Optimal seam line detection method and system based on improved A star algorithm

By improving the A-satellite algorithm combined with adaptive weights and two-way search, seam detection is optimized, which solves the problems of high computational complexity and poor spectral consistency in satellite multispectral image stitching, and achieves efficient, smooth and spectrally consistent seam detection.

CN120339057APending Publication Date: 2025-07-18DALIAN MARITIME UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510409416.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-04-02
Publication Date
2025-07-18

AI Technical Summary

Technical Problem

The prior art has high computational complexity and difficult to guarantee local optimality in satellite multispectral image stitching, and ignoring spectral information leads to poor spectral consistency of the stitching image.

Method used

The improved A-star algorithm is adopted, combining adaptive weights, two-way search and eight-direction neighborhood search, combining spatial information and spectral information to optimize the seam lines, image registration is performed through SIFT, KNN and F-LPM algorithms, and seam lines are detected using the optimal band combination.

Benefits of technology

The speed of seam detection is accelerated, the smoothness and adaptability of seam lines is improved, the spectral consistency and spatial consistency of the stitching image are ensured, and spectral distortion is reduced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120339057A_ABST
    Figure CN120339057A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of multispectral image splicing, in particular to an optimal seam line detection method and system based on an improved A star algorithm, and the method comprises the following steps: calculating an overlapping region of a plurality of multispectral images; recursively deducing a path with the minimum cost in the overlapped region as a seam line by adopting an improved A star algorithm based on adaptive weight, a bidirectional search mechanism and eight-direction neighborhood search; based on the spatial information and the spectral information, establishing an energy function of pixel points in the overlapping region, performing spatial-spectral joint optimization on the joint seam line by taking the energy function as a constraint to obtain an optimal seam line, and extracting the spatial information by an optimal waveband combination. According to the method, the seam line detection speed can be increased, the smoothness and adaptability of the seam line can be improved, the occurrence probability of a local optimal solution can be reduced, and spectral distortion during multi-spectral image splicing can be reduced.
Need to check novelty before this filing date? Find Prior Art