Dynamic Focal Length Adjustment for Drift-Free Cylindrical Panorama Stitching Using Feature-Based Image Alignment

Panoramic image stitching is a fundamental technique in computer vision and graphics , widely utilized in virtual tours, immersive experiences, and robotic vision. However , traditional cylindrical panorama stitching techniques often face challenges with accumulated drift, resulting in visual misalignments in the final output. This paper presents a novel approach to drift-free cylindrical panorama stitching by dynamically adjusting the focal length based on the gap angle between the first and last images. The proposed method incorporates cylindrical warping, robust feature extraction using the Scale-Invariant Feature Transform (SIFT), and image alignment through Random Sample Consensus (RANSAC). Drift correction is achieved by iteratively recalibrating the focal length to minimize alignment errors and ensure seamless stitching across the panoramic sequence. Experimental results demonstrate the effectiveness of the proposed approach in reducing drift, achieving precise alignment, and producing high-quality panoramas. The dynamic focal length adjustment offers significant improvements over existing methods, addressing key challenges in panoramic imaging and enhancing its applicability in real-world scenarios.