Information processing of stumpage in forest area is a key content of forestry intellectualisation research. In this study, instead of the traditional three-dimensional laser measurement, an enhanced algorithm for the fusion of infrared and visible images is introduced. The proposed method initially utilises the non-subsampled Contourlet transform (NSCT) to decompose the images into their respective low and high-frequency sub-bands. Subsequently, the fusion of the low-frequency sub-bands is executed using a regional energy-based method supplemented by fuzzy logic to determine the fusion coefficients. In contrast, the high-frequency sub-bands are fused by assessing the regional gradient differences. The process culminates in the reconstruction of the fused images through the application of the NSCT inverse transform. In this paper, stumpage images in forest are taken as experimental objects. The results show that the algorithm enhances the edge of images and improves the quality of images, which provides a powerful information basis for subsequent stumpage recognition.
Ding et al. (Thu,) studied this question.