An Improved Mapping with Super-Resolved Multispectral Images for Geostationary Satellites

Super-resolution (SR) technology has shown great potential for improving the performance of the mapping and classification of multispectral satellite images. However, it is very challenging to solve ill-conditioned problems such as mapping for remote sensing images due to the presence of complicated ground features. In this paper, we address this problem by proposing a super-resolution reconstruction (SRR) mapping method called the mixed sparse representation non-convex high-order total variation (MSR-NCHOTV) method in order to accurately classify multispectral images and refine object classes. Firstly, MSR-NCHOTV is employed to reconstruct high-resolution images from low-resolution time-series images obtained from the Gaofen-4 (GF-4) geostationary orbit satellite. Secondly, a support vector machine (SVM) method was used to classify the results of SRR using the GF-4 geostationary orbit satellite images. Two sets of GF-4 satellite image data were used for experiments, and the MSR-NCHOTV SRR result obtained using these data was compared with the SRR results obtained using the bilinear interpolation (BI), projection onto convex sets (POCS), and iterative back projection (IBP) methods. The sharpness of the SRR results was evaluated using the gray-level variation between adjacent pixels, and the signal-to-noise ratio (SNR) of the SRR results was evaluated by using the measurement of high spatial resolution remote sensing images. For example, compared with the values obtained using the BI method, the average sharpness and SNR of the five bands obtained using the MSR-NCHOTV method were higher by 39.54% and 51.52%, respectively, and the overall accuracy (OA) and Kappa coefficient of the classification results obtained using the MSR-NCHOTV method were higher by 32.20% and 46.14%, respectively. These results showed that the MSR-NCHOTV method can effectively improve image clarity, enrich image texture details, enhance image quality, and improve image classification accuracy. Thus, the effectiveness and feasibility of using the proposed SRR method to improve the classification accuracy of remote sensing images was verified.

[1]  Yu Zheng,et al.  Denoising Algorithm for the FY-4A GIIRS Based on Principal Component Analysis , 2019, Remote. Sens..

[2]  A. Okuyama,et al.  An Introduction to Himawari-8/9— Japan’s New-Generation Geostationary Meteorological Satellites , 2016 .

[3]  Chang Huang,et al.  Super-resolution mapping of wetland inundation from remote sensing imagery based on integration of back-propagation neural network and genetic algorithm , 2015 .

[4]  Steven D. Miller,et al.  Tracking oceanic nonlinear internal waves in the Indonesian seas from geostationary orbit , 2018 .

[5]  Qifeng Lu,et al.  Latest Progress of the Chinese Meteorological Satellite Program and Core Data Processing Technologies , 2019, Advances in Atmospheric Sciences.

[6]  Patricia Ladret,et al.  The blur effect: perception and estimation with a new no-reference perceptual blur metric , 2007, Electronic Imaging.

[7]  Cheng Jiehai,et al.  A Method for Measuring Signal-to-noise Ratio of High Spatial Resolution Remote Sensing Images , 2015 .

[8]  Xue-Cheng Tai,et al.  Augmented Lagrangian Method, Dual Methods, and Split Bregman Iteration for ROF, Vectorial TV, and High Order Models , 2010, SIAM J. Imaging Sci..

[9]  Guo Cao,et al.  Active Semi-Supervised Random Forest for Hyperspectral Image Classification , 2019, Remote. Sens..

[10]  Aixia Yang,et al.  Radiometric Cross-Calibration of GF-4 in Multispectral Bands , 2017, Remote. Sens..

[11]  Adil Mehmood Khan,et al.  Multi-layer Extreme Learning Machine-based Autoencoder for Hyperspectral Image Classification , 2019, VISIGRAPP.

[12]  Laurent Condat,et al.  Discrete Total Variation: New Definition and Minimization , 2017, SIAM J. Imaging Sci..

[13]  Yong Chen,et al.  Group sparsity based regularization model for remote sensing image stripe noise removal , 2017, Neurocomputing.

[14]  Liangpei Zhang,et al.  Super-Resolution Reconstruction for Multi-Angle Remote Sensing Images Considering Resolution Differences , 2014, Remote. Sens..

[15]  Peijun Li,et al.  Improving Super-Resolution Mapping by Combining Multiple Realizations Obtained Using the Indicator-Geostatistics Based Method , 2017, Remote. Sens..

[16]  李志来 Li Zhi-lai,et al.  Filter wheel mechanism for optical remote sensor in geostationary orbit , 2015 .

[17]  Zhenchao Li,et al.  Nowcasting of Surface Solar Irradiance Using FengYun-4 Satellite Observations over China , 2019, Remote. Sens..

[18]  M. Pierre,et al.  Regularity of Minimizers of Shape Optimization Problems involving Perimeter , 2016, 1605.06294.

[19]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[20]  Li Fang,et al.  Evapotranspiration Data Product from NESDIS GET-D System Upgraded for GOES-16 ABI Observations , 2019, Remote. Sens..

[21]  Neelam Aziz,et al.  Land use change mapping and analysis using Remote Sensing and GIS: A case study of Simly watershed, Islamabad, Pakistan , 2015 .

