An automatic method for impervious surface area extraction by fusing high-resolution night light and Landsat OLI images

Abstract

Supervised classification is a vital approach to extract impervious surface areas(ISA)from satellite images,but the training samples need to be provided through heavy manual work. To address it,this study proposed an automatic method to generate training samples from high-resolution night light data,considering that nighttime lights generated by human activities is strongly correlated with impervious surface. First,positive and negative samples for ISA were located according to the distribu‐ tion of nighttime lights. Second,the feature sets were constructed by calculating the spectral and tex‐ ture feature from the OLI images. Third,an ensemble ELM classifier was selected for ISA classifica‐ tion and extraction. Four large cities were selected as study areas to examine the performance of the 文章编号:1001-9014(2020)01-0128-09 DOI:10. 11972/j. issn. 1001-9014. 2020. 01. 017 收稿日期:2019-08-16,修回日期:2019-12-16 Received date:2019-08-16,Revised date:2019-12-16 基金项目:国家自然科学基金重点项目(41631176) Foundation items:Supported by the National Natural Science Foundation of China(41631176) 作者简介(Biography):唐鹏飞(1997-),男,安徽合肥人,博士生,主要研究领域为遥感图像智能处理 . E-mail:Sgos_tpf@smail. nju. edu. cn *通讯作者(Corresponding author):zelang. miao@csu. edu. cn;dupjrs@126. com 1期 唐鹏飞 等:融合高分夜光和Landsat OLI影像的不透水面自动提取方法 proposed method in different environment. The results show that the proposed method can automatical‐ ly and accurately acquire ISA with an overall accuracy higher than 93% and Kappa coefficient higher than 0. 87. Furthermore,comparative experiments by biophysical composition index(BCI)and classi‐ fication by manual sample were conducted to evaluate its superiority. The results show that our method has better separability for ISA and soil than the BCI. In general,the proposed method is superior to manual methods,except Harbin mostly because some impervious surfaces with weak light intensity are selected as negative samples.