Sharpening the VNIR-SWIR-TIR Bands of the WIS of Tiangong-2 for Mapping Land Use and Land Cover

  • Qingsheng LiuEmail author
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 541)


Land use and land cover maps derived from satellite remote sensing imagery are important to support landscape ecology and natural resource protecting and planning, especially over large areas. The classification information resulted from combination of the visible and near infrared bands (VNIR), shortwave infrared bands (SWIR) and thermal infrared bands (TIR) should be better than those obtained using the VNIR, SWIR and TIR images separately. Nonetheless, assessment on improvement for mapping land use and land cover based on the combination of the VNIR, SWIR and TIR imagery remain scarce. This paper evaluates the random forest classification results from four combinations from the VNIR, SWIR and TIR of the Wide-band Imaging Spectrometer onboard the Tiangong-2. The result showed that combination of fourteen VNIR bands with two TIR bands had produced the best result (overall accuracy (OA) = 84.29%), followed by the combination of fourteen VNIR bands with two SWIR bands (84.13%), then the combination of fourteen VNIR bands and two SWIR bands and two TIR bands (83.73%). Only fourteen VNIR bands had produced the worst classification result (83.5%).


Tiangong-2 VNIR SWIR TIR Gram-Schmidt sharpening Random forest 



This research work was jointly financially supported by the National Natural Science Foundation of China (Project No.41671422, 41661144030). Thanks to China Manned Space Engineering for providing the Tiangong-2 space science and application data products.


  1. 1.
    Radoux, J., Chome, G., Jacques, D.C., Waldner, F., Bellemans, N., Matton, N., Lemarche, C., dAndrimont, R., Defourny, P.: Sentinel-2’s potential for sub-pixel landscape feature detection. Remote Sens. 8, 488 (2016)CrossRefGoogle Scholar
  2. 2.
    Matheson, D.S., Dennison, P.E.: Evaluating the effects of spatial resolution on hyperspectral fire detection and temperature retrieval. Remote Sens. Environ. 124, 780–792 (2012)CrossRefGoogle Scholar
  3. 3.
    Jung, H.S., Park, S.W.: Multi-sensor fusion of Landsat 8 thermal infrared (TIR) and panchromatic (PAN) images. Sensors 14, 24425–24440 (2014)CrossRefGoogle Scholar
  4. 4.
    Milewski, R., Chabrillat, S., Eisele, A.: VNIR-SWIR-TIR hyperspectral airborne campaign for soil and sediment mapping in semi-arid SouthAfrican environments. In: EGU General Assembly 2016, EGU2016-18438, Vienna, Austria (2016)Google Scholar
  5. 5.
    Sanchez-Ruiz, S., Piles, M., Sanchez, N., Martinez-Fernandez, J., Vall-llossera, M., Camps, A.: Combing SMOS with visible and near/shortwave/thermal infrared satellite data for high resolution soil moisture estimates. J. Hydrol. 516, 273–283 (2014)CrossRefGoogle Scholar
  6. 6.
    Yong, D.K.: Our SWIR imagery product is now available, at the highest resolution ever from space, only from DigitalGlobe, our eyes can play tricks on us but shortwave infrared (SWIR) imagery reveals all. Last accessed 25 Jul 2018
  7. 7.
    Agam, N., Kustas, W.P., Anderson, M.C., Li, F.Q., Neale, C.M.U.: A vegetation index based technique for spatial sharpening of thermal imagery. Remote Sens. Environ. 107, 545–558 (2007)CrossRefGoogle Scholar
  8. 8.
    Padwick, C., Deskevich, M., Pacifici, F., Smallwood, S.: WorldView-2 pan-sharpening. In: ASPRS 2010 Annual Conference, San Diego, California, USA (2010)Google Scholar
  9. 9.
    Tonooka, H.: Resolution enhancement of ASTER shortwave and thermal infrared bands based on spectral similarity. In: Proceeding of SPIE 5657, Image Processing and Pattern Recognition in Remote Sensing II, SPIE, Bellingham, WA, pp. 9–19 (2005)Google Scholar
  10. 10.
    Lanaras, C., Biouca-Dias, J., Baltsavias, E., Schindler, K.: Super-resolution of multispectral multiresolution images from a single sensor. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, USA, pp. 20–28 (2017)Google Scholar
  11. 11.
    Ko, B.C., Kim, H.H., Nam, J.Y.: Classification of potential water bodies using Landsat 8 OLI and a combination of two boosted random forest classifiers. Sensors 15(6), 13763–13777 (2015)CrossRefGoogle Scholar
  12. 12.
    Wang, H., Zhao, Y., Pu, R.L., Zhang, Z.Z.: Mapping RobiniaPseudoacacia forest health conditions by using combined spectral, spatial and textural information extracted from IKONOS imagery and random forest classifier. Remote Sens. 7(7), 9020–9044 (2015)CrossRefGoogle Scholar
  13. 13.
    Pu, R.L., Landry, S., Yu, Q.Y.: Assessing the potential of multi-seasonal high resolution Pleiades satellite imagery for mapping urban tree species. Int. J. Appl. Earth Obs. Geoinf. 71, 144–158 (2018)CrossRefGoogle Scholar
  14. 14.
    Berbstein, L.S., Jin, X.M., Gregor, B., Adler-Golden, S.M.: Quick atmospheric correction code: algorithm description and recent upgrades. Opt. Eng. 51, 111719 (2012)CrossRefGoogle Scholar
  15. 15.
    Liu, Q.S., Li, X.Y., Liu, G.H., Huang, C., Li, H., Guan, X.D.: Sharpening of the VNIR and SWIR bands of the wide band spectral imager onboard Tiangong-II imagery using the selected bands. In: the International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Beijing, China, vol. XLII-3, pp. 1085–1092 (2018)CrossRefGoogle Scholar
  16. 16.
    Liu, Q.S.: Sharpening the WBSI imagery of Tiangong-II: Gram-Schmidt and principal components transform in comparison. In: 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD 2018), Huangshan, China, pp. 524–531 (2018)Google Scholar
  17. 17.
    Ismail, R., Mutanga, O.A.: A comparison of regression tree ensembles: predicting Sirexnoctilio induced water stress in Pinuspatula forest of KwaZulu-Natal, South Africa. Int. J. Appl. Earth Obs. Geoinf. 12, 45–51 (2010)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of SciencesBeijingChina

Personalised recommendations