Précédent|Prochain

Multi-satellite integrated processing and analysis method under remote sensing big data

  • role： Corresponding author, First author通信作者, 第一作者
  • Affiliation：

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

    The Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China

    University of Chinese Academy of Sciences, Beijing 100101, China

  • Email：fukun@aircas.ac.cn
  • Introduction：付琨,1974年生,男,研究员,研究方向为遥感图像处理与分析、地理空间数据挖掘。E-mail: fukun@aircas.ac.cn
FU Kun123*,  
  • Affiliation：

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

    The Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China

    University of Chinese Academy of Sciences, Beijing 100101, China

SUN Xian123,  
  • Affiliation：

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

    The Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China

    University of Chinese Academy of Sciences, Beijing 100101, China

QIU Xiaolan123,  
  • Affiliation：

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

    The Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China

DIAO Wenhui12,  
  • Affiliation：

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

    The Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China

YAN Zhiyuan12,  
  • Affiliation：

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

    The Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China

    University of Chinese Academy of Sciences, Beijing 100101, China

HUANG Lijia123,  
  • Affiliation：

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

    The Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China

YU Hongfeng12

résumé

With the rapid development of aerospace technology and the continuous increase of China’s high resolution earth observation data acquisition in the past few decades, the era of remote sensing big data has coming now. Developing multi-satellite integrated data processing and application technology has become an important trend. In this paper, we systematically review the technological development process from two aspects, including multi-satellite imaging processing and multi-element information extraction. Then, we analyze the advantages and characteristics of the existing cutting-edge methods, and points out the main challenge of establishing the integrated processing model for imaging processing field and efficient learning model for information extraction field. On this basis, as well as according to the practical application requirements, a novel method of multi-satellite integrated processing and analysis under remote sensing big data is proposed in this paper. We emphatically define the basic concepts, scientific problems, research ideas and solutions of this method. On one hand, in terms of multi-satellite imaging processing, aiming at the problem of difficult estimation of high-dimensional coupled imaging parameters at high resolution, the various errors caused by the whole cycles of electromagnetic waves are calculated quantitatively, including payload error, platform error, data transmission error, atmospheric influence and so on. Then a multi-satellite integrated imaging processing physical model based on the Generative Adversarial Networks (GAN) is constructed to approximate estimate imaging parameters. In this way, we can achieve high-precision geometric corrections and radiation corrections, as well as generate high-quality remote sensing image products. On the other hand, in terms of multi-element information extraction, to solve the problem that the accuracy of the original tasks is difficult to maintain due to the addition of new tasks and requires full sample retraining, we design a multi-task feature sharing model based on few-shot incremental learning. It has a novel memory retention unit and multi-modal joint optimization of convex non-negative matrix factors. Through this model, we can generate parallel and high-precision annotations for multiple objects. Compared with the existing methods, the information between different satellites and payloads, different missions and objects are complementary to each other, leading to the simultaneous improvement of multi-sensor imaging quality and object extraction accuracy. The specific technical approach and preliminary experimental verification are given in detail in this paper. Experiments on multi-satellite imaging processing show that our method can effectively estimate multiple imaging errors. The phase estimation accuracy is within 1 degree when the signal-to-noise ratio is -5dB, which indicates the good performance even under low signal-to-noise ratio condition. At the same time, experiments on multi-element information extraction show that compared to single-modal method, our method, which uses multi-modal data in combination and embedded the novel memory retention unit, improve the extraction accuracy in multi-tasks of object detection and semantic segmentation. In the future, we will pay more attention to the disconnection problem between multi-satellite imaging processing and multi-element information extraction in the field of remote sensing. By establishing a benign mutual feedback mechanism between these two procedures to maximize the benefits of the remote sensing big data.

mots-clés

remote sensing big data;multi-satellite integrated;multi-satellite imaging processing;multi-element information analysis;Generative Adversarial Networks(GAN);multi-task

