Früher|Nächster

Multispectral image dataset of Tiangong-2 for port cities along the Belt and Road

  • role： First author第一作者
  • Affiliation：

    Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing 100094, China

  • Email：qinby@csu.ac.cn
  • Introduction：覃帮勇，1987年生,男,助理研究员,研究方向为航天数据处理、数据质量分析与控制方法。E-mail:qinby@csu.ac.cn
QIN Bangyong1,  
  • Affiliation：

    Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing 100094, China

WAN Xue1,  
  • Affiliation：

    Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing 100094, China

XUAN Shiyu1,  
  • role： Corresponding author通信作者
  • Affiliation：

    Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing 100094, China

  • Email：shyli@csu.ac.cn
  • Introduction：李盛阳，1976年生，男,研究员,研究方向为航天地面数据系统技术、空间科学大数据技术、遥感图像智能分析与理解。E-mail: shyli@csu.ac.cn
LI Shengyang1*,  
  • Affiliation：

    Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing 100094, China

LIU Kang1

Resümee

Port cities play a vital role in the implementation of the Belt and Road initiative. Remote sensing data can provide effective information support for the dynamic monitoring of port cities. In this paper, 58 groups of high-quality multispectral image data obtained by the wide-band imaging spectrometer of Tiangong-2 at different times are selected to construct the thematic dataset of 25 port cities along the Belt and Road. This dataset can provide important support for the remote sensing monitoring in resources and environment of the port cities and its surrounding area along the Belt and Road.Firstly, The raw data of wide-band imaging spectrometer undergo through a series of processing steps, such as format analyzing, field of view combination, homogeneity correction, image framing, absolute radiometric correction, geometric correction and format packaging, to generate standard data products and its auxiliary files. Then, image quality evaluation indexes, including signal to noise ratio, information entropy, clarity, contrast, radiation uniformity, etc. are adopted to assess data quality and to select high quality data products. Calibration and data quality control methods are used to improve the accuracy of data products. At last, several typical convolution neural network algorithms are used to verify the application potential of the data set in scene classification and recognition.350 typical port and non-port image samples are extracted from the data set in this article and be marked manually. After data enhancement, 250 samples of them are used to train several typical convolutional neural networks, they are AlexNet, VGG16, ResNet18 and MobileNet-v2, and the remaining samples are used for verification. The average recognition accuracy of the four algorithms is 91%, in which Resnet18 and MobileNet-v2 networks have the highest accuracy rate (93%), Resnet18 network has more advantages than other networks in precision rate, VGG16 and MobileNet-v2 network have the highest recall rate. Therefore, the dataset is suitable for the common convolutional neural networks and has good application effect in the scene classification and recognition of port city.The multispectral remote sensing image data set constructed in this paper comes from the wide-band imaging spectrometer of Tiangong-2. It has the characteristics of wide spectral range, high spatial resolution and diverse observation time, and is a beneficial extension for the existing data set of the port city along the Belt and Road. After strictly data processing and data quality control, the image data has standard format and reliable quality. Some of them has been applied in many fields, such as ocean, land, ecology and environment. In addition, it has a good application effect in the scene classification and recognition of port city. This data set is a valuable data resource for the remote sensing applications of the port city and its surrounding areas along the Belt and Road.

Schlüsselwort

Tiangong-2;Wide-band Imaging Spectrometer;the Belt and Road;port city;remote sensing image data set

