The application discloses a multi-scale lining
image splicing method in a tunnel detection
parallax scene and a
computer program product, relates to the technical field of
computer vision, and solves the technical problem that a lining
image splicing method has poor adaptability and is difficult to guarantee the quality of lining
image splicing. The method comprises the following steps: performing feature
map matching on a first image and a second image to obtain an initial global
homography matrix; performing multi-scale matrix iterative optimization and global alignment feature map generation to obtain an optimal global
homography matrix; performing local non-rigid adjustment on the second image through a TPS interpolation
algorithm; extracting an initial
mask from the registered first image and the second image, and generating a joint
mask; searching for optimal seam lines in the joint
mask to generate a content mask; and performing fusion
processing on the registered first image and the second
image based on the content mask, and outputting a panoramic image. The application has good adaptability to scenes with different
parallax degrees, and the quality of lining image splicing is greatly improved.