rapid Eye image to monitor rural residents at county level, which can provide a technical reference for the follow-up similar research.
【作者单位】：中国科学院地理科学与资源研究所资源与环境信息系统国家重点实验室;江苏省地理信息资源开发与利用协同创新中心;中国科学院大学;
【基金】：国家科技基础性工作专项重点项目“格网化资源环境综合科学调查规范”(编号:2011FY110400) 国家自然科学基金青年基金项目“基于地理环境遥感监测的喜马拉雅旱獭鼠疫疫源地空间分布与预测研究”(编号:41301474) 中国博士后科学基金资助项目(编号:2013M530708,2014T70114)共同资助
【分类号】：P237

【相似文献】