References

  1. 1.
    Bai J. 2019. Launch of Zhuhai-1 Group 03 Satellite [2021-01-20].
  2. 2.
    Bamler R. 1992. A comparison of range-doppler and wavenumber domain SAR focusing algorithms. IEEE Transactions on Geoscience & Remote Sensing, 30(4): 706-713
  3. 3.
    Bennett J R and Cumming I G. 1979. A digital processor for the production of seasat synthetic aperture radar imagery. Proc. SURGE Workshop, (154):16-18.
  4. 4.
    Benson M, Pierce L and Sarabandi K. 2017. Estimating the three-dimensional structure of the harvard forest using a database driven multi-modal remote sensing technique. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 5814-5817.
  5. 5.
    Breit H, Börner E, Mittermayer J, Holzner J and Eineder M. 2004. The TerraSAR-X multi-mode sar processor algorithms and design. Eusar, Ulm, May. DLR.
  6. 6.
    Bresnahan P C. 2011. Geolocation accuracy evaluations of commercial satellite imagery: challenges and results. The 34th Annual AAS Guidance and Control Conference.
  7. 7.
    Brockmann Consult GmbH. 2019. Calvalus Processing System [2021-01-25].
  8. 8.
    Chen K, Fu K, Gao X, Yan M and Sun X. 2019. Effective fusion of multi-modal data with group convolutions for semantic segmentation of aerial imagery. IEEE International Geoscience and Remote Sensing Symposium, 3911-3914.
  9. 9.
    Chen Q, He F, Yu A, Dong Z and Liang D. 2012. A multi-mode space-borne synthetic aperture radar signal processor. International Conference on Signal Processing (ICSP), Beijing, China: 2040-2043
  10. 10.
    Chen Y, Li G, Zhang Q and Sun J. 2017. Refocusing of moving targets in SAR images via parametric sparse representation. Remote Sensing, 9(8):795
  11. 11.
    Cheng C Q, Zhang J X, Huang G M, Zhang L and Yang J H. 2017. Combined positioning of TerraSAR-X and SPOT-5 HRS images with RFM considering accuracy information of orientation parameters. Acta Geodaetica et Cartographica Sinica, 46(2): 179-187
  12. 12.
    Cui L, Qiu X L, Guo J Y, Wen X J, Yang J Y and Fu K. 2020. Multi-channel phase error estimation method based on an error backpropagation algorithm for a multichannel SAR. Journal of Radars, 9(5): 878-885
  13. 13.
    Ding C B, Liu J Y, Lei B and Qiu X L. 2017. Preliminary exploration of systematic geolocation accuracy of gf-3 sar satellite system. Journal of Radars, 6(1): 11-16
  14. 14.
    Fernandez-Beltran R, Haut J M, Paoletti M E, Plaza J, Plaza A and Pla F. 2018. Remote sensing image fusion using hierarchical multimodal probabilistic latent semantic analysis. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(12):4982-4993
  15. 15.
    Grodecki J and Dial G. 2003. Block adjustment of high-resolution satellite images described by rational polynomials. Photogrammetric Engineering & Remote Sensing, 9(7): 12-28.
  16. 16.
    Helder D, Thome K J. Mishra N, Chander G and Choi T. 2013. Absolute radiometric calibration of landsat using a pseudo invariant calibration site. IEEE Transactions on Geoscience and Remote Sensing, 51(3): 1360-1369.
  17. 17.
    Hu F and Jin S Y. 2017. Analysis on the development of high-resolution optical remote sensing satellite wide-format imaging technology. Geomatics World,24(5): 45-50
  18. 18.
    Jeong J, Yang C and Kim T. 2015. Geo-positioning accuracy using multiple-satellite images: Ikonos, QuickBird, and Kompsat-2 stereo images. Remote Sensing, 7(4): 4549-4564
  19. 19.
    Jiao N G, Wang F, You H J, Qiu X L and Yang M D. 2019. Geolocation accuracy improvement of multiobserved GF-3 spaceborne SAR imagery. IEEE Geoscience and Remote Sensing Letters, (99):1-5
  20. 20.
    Jin H H. 2020. Look at the Huoshenshan hospital from 500 kilometers above [2021-01-20].
  21. 21.
    Kampffmeyer M, Salberg A B, Jenssen R. 2016. Semantic Segmentation of Small Objects and Modeling of Uncertainty in Urban Remote Sensing Images Using Deep Convolutional Neural Networks. 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Las Vegas, NV,2016, pp. 680-688.
  22. 22.
    Khalel A, Tasar O, Charpiat G and Tarabalka Y. 2019. Multi-task deep learning for satellite image pansharpening and segmentation. 2019 IEEE International Geoscience and Remote Sensing Symposium, 4869-4872.
  23. 23.
    Kusk A, Abulaitijiang A and Dall J. 2016. Synthetic SAR image generation using sensor, terrain and target models. Proceedings of EUSAR 2016: 11th European Conference on Synthetic Aperture Radar. Hamburg, Germany: VDE: 405-409.
  24. 24.
    Leberl F. 1973. Radargrammetry for Image Interpretation. Paris: International Institute for Aerial Survey and Earth.
  25. 25.
    Li C, Shen Y, Li B, Gang Q, Liu S, Wang W and Tong X. 2014. An improved geopositioning model of QuickBird high resolution satellite imagery by compensating spatial correlated errors. ISPRS Journal of Photogrammetry and Remote Sensing 96:12-19.
  26. 26.
    Li J, Zhang H and Zhang L. 2015. Efficient superpixel-oriented multi-task joint sparse representation classification for hyperspectral imagery. 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS),2592-2595.
  27. 27.
    Li K, Wan G, Cheng G, Meng L and Han J. 2019. Object detection in optical remote sensing images: A survey and a new benchmark. ISPRS Journal of Photogrammetry and Remote Sensing, 159:296-307
  28. 28.
    Li R, Zhou F, Niu X and Di K. 2007. Integration of Ikonos and QuickBird imagery for geopositioning accuracy analysis. Photogrammetric Engineering and Remote Sensing, 73(9):1067-1074
  29. 29.
    Li S Y, Zhang W F and Yang S. 2017. Intelligence fusion method research of multisource high-resolution remote sensing images. Journal of Remote sensing,21(3): 415-424
  30. 30.
    Liang J. 2017. Gaojing-1 satellite imagery parameters [2021-02-02].
  31. 31.
    Liebel L, Bittner K and Krner M. 2020. A generalized multi-task learning approach to stereo DSM filtering in urban areas. ISPRS Journal of Photogrammetry and Remote Sensing 166:213-227
  32. 32.
    Liu L, Yao F and Wang H. 2020. 2020 Global space launch reports [2021-01-16].
  33. 33.
    Liu Y, Minh Nguyen D, Deligiannis N, Ding W and Munteanu A. 2017. Hourglass-ShapeNetwork Based Semantic Segmentation for High Resolution Aerial Imagery. Remote Sensing, 9(6):522-535
  34. 34.
    Longbotham N, Pacifici F, Glenn T, Zare A, Volpi M, Tuia D, Christophe E, Michel J, Inglada J and Chanussot J. 2012. Multi-modal change detection, application to the detection of flooded areas: outcome of the 2009–2010 data fusion contest. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(1):331-342
  35. 35.
    Luo C and Ma L. 2018. Manifold regularized distribution adaptation for classification of remote sensing images. IEEE Access, 6: 4697-4708
  36. 36.
    Lyu G N, Tang X M, Ai B, Li T and Chen Q F. 2018. Hybrid geometric calibration method for multi-platform spaceborne sar image with sparse gcps. Acta Geodaetica et Cartographica Sinica, 47(7): 986-995
  37. 37.
