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.

Highlights

  • With the development of imaging sensor technology, the imaging quality of remote sensing images is constantly improving, which makes obtaining high-resolution remote sensing images more convenient

  • Four indicators are used to evaluate the effectiveness in image pixel-level prediction tasks: true positive case (TP), false positive case (FP), true negative case (TN) and false negative case (FN)

  • We propose a new end-to-end deep learning network Building Residual Refine Network (BRRNet) to address the problems of incomplete building extraction and inaccurate building footprint extraction of the buildings with complex shapes in high-resolution remote sensing images

Read more

Summary

Introduction

With the development of imaging sensor technology, the imaging quality of remote sensing images is constantly improving, which makes obtaining high-resolution remote sensing images more convenient. The improvement of the spatial resolution of remote sensing images makes the information of ground features more abundant, but it brings greater challenges to the extraction of buildings [5,6,7,8]. Many researchers are working on the automatic extraction of buildings from remote sensing images, and have proposed some effective building extraction methods. These methods can roughly be classified into two categories: one is based on artificially designed features and the other is based on deep learning

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call