EfficientUNet+: A Building Extraction Method for Emergency Shelters Based on Deep Learning

Quickly and accurately extracting buildings from remote sensing images is essential for urban planning, change detection, and disaster management applications. In particular, extracting buildings that cannot be sheltered in emergency shelters can help establish and improve a city’s overall disaster prevention system. However, small building extraction often involves problems, such as integrity, missed and false detection, and blurred boundaries. In this study, EfficientUNet+, an improved building extraction method from remote sensing images based on the UNet model, is proposed. This method uses EfficientNet-b0 as the encoder and embeds the spatial and channel squeeze and excitation (scSE) in the decoder to realize forward correction of features and improve the accuracy and speed of model extraction. Next, for the problem of blurred boundaries, we propose a joint loss function of building boundary-weighted cross-entropy and Dice loss to enforce constraints on building boundaries. Finally, model pretraining is performed using the WHU aerial building dataset with a large amount of data. The transfer learning method is used to complete the high-precision extraction of buildings with few training samples in specific scenarios. We created a Google building image dataset of emergency shelters within the Fifth Ring Road of Beijing and conducted experiments to verify the effectiveness of the method in this study. The proposed method is compared with the state-of-the-art methods, namely, DeepLabv3+, PSPNet, ResUNet, and HRNet. The results show that the EfficientUNet+ method is superior in terms of Precision, Recall, F1-Score, and mean intersection over union (mIoU). The accuracy of the EfficientUNet+ method for each index is the highest, reaching 93.01%, 89.17%, 91.05%, and 90.97%, respectively. This indicates that the method proposed in this study can effectively extract buildings in emergency shelters and has an important reference value for guiding urban emergency evacuation.

[1]  Zhenchao Tang,et al.  Capsule-Encoder-Decoder: A Method for Generalizable Building Extraction from Remote Sensing Images , 2022, Remote. Sens..

[2]  Shaodan Li,et al.  Rural Built-Up Area Extraction from Remote Sensing Images Using Spectral Residual Methods with Embedded Deep Neural Network , 2022, Sustainability.

[3]  D. Zhuang,et al.  B-FGC-Net: A Building Extraction Network from High Resolution Remote Sensing Imagery , 2022, Remote. Sens..

[4]  F. Miao,et al.  Building extraction from remote sensing images using deep residual U-Net , 2022, European Journal of Remote Sensing.

[5]  Padmavathi Kora,et al.  EfficientNet-B0 Based Monocular Dense-Depth Map Estimation , 2021, Traitement du Signal.

[6]  Peijun Du,et al.  Integrating EfficientNet into an HAFNet Structure for Building Mapping in High-Resolution Optical Earth Observation Data , 2021, Remote. Sens..

[7]  Hanfa Xing,et al.  A Stacking Ensemble Deep Learning Model for Building Extraction from Remote Sensing Images , 2021, Remote. Sens..

[8]  Jiayi Li,et al.  Recognition and extraction of high-resolution satellite remote sensing image buildings based on deep learning , 2021, Neural Computing and Applications.

[9]  Wenbo Xu,et al.  Boundary-Aware Refined Network for Automatic Building Extraction in Very High-Resolution Urban Aerial Images , 2021, Remote. Sens..

[10]  Lei Wang,et al.  An end-to-end shape modeling framework for vectorized building outline generation from aerial images , 2020, ISPRS Journal of Photogrammetry and Remote Sensing.

[11]  Zhiyu Xu,et al.  A Novel Intelligent Classification Method for Urban Green Space Based on High-Resolution Remote Sensing Images , 2020, Remote. Sens..

[12]  Martin Jägersand,et al.  U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection , 2020, Pattern Recognit..

[13]  Yuhao Wang,et al.  Real-Time Dense Semantic Labeling with Dual-Path Framework for High-Resolution Remote Sensing Image , 2019, Remote. Sens..

[14]  Ke Wang,et al.  Building Extraction from Very High Resolution Aerial Imagery Using Joint Attention Deep Neural Network , 2019, Remote. Sens..

[15]  Jiancheng Luo,et al.  DE-Net: Deep Encoding Network for Building Extraction from High-Resolution Remote Sensing Imagery , 2019, Remote. Sens..

[16]  Christian Desrosiers,et al.  Revisiting CycleGAN for semi-supervised segmentation , 2019, ArXiv.

[17]  Mengyu Li,et al.  Hyperspectral Remote Sensing of Phytoplankton Species Composition Based on Transfer Learning , 2019, Remote. Sens..

[18]  JI Shunping,et al.  Building extraction via convolutional neural networks from an open remote sensing building dataset , 2019 .

[19]  Ali Mohammadzadeh,et al.  Evaluation of effectiveness of three fuzzy systems and three texture extraction methods for building damage detection from post-event LiDAR data , 2018, Int. J. Digit. Earth.

[20]  Nassir Navab,et al.  Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks , 2018, MICCAI.

[21]  Yongyang Xu,et al.  Building Extraction in Very High Resolution Remote Sensing Imagery Using Deep Learning and Guided Filters , 2018, Remote. Sens..

[22]  Menglong Yan,et al.  Automatic Ship Detection in Remote Sensing Images from Google Earth of Complex Scenes Based on Multiscale Rotation Dense Feature Pyramid Networks , 2018, Remote. Sens..

[23]  Yi Li,et al.  Building segmentation and outline extraction from UAV image-derived point clouds by a line growing algorithm , 2017, Int. J. Digit. Earth.

[24]  Jia Yu,et al.  Multi-criteria Satisfaction Assessment of the Spatial Distribution of Urban Emergency Shelters Based on High-Precision Population Estimation , 2016, International Journal of Disaster Risk Science.

[25]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[26]  Trevor Darrell,et al.  Fully convolutional networks for semantic segmentation , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Tobia Lakes,et al.  Urban adaptation planning and climate-related disasters: An integrated assessment of public infrastructure serving as temporary shelter during river floods in Colombia , 2014 .

[28]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .