Früher|Nächster

Deep learning-based super-resolution for GF-4 satellite imagery

  • role： First author第一作者
  • Affiliation：

    School of Geography and Planning, Center of Integrated Geographic Information Analysis, Sun Yat-sen University, Guangzhou 510275, China

    Guangdong Provincial Key Laboratory of Urbanization and Geo-simulation, Guangzhou 510275, China

  • Email：hzhdhz@126.com
  • Introduction：贺智，1988年生，女，副教授，研究方向为高光谱遥感、特征提取、模式识别和深度学习。E-mail：hzhdhz@126.com
HE Zhi12,  
  • Affiliation：

    City College of Dongguan University of Technology, Dongguan 511700, China

HE Dan3

Resümee

GF-4 is a geostationary orbit satellite launched under the support of the major special project of China’s high-resolution earth observation system. Notably, the spatial resolution of the medium-wave infrared channel in GF-4 satellite imagery is much lower than the corresponding visible near-infrared channels of the same scene. The resolution of the medium-wave infrared channel needs to be improved.In this study, a deep learning method termed as GF-4 Super-Resolution Network (GF-4-SRN) is proposed for super-resolution GF-4 satellite imagery. First, a convolutional regression network is designed for preliminary reconstruction of the original image. The convolutional regression network is trained using eight times down-sampled visible near-infrared channels and the original low-resolution medium-wave infrared channel. Thus, the correspondence between the visible near-infrared channels and the medium-wave infrared channel is developed. Second, a convolutional reconstruction network is designed to further reconstruct the preliminary results. This network is trained using the low-resolution preliminary reconstruction results and the original medium-wave infrared image. Notably, the convolutional reconstruction network can build the relationship between the preliminary reconstruction results and the medium-wave infrared image. Finally, the original visible near-infrared channels in GaoFen-4 satellite imagery are fed into the trained GF-4-SRN. The final super-resolution reconstruction results can be obtained by the relationship between visible near-infrared images and the medium-wave infrared image.Experiments are performed on two real-world GF-4 satellite images acquired from Hubei and Jiangxi regions. Experimental results demonstrate that the proposed GF-4-SRN method can effectively enhance the spatial resolution of the medium-wave infrared image. Compared with the root mean square error of state-of-the-art methods, that of the GF-4-SRN is reduced by at least 7.54. Moreover, the visual effects are much clearer and more natural. Therefore, the GF-4-SRN contributes to expanding the application range of the GF-4 satellite imagery.This paper proposes a deep learning-based super-resolution method for GF-4 satellite imagery. The proposed GF-4-SRN is composed of preliminary reconstruction by convolutional regression network and further reconstruction by convolutional reconstruction network. Experimental results on Hubei and Jiangxi regions demonstrate the effectiveness of the proposed GF-4-SRN. The spatial resolution is increased by fully utilizing the information provided by the visible near-infrared images. The root mean square error, erreur relative globale adimensionnelle de synthèse, and spectral angle mapper are lower than those of other methods. Meanwhile, the peak signal-to-noise ratio is higher than those of the competitors. Moreover, the visual effect of the results provided by the GF-4-SRN is much clearer and the reconstruction results contain more details. Notably, the deep learning-based method has great potential in super-resolution GF-4 satellite imagery.In the future, we will improve the GF-4-SRN by adopting various window sizes in the convolutional kernel. The network connection mode and optimization method can also be changed to improve the speed and performance of the network. The GF4-SRN will also be extended to other application areas, such as disaster monitoring.

Schlüsselwort

GF-4;super-resolution;reconstruction;deep learning;convolutional networks;Hubei;Jiangxi

