BRRNet: A Fully Convolutional Neural Network for Automatic Building Extraction From High-Resolution Remote Sensing Images
Open Access
- 24 March 2020
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 12 (6) , 1050
Abstract
Building extraction from high-resolution remote sensing images is of great significance in urban planning, population statistics, and economic forecast. However, automatic building extraction from high-resolution remote sensing images remains challenging. On the one hand, the extraction results of buildings are partially missing and incomplete due to the variation of hue and texture within a building, especially when the building size is large. On the other hand, the building footprint extraction of buildings with complex shapes is often inaccurate. To this end, we propose a new deep learning network, termed Building Residual Refine Network (BRRNet), for accurate and complete building extraction. BRRNet consists of such two parts as the prediction module and the residual refinement module. The prediction module based on an encoder–decoder structure introduces atrous convolution of different dilation rates to extract more global features, by gradually increasing the receptive field during feature extraction. When the prediction module outputs the preliminary building extraction results of the input image, the residual refinement module takes the output of the prediction module as an input. It further refines the residual between the result of the prediction module and the real result, thus improving the accuracy of building extraction. In addition, we use Dice loss as the loss function during training, which effectively alleviates the problem of data imbalance and further improves the accuracy of building extraction. The experimental results on Massachusetts Building Dataset show that our method outperforms other five state-of-the-art methods in terms of the integrity of buildings and the accuracy of complex building footprints.Keywords
Funding Information
- the National key R & D plan on strategic international scientific and technological innovation cooperation special project (2016YFE0202300)
- National Natural Science Foundation of China (61671332, 41771452, 51708426,41890820 and 41771454)
- the Natural Science Fund of Hubei Province in China (2018CFA007)
This publication has 32 references indexed in Scilit:
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- BASI: a new index to extract built-up areas from high-resolution remote sensing images by visual attention modelRemote Sensing Letters, 2014
- Very High-Resolution Remote Sensing: Challenges and Opportunities [Point of View]Proceedings of the IEEE, 2012
- A pixel shape index coupled with spectral information for classification of high spatial resolution remotely sensed imageryIEEE Transactions on Geoscience and Remote Sensing, 2006
- Application of high-resolution stereo satellite images to detailed landslide hazard assessmentGeomorphology, 2006
- A Tutorial on the Cross-Entropy MethodAnnals of Operations Research, 2005
- High Spatial Resolution Remotely Sensed Data for Ecosystem CharacterizationBioScience, 2004
- Automated analysis of ultra high resolution remote sensing data for biotope type mapping: new possibilities and challengesISPRS Journal of Photogrammetry and Remote Sensing, 2003
- Building Detection and Description from a Single Intensity ImageComputer Vision and Image Understanding, 1998
- Application of high-resolution thermal infrared remote sensing and GIS to assess the urban heat island effectInternational Journal of Remote Sensing, 1997