Predicting the liveability of Dutch cities with aerial images and semantic intermediate concepts

In order to provide urban residents with suitable living conditions, it is essential to keep track of the liveability of neighbourhoods. This is traditionally done through surveys and by predictive modelling. However, surveying on a large scale is expensive and hard to repeat. Recent research has shown that deep learning models trained on remote sensing images may be used to predict liveability. In this paper we study how well a model can predict liveability from aerial images by first predicting a set of intermediate domain scores. Our results suggest that our semantic bottleneck model perfor... Mehr ...