References

  1. 1.
    Aiazzi B, Baronti S, Selva M. 2007. Improving component substitution pansharpening through multivariate regression of MS+Pan data. IEEE Transactions on Geoscience and Remote Sensing, 45(10): 3230-3239
  2. 2.
    Bevilacqua M, Roumy A, Guillemot C, Alberi-Morel M L. 2012. Low-complexity single-image super-resolution based on nonnegative neighbor embedding//British Machine Vision Conference. Surrey: BMVA Press: 1-10
  3. 3.
    Chen X Y, Zhang J, Cui T W and Song P J. 2018. Extraction of the green tide drift velocity in the Yellow Sea based on GF-4. Acta Oceanologica Sinica, 40(1): 29-38
  4. 4.
    Dong C, Loy C C, He K M and Tang X O. 2016. Image super-resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(2): 295-307
  5. 5.
    Gerchberg R W. 1974. Super-resolution through error energy reduction. Optica Acta: International Journal of Optics, 21(9): 709-720
  6. 6.
    Guo J, Ji C D, Yang J and Meng Q Y. 2018. Edge detection technique for GF-4 satellite imagery. Remote Sensing Information, 33(3): 108-115
  7. 7.
    Kim J, Lee J K and Lee K M. 2016. Accurate image super-resolution using very deep convolutional networks//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE: 1646-1654
  8. 8.
    Köhler T, Brost A, Mogalle K, Zhang Q Y, Köhler C, Michelson G, Hornegger J and Tornow R P. 2014. Multi-frame super-resolution with quality self-assessment for retinal fundus videos//Proceedings of the 17th International Conference on Medical Image Computing and Computer-Assisted Intervention. Boston: Springer: 650-657
  9. 9.
    Li X, Wei H W and Zhang H Q. 2018. Super-resolution reconstruction of single remote sensing image combined with deep learning. Journal of Image and Graphics, 23(2): 209-218
  10. 10.
    Liao W Z, Huang X, Van Coillie F, Gautama S, Pižurica A, Philips W, Liu H, Zhu T T, Shimoni M, Moser G and Tuia D. 2015. Processing of multiresolution thermal hyperspectral and digital color data: outcome of the 2014 IEEE GRSS data fusion contest. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(6): 2984-2996
  11. 11.
    Meng X C, Shen H F, Yuan Q Q, Li H F, Zhang L P and Sun W W. 2019. Pansharpening for cloud-contaminated very high-resolution remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 57(5): 2840-2854
  12. 12.
    Nie J, Deng L, Hao X L, Liu M and He Y. 2018. Application of GF-4 satellite in drought remote sensing monitoring: a case study of Southeastern Inner Mongolia. Journal of Remote Sensing, 22(3): 400-407
  13. 13.
    Pi Y D, Yang B and Li X. 2016. Block-adjustment and accuracy validation for GF4 patch-images based on RFM. Acta Geodaetica et Cartographica Sinica, 45(12): 1448-1454
  14. 14.
    Song T, Gong S Q, Liu J Z, Gu Z F, Shi J Z and Wu W. 2018. Performance assessment of atmospheric correction for multispectral data of GF-4 on inland case II Turbid water. Spectroscopy and Spectral Analysis, 38(4): 1191-1197
  15. 15.
    Sun Y J, Wang Z H, Qin Q M, Han G H, Ren H Z and Huang J F. 2018. Retrieval of surface albedo based on GF-4 geostationary satellite image data. Journal of Remote Sensing, 22(2): 220-233
  16. 16.
    Tian Y P, Zhou F, Yang W M, Shang X S and Liao Q M. 2016. Anchored neighborhood regression based single image super-resolution from self-examples//Proceedings of 2016 IEEE International Conference on Image Processing. Phoenix: IEEE: 2827-2831
  17. 17.
    Wang D Z and He H Y. 2017. Observation capability and application prospect of GF-4 satellite. Spacecraft Recovery and Remote Sensing, 38(1): 98-106
  18. 18.
    Wang M, Cheng Y F, Chang X L, Long X X and Li Q P. 2017. High accuracy on-orbit geometric calibration of geostationary satellite GF4. Acta Geodaetica et Cartographica Sinica, 46(1): 53-61
  19. 19.
    Wang Z T, Zhang Y H, Yuan S Y, Zhao S H, Zhou C Y, Chen H and Ma P F. 2016. The aerosol monitoring over Beijing-Tianjin-Hebei region from GF-4 data. Environment and Sustainable Development, (5): 113-116
  20. 20.
    Xu J P, Liang Y H, Liu J and Huang Z F. 2017. Multi-frame super-resolution of Gaofen-4 remote sensing images. Sensors, 17(9): 2142
  21. 21.
    Xu L N and He L X. 2017. GF-4 images super resolution reconstruction based on POCS. Acta Geodaetica et Cartographica Sinica, 46(8): 1026-1033
  22. 22.
    Yang G, Shen H F, Sun W W, Li J L, Diao N H and He Z Y. 2018. On the generation of gapless and seamless daily surface reflectance data. IEEE Transactions on Geoscience and Remote Sensing, 56(8): 4289-4306
  23. 23.
    Zeyde R, Elad M and Protter M. 2010. On single image scale-up using sparse-representations//Proceedings of the 7th International Conference on Curves and Surfaces. Avignon: Springer: 711-730
  24. 24.
    Zhang Z X, Shao Y, Tian W, Wei Q F, Zhang Y Z and Zhang Q J. 2017. Application potential of GF-4 images for dynamic ship monitoring. IEEE Geoscience and Remote Sensing Letters, 14(6): 911-915

Lesen Sie die ganze Passage

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website