[22]  Adil Mehmood Khan,et al.  Spatial Prior Fuzziness Pool-Based Interactive Classification of Hyperspectral Images , 2019, Remote. Sens..

[23]  Huazhong Ren,et al.  Snow Cover Monitoring with Chinese Gaofen-4 PMS Imagery and the Restored Snow Index (RSI) Method: Case Studies , 2018, Remote. Sens..

[24]  Antonio J. Plaza,et al.  A New Genetic Method for Subpixel Mapping Using Hyperspectral Images , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[25]  Lei Wang,et al.  Remote Sensing Image Super-Resolution Using Sparse Representation and Coupled Sparse Autoencoder , 2019, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[26]  Jan-Peter Muller,et al.  Super-Resolution Restoration of MISR Images Using the UCL MAGiGAN System , 2018, Remote. Sens..

[27]  Yi Zhang,et al.  Developing Land Surface Directional Reflectance and Albedo Products from Geostationary GOES-R and Himawari Data: Theoretical Basis, Operational Implementation, and Validation , 2019, Remote. Sens..

[28]  Cesar Guerreiro Diniz,et al.  High spatial resolution land use and land cover mapping of the Brazilian Legal Amazon in 2008 using Landsat-5/TM and MODIS data , 2016 .

[29]  Da He,et al.  Spatial-Temporal Sub-Pixel Mapping Based on Swarm Intelligence Theory , 2016, Remote. Sens..

[30]  Chun-Hung Liu,et al.  Enhanced Noisy Sparse Subspace Clustering via Reweighted L1-Minimization† , 2018, 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP).

[31]  Luxiao He,et al.  System Noise Removal for Gaofen-4 Area-Array Camera , 2018, Remote. Sens..

[32]  Feng Li,et al.  Finer scale mapping with super resolved GF-4 satellite images , 2019, Remote Sensing.

[33]  Yerin Kim,et al.  Deep Learning-Generated Nighttime Reflectance and Daytime Radiance of the Midwave Infrared Band of a Geostationary Satellite , 2019, Remote. Sens..

[34]  Zahra Hossein-Nejad,et al.  A-RANSAC: Adaptive random sample consensus method in multimodal retinal image registration , 2018, Biomed. Signal Process. Control..

[35]  Shaharyar Ahmed Khan Tareen,et al.  A comparative analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK , 2018, 2018 International Conference on Computing, Mathematics and Engineering Technologies (iCoMET).

[36]  George P. Petropoulos,et al.  Co-Orbital Sentinel 1 and 2 for LULC Mapping with Emphasis on Wetlands in a Mediterranean Setting Based on Machine Learning , 2017, Remote. Sens..

[37]  Feng Li,et al.  A Framework of Mixed Sparse Representations for Remote Sensing Images , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[38]  Gerard B. M. Heuvelink,et al.  Hybrid Constraints of Pure and Mixed Pixels for Soft-Then-Hard Super-Resolution Mapping With Multiple Shifted Images , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[39]  Raveendran Paramesran,et al.  Hybrid non-convex second-order total variation with applications to non-blind image deblurring , 2020, Signal Image Video Process..

[40]  Jong-Ok Kim,et al.  Noise-Robust Iterative Back-Projection , 2020, IEEE Transactions on Image Processing.

[41]  Wajahat Ali Khan,et al.  Fuzziness-based active learning framework to enhance hyperspectral image classification performance for discriminative and generative classifiers , 2018, PloS one.

[42]  Antonio J. Plaza,et al.  Joint Sparse Sub-Pixel Mapping Model with Endmember Variability for Remotely Sensed Imagery , 2016, Remote. Sens..

[43]  K. Moffett,et al.  Remote Sens , 2015 .

[44]  Patrick Bouthemy,et al.  Intensity-based matching and registration for 3D correlative microscopy with large discrepancies , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[45]  Liang Xiao,et al.  Hyperspectral Mixed Denoising via Spectral Difference-Induced Total Variation and Low-Rank Approximation , 2018, Remote. Sens..

[46]  Liangpei Zhang,et al.  Adaptive Sparse Subpixel Mapping With a Total Variation Model for Remote Sensing Imagery , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[47]  Nicholas C. Makris,et al.  Maximum Likelihood Deconvolution of Beamformed Images with Signal-Dependent Speckle Fluctuations from Gaussian Random Fields: With Application to Ocean Acoustic Waveguide Remote Sensing (OAWRS) , 2016, Remote. Sens..

[48]  Junfeng Yang,et al.  A New Alternating Minimization Algorithm for Total Variation Image Reconstruction , 2008, SIAM J. Imaging Sci..

[49]  Gang Liu,et al.  Total variation with overlapping group sparsity for speckle noise reduction , 2016, Neurocomputing.

[50]  Behrooz Nasihatkon,et al.  Globally Optimal Rigid Intensity Based Registration: A Fast Fourier Domain Approach , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[51]  Lin Liu,et al.  Hyperspectral Image Super-Resolution Inspired by Deep Laplacian Pyramid Network , 2018, Remote. Sens..