Night panoramic image stitching algorithm based on cyclic symmetric structure

Abstract

Aiming at the problem that the current stitching image has poor visual effect and low stitching efficiency when performing the night panoramic image stitching task, a night panoramic image stitching algorithm based on cyclic symmetric structure is proposed. In this algorithm, appropriate image acquisition method is used and the image obtained by the acquisition is smoothed, edge sharpened, geometrically corrected, etc. The position of the key point of the preprocessed image and the corresponding scale are determined by Gaussian function, and the direction value is assigned to the feature point to generate the feature descriptor, so as to realize the image edge feature extraction; on this basis, the edge feature points are hierarchically segmented according to the topological structure of the edge feature point set of target image, and the edge feature point registration of night panoramic image is completed; the cyclic symmetric structure is used to make the discrete Fourier transform of the target image, in order to reduce the amount of calculation; according to the gradient value and correlation coefficient of each pixel neighborhood in the overlapping region, the stitching line is searched to overcome the ghost image of the image after registration and realize seamless stitching of night panoramic image. The experimental results show that the proposed algorithm can effectively preserve the texture information of the original image while eliminating the smooth transition of the stitching seam, and at the same time, it has better stitching effect and stitching efficiency for the images under different conditions.