Sharpening the VNIR-SWIR-TIR Bands of the WIS of Tiangong-2 for Mapping Land Use and Land Cover
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%).
KeywordsTiangong-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.
- 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
- 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. http://blog.digitalglobe.com/technologies/our-eyes-can-play-tricks-on-us-but-shortwave-infrared-swir-imagery-reveals-all-part-1-of-2. Last accessed 25 Jul 2018
- 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.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.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
- 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.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