基于多源数据融合的城市建成区提取方法

Urban Built-up Area Extraction Method Based on Multi-source Data Fusion

目前城市建成区提取方法存在城乡界限不清晰、单一数据源自身缺陷等问题,从多源数据融合角度入手,提出了一种在遥感影像深度学习提取建设用地的基础上,融合夜光、兴趣点(POI)等数据提取城市建成区的方法。将该方法与单一数据源提取建成区方法以及真实建成区数据进行比较分析发现,该方法能充分利用各种数据优势,实现数据互补,合理提取城市建成区范围。

At present,there are some defects in the urban built-up area extraction method,such as unclear urban-rural boundaries and the defects of a single data source.From the perspective of multi-source data fusion,we proposed an urban built-up area extraction method by fusing nighttime light,points of interest(POI)and other data based on remote sensing image deep learning extracting construction land.Then,we compared this method with various built-up area extraction methods from single data source and real built-up area data.The result shows that this method can make full use of various data advantages,realize data complementarity and reasonably extract the scope of urban built-up area.