Progressively Growing Generative Adversarial Networks for High Resolution Semantic Segmentation of Satellite Images

Machine learning has proven to be useful in classification and segmentation of images. In this paper, we evaluate a training methodology for pixel-wise segmentation on high resolution satellite images using progressive growing of generative adversarial networks. We apply our model to segmenting building rooftops and compare these results to conventional methods for rooftop segmentation. We present our findings using the SpaceNet version 2dataset. Progressive GAN training achieved a test accuracy of 93% compared to 89% for traditional GAN training.

[1]  Alexei A. Efros,et al.  Context Encoders: Feature Learning by Inpainting , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Motaz El-Saban,et al.  Automatic Pixelwise Object Labeling for Aerial Imagery Using Stacked U-Nets , 2018, ArXiv.

[3]  Andreas Dengel,et al.  Overcoming Missing and Incomplete Modalities with Generative Adversarial Networks for Building Footprint Segmentation , 2018, 2018 International Conference on Content-Based Multimedia Indexing (CBMI).

[4]  W. Woon,et al.  Novel Approach for Rooftop Detection Using Support Vector Machine , 2013 .

[5]  J. Townshend,et al.  Characterizing the magnitude, timing and duration of urban growth from time series of Landsat-based estimates of impervious cover , 2016 .

[6]  Qingxuan Jia,et al.  Building recognition from aerial images combining segmentation and shadow , 2009, 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems.

[7]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[8]  Sangram Ganguly,et al.  DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution , 2017, KDD.

[9]  Marco Körner,et al.  Automatic Large-Scale 3D Building Shape Refinement Using Conditional Generative Adversarial Networks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[10]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[12]  Sangram Ganguly,et al.  A theoretical analysis of Deep Neural Networks for texture classification , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[13]  Ting Jiang,et al.  A New Classification Method for LIDAR Data Based on Unbalanced Support Vector Machine , 2011, 2011 International Symposium on Image and Data Fusion.

[14]  Xia Li,et al.  Road Detection From Remote Sensing Images by Generative Adversarial Networks , 2018, IEEE Access.

[15]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[16]  Konstantinos Kamnitsas,et al.  Unsupervised domain adaptation in brain lesion segmentation with adversarial networks , 2016, IPMI.

[17]  Yoonseok Jwa,et al.  AN IMPLICIT REGULARIZATION FOR 3D BUILDING ROOFTOP MODELING USING AIRBORNE LIDAR DATA , 2012 .

[18]  Sangram Ganguly,et al.  Learning Sparse Feature Representations Using Probabilistic Quadtrees and Deep Belief Nets , 2015, Neural Processing Letters.

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

[20]  Supratik Mukhopadhyay,et al.  A Semiautomated Probabilistic Framework for Tree-Cover Delineation From 1-m NAIP Imagery Using a High-Performance Computing Architecture , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Xiaohui Xie,et al.  Adversarial Deep Structural Networks for Mammographic Mass Segmentation , 2016, bioRxiv.

[22]  Supratik Mukhopadhyay,et al.  Core Sampling Framework for Pixel Classification , 2016, ICANN.

[23]  Supratik Mukhopadhyay,et al.  CactusNets: Layer Applicability as a Metric for Transfer Learning , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[24]  Supratik Mukhopadhyay,et al.  DeepSat: a learning framework for satellite imagery , 2015, SIGSPATIAL/GIS.

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

[26]  Supratik Mukhopadhyay,et al.  Deep neural networks for texture classification - A theoretical analysis , 2018, Neural Networks.

[27]  Bikash Joshi,et al.  Automatic Rooftop Detection Using a Two-Stage Classification , 2014, 2014 UKSim-AMSS 16th International Conference on Computer Modelling and Simulation.

[28]  G. Meehl,et al.  More Intense, More Frequent, and Longer Lasting Heat Waves in the 21st Century , 2004, Science.

[29]  Jianguo Tan,et al.  The urban heat island and its impact on heat waves and human health in Shanghai , 2010, International journal of biometeorology.

[30]  Jie Shan,et al.  A comprehensive review of earthquake-induced building damage detection with remote sensing techniques , 2013 .

[31]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

[32]  Curt H. Davis,et al.  Automated Building Extraction from High-Resolution Satellite Imagery in Urban Areas Using Structural, Contextual, and Spectral Information , 2005, EURASIP J. Adv. Signal Process..

[33]  Iasonas Kokkinos,et al.  Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs , 2014, ICLR.

[34]  Xiaoling Chen,et al.  Remote sensing image-based analysis of the relationship between urban heat island and land use/cover changes , 2006 .

[35]  Yifan Wu,et al.  Aerial Imagery for Roof Segmentation: A Large-Scale Dataset towards Automatic Mapping of Buildings , 2018, ArXiv.

[36]  Camille Couprie,et al.  Semantic Segmentation using Adversarial Networks , 2016, NIPS 2016.