Abstract
In this paper we present a method for building boundary re-finement and regularization in satellite images using a fullyconvolutional neural network trained with a combination ofadversarial and regularized losses. Compared to a pure MaskR-CNN model, the overall algorithm can achieve equivalentperformance in terms of accuracy and completeness. How-ever, unlike Mask R-CNN that produces irregular footprints,our framework generates regularized and visually pleasingbuilding boundaries which are beneficial in many applica-tions.
Original language | English |
---|---|
Title of host publication | IGARSS 2019 |
Publisher | IEEE Publications |
Pages | 5140-5143 |
Number of pages | 4 |
Publication status | Published - 1 Jul 2019 |
Keywords
- Generative adversarial networks
- build-ing segmentation
- boundary refinement
- satellite images