基于投影模型和图像融合的拼接畸变消除算法

STITCHING ABERRATION ELIMINATION ALGORITHM BASED ON PROJECTION MODEL AND IMAGE FUSION

图像拼接技术是数字图像处理的一个重要分支,广泛运用于空间纹理检测、文物保护、医学图像、公安取证、虚拟现实等领域。由于拍摄的图像存在光照、角度、位移和抖动等各种因素影响,导致图像拼接时易造成图像畸变和变形。采取投影模型和图像融合,对畸变和变形进行研究,改进传统的拼接算法,提出一种自适应强、时效性高、稳定性好的投影模型和图像融合相结合的拼接算法。实验结果表明,该算法能够很好地消除拼接过程中产生的畸变和变形,并具有很好的鲁棒性。

Image stitching technique is an important branch in the field of digital image processing and is widely used in spatial texture detection,cultural relics protection,medical image,public security forensics,virtual reality and so on. Due to the impacts of various factors such as lighting,angle,shift and dithering in captured images,it is easy to lead to image aberration and deformation when image is stitching.In this paper we use the projection model and image fusion to study the aberration and deformation,by improving traditional stitching algorithm we present a new algorithm combining the projection model and image fusion which has good adaptive ability,high efficiency and good stability. Experimental result shows that the proposed algorithm can well eliminate the aberration and deformation brought about in stitching process,and it has good robustness as well.