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.
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
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.
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.
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.
Smart Images

Figure CN120339057A_ABST