Integrating intensity and context for improved supervised river ice classification from dual-pol Sentinel-1 SAR data

Sophie de Roda Husman,Joost J. van der Sanden,Stefaan Lhermitte,Marieke A. Eleveld

International Journal of Applied Earth Observation and Geoinformation（2021）

引用 9|浏览6

暂无评分

摘要

•An operational Sentinel-1 river ice classification has relevance for flood early-warning.•Different intensity, polarimetric and texture feature combinations for classification.•GLCM mean of VV, and VH intensity were most useful features.•>85% classification accuracy of Random Forest river ice breakup classification.•Developed approach also results in >85% accuracies for other SAR missions.

查看译文

关键词

River ice,Classification,SAR,Sentinel-1,Random Forest,GLCM texture

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