Building Footprint Generation Using Improved Generative Adversarial Networks

Abstract

Building footprint information is an essential ingredient for 3-D reconstruction of urban models. The automatic generation of building footprints from satellite images presents a considerable challenge due to the complexity of building shapes. In this work, we have proposed improved generative adversarial networks (GANs) for the automatic generation of building footprints from satellite images. We used a conditional GAN with a cost function derived from the Wasserstein distance and added a gradient penalty term. The achieved results indicated that the proposed method can significantly improve the quality of building footprint generation compared to conditional generative adversarial networks, the U-Net, and other networks. In addition, our method nearly removes all hyperparameters tuning.

arXiv comment5 pages

References in corpus (5)

• Conditional Generative Adversarial Nets
• Deep learning in remote sensing: a review
• Optimal Clustering Framework for Hyperspectral Band Selection
• Locality and Structure Regularized Low Rank Representation for Hyperspectral Image Classification
• Understanding Convolution for Semantic Segmentation

Cited by in corpus (6)

• Building Footprint Generation by IntegratingConvolution Neural Network with Feature PairwiseConditional Random Field (FPCRF)
• Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images
• Semi-Supervised Building Footprint Generation with Feature and Output Consistency Training
• Building Footprint Extraction with Graph Convolutional Network
• Building Segmentation through a Gated Graph Convolutional Neural Network with Deep Structured Feature Embedding
• Instance segmentation of buildings using keypoints