    Ma D A, Tang P and Zhao L J. 2018. SiftingGAN: generating and sifting labeled samples to improve the remote sensing image scene classification baseline in vitro. IEEE Geoscience and Remote Sensing Letters, 16(7): 1046-1050
  38. 38.
    Malmgren-Hansen D, Kusk A, Dall J and Nielsen A. 2017. Engholm R and Skriver H. Improving SAR automatic target recognition models with transfer learning from simulated data. IEEE Geoscience and Remote Sensing Letters, 14(9): 1484-1488
  39. 39.
    Meng D, Ding C, Hu D, Qiu X, Huang L, Han B, Liu J and Xu N. 2017. On the processing of very high resolution spaceborne SAR data:a chirp-modulated back projection approach. IEEE Transactions on Geoscience and Remote Sensing, 99: 1-11
  40. 40.
    Meng D, Hu D and Ding C. 2015. Precise focusing of airborne SAR data with wide apertures large trajectory deviations:a chirp modulated back-projection approach. IEEE Transactions on Geoscience and Remote Sensing, 53(5): 2510-2519
  41. 41.
    Nan K, Qi H and Ye Y X. 2019. A template matching method of multimodal remote sensing images based on deep convolutional feature representation. Acta Geodaetica et Cartographica Sinica, 48(6): 727-736
  42. 42.
    Pan H B, Zhang G, Tang X M, Wang X, Zhou P, Xu M Z and Li D R. 2013. Analysis and verification of the accuracy of the image products of the zy-3 surveying and mapping satellite. Acta Geodaetica et Cartographica Sinica, 042(005):738-744
  43. 43.
    Papadomanolaki M, Karantzalos K and Vakalopoulou M. 2019. A multi-task deep learning framework coupling semantic segmentation and image reconstruction for very high-resolution imagery. 2019 IEEE International Geoscience and Remote Sensing Symposium.
  44. 44.
    Papoulis A. 1968. System and transforms with applications in optics. New York: McGraw-Hill.
  45. 45.
    Qiu X, Hu D and Ding C. 2008. An improved NLCS algorithm with capability analysis for one-stationary BiSAR. IEEE Transactions on Geoscience & Remote Sensing, 46(10): 3179-3186
  46. 46.
    Rao M B, Tang P and Zhang Z. 2019. Spatial-spectral relation network for hyperspectral image classification with limited training samples. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(12): 5086-5100
  47. 47.
    Rosa L, Zortea M, Gemignani B H, Oliveira D and Feitosa R. 2020. FCRN-based multi-task learning for automatic citrus tree detection from uav images. 2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS), 403-408
  48. 48.
    Shao Q, Wang S Y, Yang C X and Zhang X H. 2017. Landsat 5 tm, landsat 7 etm+ and landsat 8 oli cross calibration research. Industry and Technology Forum, 16(017): 54-57
  49. 49.
    Shi J, Shao T, Liu X, Zhang X and Lei Y. 2020. Evolutionary multi-task ensemble learning model for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,99:1-15[10.1109/JSTARS.2020.3037353]
  50. 50.
    Tang S, Wu B, Zhu Q. 2016. Combined adjustment of multi-resolution satellite imagery for improved geo-positioning accuracy. ISPRS Journal of Photogrammetry & Remote Sensing, 114:125-136
  51. 51.
    Thome K, Mccorkel J and Czapla-Myers J. 2013. In-situ transfer standard and coincident-view intercomparisons for sensor cross-calibration. IEEE Transactions on Geoscience and Remote Sensing, 51(3): 1088-1097.
  52. 52.
    UCS satellite database [2021-01-15].
  53. 53.
    Viktor M S and Kenneth C. 2013. Big Data: A Revolution That Will Transform How We Live, Work and Think. London: Hodder
  54. 54.