References

  1. 1.
    Bai Z G. 2007. HY-1B ocean satellite. Aerospace China, (4): 12-15
  2. 2.
    Barnes W L and Salomonson V V. 1992. MODIS: a global imaging spectroradiometer for the Earth Observing System//Proceedings Volume 10269, Optical Technologies for Aerospace Sensing: A Critical Review. Boston, MA, United States: SPIE: 285-307
  3. 3.
    Bu Y D. 2012. Research on Image Texture Feature Extraction. Ji’nan: Shandong Normal University
  4. 4.
    Cong P F, Chen K X, Qu L M and Han J B. 2019. Temporal and spatial changes of the Yellow River delta wetland based on Multi-Source data during 30 years//Proceedings of the Tiangong-2 Remote Sensing Application Conference, Lecture Notes in Electrical Engineering. Singapore: Springer, 541: 286-299
  5. 5.
    Curran P J and Steele C M. 2005. MERIS: the re-branding of an ocean sensor. International Journal of Remote Sensing, 26(9): 1781-1798
  6. 6.
    Gao M. 2019. Earth observation payloads and data applications of Tiangong-2 space laboratory//Proceedings of the Tiangong-2 Remote Sensing Application Conference, Lecture Notes in Electrical Engineering. Singapore: Springer, 541: 1-13
  7. 7.
    Guo B, Fan Y W, Yang F, Jiang L, Yang W N, Chen S T, Gong R and Liang T. 2019. Quantitative assessment model of ecological vulnerability of the Silk Road Economic Belt, China, utilizing remote sensing based on the partition-integration concept. Geomatics, Natural Hazards and Risk, 10(1): 1346-1366
  8. 8.
    He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV: IEEE: 770-778
  9. 9.
    Hu Y F and Zhang Y F. 2007. Analysis of relative radiometric calibration accuracy of space camera. Spacecraft Recovery and Remote Sensing, 28(4): 54-57
  10. 10.
    Krizhevsky A, Sutskever I and Hinton G E. 2012. ImageNet classification with deep convolutional neural networks//Proceedings of the 25th International Conference on Neural Information Processing Systems. Red Hook, NY, United States: Curran Associates Inc.: 1097-1105
  11. 11.
    Li J, Xing Q G, Liu H L and Yu L. 2019. Radiometric cross-calibration between the thermal infrared data of MODIS and Tiangong-2 WIS for monitoring sea surface temperature//Proceedings of the Tiangong-2 Remote Sensing Application Conference, Lecture Notes in Electrical Engineering. Singapore: Springer, 541: 192-200
  12. 12.
    Li S Y, Zhang W F, Liu Z W, Tan H, Yu H J, Wang B, Mu L L and Li X. 2019. Tiangong-2 ground data processing and service system towards multiple categories of payloads product processing//Proceedings of the Tiangong-2 Remote Sensing Application Conference, Lecture Notes in Electrical Engineering. Singapore: Springer, 541: 61-70
  13. 13.
    Liu K, Qin B Y, Mu L L and Li S Y. 2017. Monitoring and analysing of reclamation change based on multi-data remote sensing images: a case study of partial area of Liaoning province. Marine Environmental Science, 36(6): 911-917
  14. 14.
    Liu K, Qin B Y and Li S Y. 2018. The application of the Tiangong-2 Wide-Band imaging spectrometer data in the ecological environment evaluation: a case study of Kunming//Proceedings of the International Workshop on Environment and Geoscience. Hangzhou, China: [s.n.], 1: 469-476
  15. 15.
    Liu Q H, Wu J J, Li L, Yu L, Li J, Xin X Z, Jia L, Zhong B, Niu Z, Xu X L, Meng Q Y, Zhao J, Zhang H L, Hu G C and Zheng C L. 2018. Ecological environment monitoring for sustainable development goals in the Belt and Road region. Journal of Remote Sensing, 22(4): 686-708
  16. 16.
    Liu W D. 2015. Scientific understanding of the Belt and Road Initiative of China and related research themes. Progress in Geography, 34(5): 538-544
  17. 17.
    Liu X P and Sun S J. 2015. Application of domestic remote sensing satellite in ecological environment protection in the construction of the Belt and Road. Satellite Application, (8): 52-54
  18. 18.
    Luo R, Zhou J, Yang J J, Ai L J and Feng Y L. 2019. Downscaling of Tiangong-2 land surface temperature//Proceedings of the Tiangong-2 Remote Sensing Application Conference, Lecture Notes in Electrical Engineering. Singapore: Springer, 541: 170-179
  19. 19.
    Qin B Y, Hong B, Zhang Z, Yang X F and Li Z W. 2014. A generally applicable noise-estimating method for remote sensing images. Remote Sensing Letters, 5(5): 481-490
  20. 20.
    Qin B Y, Shang R, Li S Y, Hei B Q and Liu Z W. 2015. Reliable clarity automatic-evaluation method for optical remote sensing images//Proceedings Volume 9675, AOPC 2015: Image Processing and Analysis. Beijing, China: SPIE, 9675: 967533 [DOI: 10.1117/12.2202971]
  21. 21.
    Qin B Y, Li S Y, Hao Z W, Liu K and Wang B. 2017. Earth observation data of the Tiangong-2 Space Laboratory 2016-2017). China Scientific Data, 2(4
  22. 22.
    Qin B Y, Li L J and Li S Y. 2018. Data quality evaluation and application potential analysis of Tiangong-2 wide-band imaging spectrometer//The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Beijing, China: [s.n.], XLII-3: 1427-1431
  23. 23.
    Sandler M, Howard A, Zhu M L, Zhmoginov A and Chen L C. 2018. MobileNetV2: inverted residuals and linear bottlenecks//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE: 4510-4520
  24. 24.
    Shi M, Chen J, Qin B Y and Li S Y. 2018. Inversion of land surface temperature and its application in urban agglomeration thermal environment monitoring based on Tiangong-2 data. Remote Sensing Technology and Application, 33(5): 811-819
  25. 25.
    Simonyan K and Zisserman A. 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556
  26. 26.
    Song Y and Hou X Y. 2017. A dataset of land cover classification in 25 port cities and their surrounding areas along “One Belt and One Road” (2015). China Scientific Data, 2(3) (宋洋, 侯西勇. 2017. 2015年“一带一路”25个港口城市及其周边区域土地覆盖分类数据集. 中国科学数据, 2(3))
  27. 27.
    Tang R G, Shen F, Pan Y Q, Liu K, Li M Y, Gao W L and Zang C K. 2019. Cross-Comparison of ocean color products derived from Tiangong-2/WIS and GOCI in the Yangtze estuary, China//Proceedings of the Tiangong-2 Remote Sensing Application Conference, Lecture Notes in Electrical Engineering. Singapore: Springer, 541: 201-211
  28. 28.
    Tang Y Y, Wei J, Huang X X, Feng X and Song Q J. 2019. Research on on-Board calibration system of Tiangong-2 Wide-Band Imaging Spectrometer//Proceedings of the Tiangong-2 Remote Sensing Application Conference, Lecture Notes in Electrical Engineering. Singapore: Springer, 541: 28-39
  29. 29.
    Wei J H. 2016. The Tiangong-2 has been successfully launched which is China's first space laboratory. Aerospace China, (10): 9 (魏京华. 2016. 我国首个空间实验室天宫二号发射成功. 中国航天, (10): 9)
  30. 30.
    Xing J and Meng D. 2019. Wetland monitoring application in Panjin City based on remote sensing data of Wide-Band Imaging Spectrometer of Tiangong-2//Proceedings of the Tiangong-2 Remote Sensing Application Conference, Lecture Notes in Electrical Engineering. Singapore: Springer, 541: 300-311
  31. 31.
    Zhou Y J and Tian Q J. 2008. Image quality evaluation of EO-1 Hyperion sensor. Geo-Information Science, 10(5): 678-683
  32. 32.
    Zou J L, Liu C L, Yin G Q and Tang Z P. 2015. Spatial patterns and economic effects of China's trade with countries along the Belt and Road. Progress in Geography, 34(5): 598-605

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