MSGF-GLP: fusion method of visible and hyperspectral data for early detection of discolored standing trees

Pest and disease damage to forests cannot be underestimated, so it is essential to detect diseased trees in time and take measures to stop their spread. The detection of discoloration standing trees is one of the important means to effectively control the spread of pests and diseases. In the visible wavelength range, early infected trees do not show significant color changes, which poses a challenge for early detection and is only suitable for monitoring middle and late discolor trees. The spectral resolution of hyperspectral restricts the improvement of its spatial resolution, and there are phenomena of different spectral of the same and foreign objects in the same spectrum, which affect the detection results. In this paper, the method of hyperspectral and CCD image fusion is used to achieve high-precision detection of discoloration standing trees. This paper proposes an improved algorithm MSGF-GLP, which uses multi-scale detail boosting and MTF filter to refine high-resolution data. By combining guided filtering with hyperspectral images, the spatial detail difference is enhanced, and the injection gain is interpolated into the difference of each band, so as to obtain high-resolution and high-quality hyperspectral images. This research is based on hyperspectral and CCD data obtained from LiCHy, Chinese Academy of Forestry, Maoershan Experimental Forest Farm, Shangzhi City, Heilongjiang Province. The evaluation framework is used to compare with the other five fusion algorithms to verify the good effect of the proposed method, which can effectively preserve the canopy spectrum and improve the spatial details. The fusion results of forestry remote sensing data were analyzed using the vegetation Normalized Difference Water Index and Plant Senescence Reflectance Index. The fused results can be used to distinguish the difference between discoloration trees and healthy trees by the multispectral vegetation index. The research results can provide good technical support for the practical application of forest remote sensing data fusion, and lay the foundation for promoting the scientific, automatic and intelligent forestry control.