Multi-high-resolution remote sensing image mosaic method considering surface feature category difference

Abstract

The invention discloses a multi-high-resolution remote sensing image mosaic method considering surface feature category difference. The method comprises the steps of performing geometric registrationand overlapping region coordinate determination on high-resolution images; performing color uniformization on the whole input image by using a histogram matching method by adopting an integral and local color matching strategy, and further performing local color uniformization on different ground objects by using a moment matching method; generating an initial seam line network by utilizing the Voronoi diagram; endowing different ground objects in the overlapping area with different weights, searching for a path with the minimum total weight in the buffer area based on a dynamic planning method, and taking the path as an optimized seam line network; and eliminating splicing seams by using an inverse distance weighted image fusion algorithm to obtain a final mosaic image. According to the method, the tone consistency of the mosaic image on the whole can be ensured, the local chromatic aberration can be remarkably weakened, the joint line network bypassing the building can be automatically generated, the error accumulation of searching the joint lines one by one is effectively avoided, and the mosaic image with visual nature is quickly obtained.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and relates to a method for mosaicing and processing multiple high-resolution remote sensing images in consideration of differences in types of ground objects. Background technique [0002] Due to the limitations of the physical factors of the sensor itself, the remote sensing image obtained by the sensor often cannot completely cover the research area of ​​interest with a single remote sensing image, so it is necessary to expand the coverage of the image to facilitate further processing and research. For imagery of the same size, the higher the spatial resolution, the smaller the coverage of a single image. In order to obtain the same study area of ​​interest, more high-resolution remote sensing images need to be stitched into one image. Image mosaic is to mosaic two or more images (with overlapping areas) together to form a natural image without obvious splicing traces....

AI Technical Summary

Problems solved by technology

[0005] In addition, after the traditional mosaic method finds a suitable seam line, it directly stitches the images together along the seam line

However, even after the leveling process, there will still be uneven transitions on both sides of the seam line, so the stitching seam needs to be eliminated

Commonly used seamline elimination methods include forced elimination correction, wavelet transformation, etc., but forced elimination correction may cause discontinuity in the buffer areas on both sides of the image. Wavelet transformation is relatively strict in theory, but it is very complicated to implement

Images