Cycle-Consistent Adversarial Networks for Realistic Pervasive Change Generation in Remote Sensing Imagery

This paper introduces a new method of generating realistic pervasive changes in the context of evaluating the effectiveness of change detection algorithms in controlled settings. The method – a cycle-consistent adversarial network (CycleGAN) – requires low quantities of training data to generate realistic changes. Here we show an application of CycleGAN in creating realistic snow-covered scenes of multispectral Sentinel-2 imagery, and demonstrate how these images can be used as a test bed for anomalous change detection algorithms.

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

[2]  Michael S. Warren,et al.  Monitoring forest disturbance using change detection on synthetic aperture radar imagery , 2019, Optical Engineering + Applications.

[3]  Yoshua Bengio,et al.  Generative Adversarial Networks , 2014, ArXiv.

[4]  James Theiler,et al.  Multi-sensor anomalous change detection at scale , 2019, Defense + Commercial Sensing.

[5]  Ashbindu Singh,et al.  Review Article Digital change detection techniques using remotely-sensed data , 1989 .

[6]  D. Lu,et al.  Change detection techniques , 2004 .

[7]  James Theiler,et al.  Local Coregistration Adjustment for Anomalous Change Detection , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Qian Du,et al.  Multi-Modal Change Detection, Application to the Detection of Flooded Areas: Outcome of the 2009–2010 Data Fusion Contest , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[9]  I. Hegazy,et al.  Monitoring urban growth and land use change detection with GIS and remote sensing techniques in Daqahlia governorate Egypt , 2015 .

[10]  Badrinath Roysam,et al.  Image change detection algorithms: a systematic survey , 2005, IEEE Transactions on Image Processing.

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

[12]  Nathan Longbotham,et al.  Harmonization And Fusion of Global Scale Data , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[13]  James Theiler,et al.  Right spectrum in the wrong place: a framework for local hyperspectral anomaly detection , 2016, Computational Imaging.