UHA: An Intelligent Uncertainty Map Based Hierarchical Attention Network System for Building Segmentation
Open Access
- 6 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 11 (6) , 5695-5706
Abstract
Satellite images are becoming increasingly high quality with the advancement of high-resolution remote sensing technology. Benefited from the development of deep learning, object segmentation for the high-resolution satellite images has achieved significant improvements in recent years. However, for buildings with multiple scales and almost straight edges in satellite images, the current segmentation methods usually struggle to achieve relatively good results. In this paper, we propose an Uncertainty map based Hierarchical Attention network system (UHA) for building segmentation. UHA aims to capture the information about low-confidence areas of the building's straight edges and improve the segmentation prediction step by step by a hierarchical structure network with three decoder branches. Specifically, we first generate uncertainty maps from the sigmoid prediction maps of the segmentation network. Based on the uncertainty maps, we design an attention module where a transform function transforms the uncertainty maps into attention maps. And then, we introduce the attention module to adjacent branches of the hierarchical network to guide the latter branch by the previous branch, which improves the prediction ability of the following branch smoothly. Finally, we conduct comprehensive experiments that show the proposed system can significantly improve the performance upon baselines by a large margin.Keywords
Funding Information
- National Natural Science Foundation of China (62272179)
This publication has 46 references indexed in Scilit:
- RLLNet: a lightweight remaking learning network for saliency redetection on RGB-D imagesScience China Information Sciences, 2022
- A coarse-to-fine boundary refinement network for building footprint extraction from remote sensing imageryISPRS Journal of Photogrammetry and Remote Sensing, 2022
- Integrating semantic edges and segmentation information for building extraction from aerial images using UNetMachine Learning with Applications, 2021
- Deep building footprint update network: A semi-supervised method for updating existing building footprint from bi-temporal remote sensing imagesRemote Sensing of Environment, 2021
- Building extraction from VHR remote sensing imagery by combining an improved deep convolutional encoder-decoder architecture and historical land use vector mapInternational Journal of Remote Sensing, 2020
- Deep learning in remote sensing applications: A meta-analysis and reviewISPRS Journal of Photogrammetry and Remote Sensing, 2019
- TEMPORARY REMOVAL: Aerial imagery for roof segmentation: A large-scale dataset towards automatic mapping of buildingsISPRS Journal of Photogrammetry and Remote Sensing, 2019
- V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Fully convolutional networks for semantic segmentation2015