no code implementations • 23 Jun 2020 • Kang Zhao, Muhammad Kamran, Gunho Sohn
The proposed deep learning method consists of a two-stage object detection network to produce region of interest (RoI) features and a building boundary extraction network using graph models to learn geometric information of the polygon shapes.
no code implementations • arXiv 2020 • Kang Zhao, Muhammad Kamran, Gunho Sohn
The proposed deep learning method consists of a two-stage object detection network to produce region of interest (RoI) features and a building boundary extraction network using graph models to learn geometric information of the polygon shapes.