Deep learning-based building height mapping using Sentinel-1 and Sentienl-2 data
International Journal of Applied Earth Observation and Geoinformation(2023)
摘要
•Building height samples were generated from Sentinel 1/2 and publicly available data.•A dual-branch structure building height estimation network was proposed.•A novel module was designed to facilitate optical and SAR features fusion.•The spatially continuous building height mappings with 10-m resolution were produced.•Our method offers new possibilities for fine resolution building height mapping of China.
更多查看译文
关键词
Building height,Sentinel,Deep learning,Urban agglomeration,Data fusion
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要