Instance Segmentation of Buildings in Satellite Images

Abstract: When creating a photo realistic 3D model of the world using satellite imagery, image classification is an important part of the process. In this thesis the specificpart of automated building extraction is investigated. This is done by investi-gating the difference in performance between the methods instance segmentation and semantic segmentation for extraction of building footprints in orthorectified imagery. Semantic segmentation of the images is solved by using U-net, a Fully Convolutional Network that outputs a pixel-wise segmentation of the image. Instance segmentation of the images is done by a network called Mask R-CNN.The performance of the models are measured using precision, recall and the F1 score, which is the harmonic mean between precision and recall. The resulting F1 score of the two methods are similar, with U-net achieving a the F1 score of 0.684 without any post processing. Mask R-CNN achieves the F1 score of 0.676 without post processing.