Built-Up Area Extraction Combing Densely Connected Dual-Attention Network and Multiscale Context

Abstract

Built-up areas are the main areas for human production and life. The wide availability of high-resolution satellite images provides new opportunities for fine-scale detection and mapping of built-up areas. However, great challenges remain because built-up areas are large-scale composite geographical objects, which contain diverse object classes and complex scenes, and have extremely large feature heterogeneity across space. For the automatic recognition of built-up areas in high spatial resolution satellite images, a block-level built-up area extraction framework combing densely connected dual-attention network and multiscale context is proposed. The proposed method first divides an image into multiscale blocks with a certain proportion of overlap through multisize grids and their multistep offsets. It then uses the constructed lightweight network integrating dense connection and dual attention to realize the feature representation and discrimination of image blocks. Finally, it achieves the refined detection of built-up areas by integrating the prediction results under different divisions through pixel-level multilabel voting. GaoFen-2 satellite images covering Shenzhen city, China, are used to verify the effectiveness of the proposed method. In the five selected test areas, the F1 score of the proposed method ranges from 0.8720 to 0.8983. Results visually preserve the integrity of internal morphology and have a well-defined boundary. The proposed method shows better performance than the state-of-the-art built-up area extraction methods. It can potentially be applied for fine mapping of large-scale urban built-up areas from high-resolution satellite images.