• Journal of Infrared and Millimeter Waves
  • Vol. 42, Issue 4, 538 (2023)
Peng WANG1、2、3, Yong-Kang CHEN3, Gong ZHANG3, Hong-Ying WANG4, Chun-Lei ZHAO5, and Ling HAN6、*
Author Affiliations
  • 1Key Laboratory of Southeast Coast Marine Information Intelligent Perception and Application,Ministry of Natural Resources,Zhangzhou Institute of Surveying and Mapping,Zhangzhou 363000,China
  • 2Anhui Province Key Laboratory of Physical Geographic Environment,Chuzhou University,Chuzhou 239000,China
  • 3College of Electronic and Information Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China
  • 4School of Management,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
  • 5Key Laboratory of Meteorology and Ecological Environment of Hebei Province,Meteorological Institute of Hebei,Shijiazhuang 050021,China
  • 6Xi’an Key Laboratory of Territorial Spatial Information,Chang'an University,Xi’an 710064,China
  • show less
    DOI: 10.11972/j.issn.1001-9014.2023.04.001 Cite this Article
    Peng WANG, Yong-Kang CHEN, Gong ZHANG, Hong-Ying WANG, Chun-Lei ZHAO, Ling HAN. Sub-pixel mapping based on spectral information of irregular scale areas for hyperspectral images[J]. Journal of Infrared and Millimeter Waves, 2023, 42(4): 538 Copy Citation Text show less
    Spatial information in(a)the rectangular local window and(b)the irregular scale areas
    Fig. 1. Spatial information in(a)the rectangular local window and(b)the irregular scale areas
    The flowchart of SIISA
    Fig. 2. The flowchart of SIISA
    Multispectral images covering Rome, Italy,(a)RGB of multispectral image,(b)coarse image(S=8)
    Fig. 3. Multispectral images covering Rome, Italy,(a)RGB of multispectral image,(b)coarse image(S=8)
    Hyperspectral images covering University of Pavia, Italy,(a)RGB of hyperspectral image,(b)coarse image(S=8)
    Fig. 4. Hyperspectral images covering University of Pavia, Italy,(a)RGB of hyperspectral image,(b)coarse image(S=8
    Hyperspectral images covering Xiong'an New Area, China,(a)RGB of hyperspectral image,(b)coarse image(S=10)
    Fig. 5. Hyperspectral images covering Xiong'an New Area, China,(a)RGB of hyperspectral image,(b)coarse image(S=10
    Mapping results,(a)reference image,(b)SSI,(c)PSSD,(d)OSI,(e)RWA,(f)SIISA
    Fig. 6. Mapping results,(a)reference image,(b)SSI,(c)PSSD,(d)OSI,(e)RWA,(f)SIISA
    Mapping results,(a)reference image,(b)SSI,(c)PSSD,(d)OSI,(e)RWA,(f)SIISA
    Fig. 7. Mapping results,(a)reference image,(b)SSI,(c)PSSD,(d)OSI,(e)RWA,(f)SIISA
    Mapping results,(a)reference image,(b)SSI,(c)PSSD,(d)OSI,(e)RWA,(f)SIISA
    Fig. 8. Mapping results,(a)reference image,(b)SSI,(c)PSSD,(d)OSI,(e)RWA,(f)SIISA
    Salient region,(a)reference image,(b)SSI,(c)PSSD,(d)OSI,(e)RWA, and(f)SIISA
    Fig. 9. Salient region,(a)reference image,(b)SSI,(c)PSSD,(d)OSI,(e)RWA, and(f)SIISA
    Values of(a)OA(%)and(b)Kappa obtained using the five different sub-pixel methods under different values of S
    Fig. 10. Values of(a)OA(%)and(b)Kappa obtained using the five different sub-pixel methods under different values of S
    OA(%)value of the SIISA in relation to weight parameter β in(a)experiments 2 and(b)3
    Fig. 11. OA(%)value of the SIISA in relation to weight parameter β in(a)experiments 2 and(b)3
    OA(%)value of the SIISA in relation to segmentation scale parameter V in(a)experiments 2 and(b)3
    Fig. 12. OA(%)value of the SIISA in relation to segmentation scale parameter V in(a)experiments 2 and(b)3
    ClassSSIPSSDOSIRWASIISA
    Vegetation(%)66.9969.2871.2073.3974.88
    Building(%)76.0674.2778.2680.7284.31
    Soil(%)61.6664.4567.4469.6471.37
    OA(%)70.1071.4573.7376.0578.67
    Kappa0.525 00.545 50.583 00.622 50.656 6
    Table 1. Accuracy evaluation of the five methods
    ClassSSIPSSDOSIRWASIISA
    Shadow(%)49.2355.5657.4460.2961.94
    Water(%)96.8596.6897.0197.2897.77
    Road(%)64.9962.0868.6470.3778.39
    Tree(%)75.1175.9678.7080.2584.04
    Grass(%)71.0074.3375.4978.3979.87
    Rooftop(%)76.3278.8780.5983.0683.62
    OA(%)77.9478.8881.1583.1985.22
    Kappa0.726 50.738 70.765 90.797 70.815 7
    Table 2. Accuracy evaluation of the five methods
    Peng WANG, Yong-Kang CHEN, Gong ZHANG, Hong-Ying WANG, Chun-Lei ZHAO, Ling HAN. Sub-pixel mapping based on spectral information of irregular scale areas for hyperspectral images[J]. Journal of Infrared and Millimeter Waves, 2023, 42(4): 538
    Download Citation