Building Extraction from RGB Satellite Images using Deep Learning: A U-Net Approach

Automatic building extraction from satellite RGB images, is a low-cost alternative to perform important urban planning tasks. Yet, it is a challenging one, especially when natural and non-city block objects interfere in the semantic segmentation of algorithms that extract their key features. In this work we approach the automatic building extraction using a Convolution Neural Network based on the U-Net architecture. In contrast to existing approaches, it successfully encodes important features and decodes the buildings’ localization by requiring both reduced computational time and dataset size. We evaluate the U-Net’s performance using RGB images selected from the SpaceNet 1 dataset and the experimental results show an accuracy in building localization of 92.3%. Finally, favorable comparison with existing CNN approaches to hyperspectral images targeting the SpaceNet 1 dataset, demonstrated its effectiveness.

[1]  Jon Atli Benediktsson,et al.  Advances in Spectral-Spatial Classification of Hyperspectral Images , 2013, Proceedings of the IEEE.

[2]  Anastasios Doulamis,et al.  Pixel-level Corrosion Detection on Metal Constructions by Fusion of Deep Learning Semantic and Contour Segmentation , 2020, ISVC.

[3]  Sophia Karagiorgou,et al.  A service oriented architecture for decision support systems in environmental crisis management , 2012, Future Gener. Comput. Syst..

[4]  Adam Van Etten,et al.  You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery , 2018, ArXiv.

[5]  Adam Van Etten,et al.  SpaceNet: A Remote Sensing Dataset and Challenge Series , 2018, ArXiv.

[6]  Pierre Soille,et al.  A New European Settlement Map From Optical Remotely Sensed Data , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[7]  Nikolaos Doulamis,et al.  Stacked Autoencoders Driven by Semi-Supervised Learning for Building Extraction from near Infrared Remote Sensing Imagery , 2021, Remote. Sens..

[8]  Pengcheng Zhang,et al.  Automatic building extraction from high-resolution aerial images and LiDAR data using gated residual refinement network , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[9]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Jaewook Jung,et al.  Building Extraction from Satellite Images Using Mask R-CNN with Building Boundary Regularization , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[11]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Nikolaos Doulamis,et al.  Deep convolutional neural networks for building extraction from orthoimages and dense image matching point clouds , 2017 .

[13]  Luis Ángel Ruiz Fernández,et al.  Evaluation of Automatic Building Detection Approaches Combining High Resolution Images and LiDAR Data , 2011, Remote. Sens..

[14]  E. Protopapadakis,et al.  Deep learning models for COVID-19 infected area segmentation in CT images , 2020, medRxiv.

[15]  Huadong Guo,et al.  A Global Human Settlement Layer From Optical HR/VHR RS Data: Concept and First Results , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

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

[17]  Nikos Paragios,et al.  Integrating edge/boundary priors with classification scores for building detection in very high resolution data , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[18]  Konstantinos Karantzalos,et al.  Recent Advances on 2D and 3D Change Detection in Urban Environments from Remote Sensing Data , 2015 .

[19]  Ilya Afanasyev,et al.  Deep Learning Approach for Building Detection in Satellite Multispectral Imagery , 2018, 2018 International Conference on Intelligent Systems (IS).

[20]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.