CrossGeoNet: A Framework for Building Footprint Generation of Label-Scarce Geographical Regions

Qingyu Li,Lichao Mou,Yuansheng Hua,Yilei Shi,Xiao Xiang Zhu

International Journal of Applied Earth Observation and Geoinformation（2022）

引用 6|浏览13

暂无评分

摘要

•Planet satellite imagery is utilized for building mapping in less developed regions (e.g., cities in Africa)•A co-segmentation learning framework is proposed to tackle the problem of insufficient labeled samples in target cities for the task of building footprint generation•A cross-geolocation attention module is proposed to effectively learn the underlying similarity between different geolocations

查看译文

关键词

Building footprint,Semantic segmentation,Convolutional neural network,Co-segmentation,Planet satellite

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