    Volpi M and Tuia D. 2018. Deep multi-task learning for a geographically-regularized semantic segmentation of aerial images. ISPRS journal of photogrammetry and remote sensing, 144: 48-60
  55. 55.
    Wahl D E and Eichel P H. 1994. Phase gradient autofocus-a robust tool for high resolution SAR phase correction. IEEE Transactions on Aerospace and Electronic Systems, 30(3): 827-834
  56. 56.
    Wang Y, Ding W, Zhang R and Li H. 2020. Boundary-aware multi-task learning for remote sensing imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, (99):1-15
  57. 57.
    Wei Z Q. 2001. Synthetic aperture radar satellite. Beijing: Science Press. (魏钟铨. 2001. 合成孔径雷达卫星. 北京：科学出版社.)
  58. 58.
    Wivell C E, Steinwand D R, Kelly G G and Meyer D J. 2002. Evaluation of terrain models for the geocoding and terrain correction, of synthetic aperture radar (SAR) images. IEEE Transactions on Geoscience & Remote Sensing, 30(6), 1137-1144
  59. 59.
    Wu Y D and Ming Y. 2012. Multi-source SAR image joint positioning method lacking ground control points. Journal of Hubei University of Technology. 27(4): 13-17.
  60. 60.
    Xinhua News Agency. 2020. Through the clouds and soaking rain! High-resolution satellite hits the red flood warning of the Yangtze River [2021-01-12].
  61. 61.
    Yang L, Fu Q Y, Pan Z Q, Zhang X W, Han Q J and Liu L. 2015. Research on Radiation Cross Calibration of Gaofen-1 Satellite Camera. Infrared and Laser Engineering, 44(8): 2456-2456
  62. 62.
    Yan Y M, Tan Z C and Su N. 2019. A data augmentation strategy based on simulated samples for ship detection in rgb remote sensing images. ISPRS International Journal of Geo-Information, 8(6): 276
  63. 63.
    Zhan Y, Hu D, Wang Y T and Yu X C. 2017. Semisupervised hyperspectral image classification based on generative adversarial networks. IEEE Geoscience and Remote Sensing Letters, 15(2): 212-216
  64. 64.
    Zhang L, Dong H and Zou B. 2019. Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework. ISPRS Journal of Photogrammetry and Remote Sensing, 157: 59-72
  65. 65.
    Zhang G, Li Z, Pan H B, Qiang Q and Zhai L. 2011. Orientation of spaceborne SAR stereo pairs employing the RPC adjustment model. IEEE Transactions on Geoscience and Remote Sensing, 49(7): 2782-2792
  66. 66.
    Zhang S W. 2020. More than 30 satellites escort the fight against the epidemic [2021-01-20]. .
  67. 67.
    Zhang Y, Du B, Zhang L and Liu T. 2016. Joint sparse representation and multitask learning for hyperspectral target detection. IEEE Transactions on Geoscience and Remote Sensing, 55(2): 894-906
  68. 68.
    Zhang Y H, Lin Z J, Zhang J X and Gan M L. 2002. SAR image geometric correction. Acta Geodaetica et Cartographica Sinica, 31(2):134-138
  69. 69.
    Zhang Y H, Zhong B, Yang F J and Liu Q H. 2012. BRDF feature extraction based on TM/ETM and DEM data. Journal of Remote Sensing, 16(2):361-377
  70. 70.
    Zhang Y H, Sun H, Zuo J W, Wang H Q, Xu G L and Sun X. 2018. Aircraft type recognition in remote sensing images based on feature learning with conditional generative adversarial networks. Remote Sensing, 10(7): 1123
  71. 71.
    Zhou X and Prasad S. 2018. Deep feature alignment neural networks for domain adaptation of hyperspectral data. IEEE Transactions on Geoscience and Remote Sensing, 56(10): 5863-5872
  72. 72.
    Zhu L, Chen Y S, Ghamisi P and Benediktsson J A. 2018. Generative adversarial networks for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 56(9): 5046-5063

Lire l'article complet

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