Multi-channel recurrent attention network for building extraction from high resolution remote sensing images

Abstract

Building extraction from high-resolution remote sensing images is of great importance for urban planning, disaster assessment, and geography mapping. In recent years, convolutional neural networks have made outstanding achievements in improving the precision of building extraction. However, most existing approaches have some problems, such as insufficient detailed feature extraction and ignorance of the relationship between different features. In this study, we propose a novel multi-channel recurrent attention network (MCANet) for building extraction. Firstly, the multi-scale channel attention mechanism is used to expand the convolution kernel receptive field, making the model can extract rich building region feature information. Secondly, we use the spatial pyramid recurrent block to establish long-range dependencies over space, channel, and layer of different convolutions. Finally, the multi-channel feature fusion block is used to fuse the multi-scale channel features information, and improve the building extraction precision. Experimental results show that the proposed MCANet achieves better results (recall, precision, intersection-over-union, and F1_score on the Inria Aerial Image Labeling Dataset are 89.82%, 94.38%, 87.42%, and 88.25%, respectively), and outperforms the other state-of-the-art approaches.