Cost-effective land cover classification for remote sensing images

Land cover maps are of vital importance to various fields such as land use policy development, ecosystem services, urban planning and agriculture monitoring, which mainly generated from remote sensing image classification techniques. Traditional usually needs tremendous computational resources, often becomes a huge burden the community. Undoubtedly cloud computing is one best choices for classification, however, if not managed properly, computation cost on could be surprisingly high. Recently, cutting unnecessary long tail has become promising solution saving in cloud. For it generally necessary achieve accuracy 85% can regarded reliable classification. Therefore, this paper, we propose framework cost-effective Given desired accuracy, clustering algorithm stop early cost-saving whilst achieving sufficient Experimental results show that 85%-99.9% only 27.34%-60.83% total 100% accuracy. To put into perspective, US example, proposed approach save over $1,593,490.18 government each single-use when 90%.