Super-Resolving Commercial Satellite Imagery Using Realistic Training Data

In machine learning based single image super-resolution, the degradation model is embedded in training data generation. However, most existing satellite image super-resolution methods use a simple down-sampling model with a fixed kernel to create training images. These methods work fine on synthetic data, but do not perform well on real satellite images. We propose a realistic training data generation model for commercial satellite imagery products, which includes not only the imaging process on satellites but also the post-process on the ground. We also propose a convolutional neural network optimized for satellite images. Experiments show that the proposed training data generation model is able to improve super-resolution performance on real satellite images.

[1]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[3]  Michel Barlaud,et al.  Deterministic edge-preserving regularization in computed imaging , 1997, IEEE Trans. Image Process..

[4]  Zhiwei Xiong,et al.  Camera Lens Super-Resolution , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Wei Wang,et al.  Deep Learning for Single Image Super-Resolution: A Brief Review , 2018, IEEE Transactions on Multimedia.

[6]  Karim Faez,et al.  Automatic Traffic Monitoring from Satellite Images Using Artificial Immune System , 2010, SSPR/SPR.

[7]  Pedro A. Rodriguez,et al.  Super-Resolution for Overhead Imagery Using DenseNets and Adversarial Learning , 2018, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[8]  Peyman Milanfar,et al.  NIMA: Neural Image Assessment , 2017, IEEE Transactions on Image Processing.

[9]  Junjun Jiang,et al.  Edge-Enhanced GAN for Remote Sensing Image Superresolution , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[10]  James H. Money,et al.  Total variation minimizing blind deconvolution with shock filter reference , 2008, Image Vis. Comput..

[11]  Wangmeng Zuo,et al.  Learning a Single Convolutional Super-Resolution Network for Multiple Degradations , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[12]  Amel Benazza-Benyahia,et al.  Satellite image restoration in the context of a spatially varying point spread function. , 2010, Journal of the Optical Society of America. A, Optics, image science, and vision.

[13]  Rasim Latifovic,et al.  Landsat Super-Resolution Enhancement Using Convolution Neural Networks and Sentinel-2 for Training , 2018, Remote. Sens..

[14]  Cláudia M. Viana,et al.  Long-Term Satellite Image Time-Series for Land Use/Land Cover Change Detection Using Refined Open Source Data in a Rural Region , 2019, Remote. Sens..

[15]  Kyoung Mu Lee,et al.  Accurate Image Super-Resolution Using Very Deep Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  H.Th. Verstappen,et al.  Aerospace technology and natural disaster reduction , 1995 .

[17]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Peyman Milanfar,et al.  Learned perceptual image enhancement , 2017, 2018 IEEE International Conference on Computational Photography (ICCP).

[19]  M. Körner,et al.  SINGLE-IMAGE SUPER RESOLUTION FOR MULTISPECTRAL REMOTE SENSING DATA USING CONVOLUTIONAL NEURAL NETWORKS , 2016 .

[20]  Qian Du,et al.  Using High-Resolution Airborne and Satellite Imagery to Assess Crop Growth and Yield Variability for Precision Agriculture , 2013, Proceedings of the IEEE.

[21]  Chiman Kwan,et al.  Deep Learning for Remote Sensing Image Super-Resolution , 2019, 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON).