Building Footprint Extraction with Graph Convolutional Network

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. Recent developments in deep convolutional neural networks (DCNNs) have enabled accurate pixel-level labeling tasks. One central issue remains, which is the precise delineation of boundaries. Deep architectures generally fail to produce fine-grained segmentation with accurate boundaries due to progressive downsampling. In this work, we have proposed a end-to-end framework to overcome this issue, which uses the graph convolutional network (GCN) for building footprint extraction task. Our proposed framework outperforms state-of-the-art methods.

arXiv comment4 pages. arXiv admin note: text overlap with arXiv:1911.03165

References in corpus (6)

• Semi-Supervised Classification with Graph Convolutional Networks
• Deep learning in remote sensing: a review
• Fully Convolutional Networks for Semantic Segmentation
• Conditional Random Fields as Recurrent Neural Networks
• Deep Convolutional Networks on Graph-Structured Data
• Building Footprint Generation Using Improved Generative Adversarial Networks