Building segmentation through a gated graph convolutional neural network with deep structured feature embedding

Abstract

Automatic building extraction from optical imagery remains a challenge due to, for example, the complexity ofbuilding shapes. Semantic segmentation is an efficient approach for this task. The latest development in deep convolutional neural networks (DCNNs) has made accurate pixel-level classification tasks possible. Yet onecentral issue remains: the precise delineation of boundaries. Deep architectures generally fail to produce fine-grained segmentation with accurate boundaries due to their progressive down-sampling. Hence, we introduce ageneric framework to overcome the issue, integrating the graph convolutional network (GCN) and deep struc-tured feature embedding (DSFE) into an end-to-end workflow. Furthermore, instead of using a classic graphconvolutional neural network, we propose a gated graph convolutional network, which enables the refinement of weak and coarse semantic predictions to generate sharp borders and fine-grained pixel-level classification.Taking the semantic segmentation of building footprints as a practical example, we compared different feature embedding architectures and graph neural networks. Our proposed framework with the new GCN architectureoutperforms state-of-the-art approaches. Although our main task in this work is building footprint extraction, theproposed method can be generally applied to other binary or multi-label segmentation tasks.