30 October 2009 A global optimization approach for construction of panoramic mosaics
Author Affiliations +
Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74950F (2009) https://doi.org/10.1117/12.833213
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
Abstract
A global optimization approach for construction of a 360° full-view panoramic mosaic is presented with global consistency in this paper. There are three primary steps in this approach. The first is a local registration using SIFT. In the second step, an efficient algorithm for finding a global consistent registration of all images is developed. The local registration matrices with the boundary condition are used for computing the initial parameters of the iterative optimization for the global consistent registration, to adjust/reduce the alignment error accumulated by the local registering and stitching of adjacent two images. Lastly, the overlapping areas of the images are stitched by the graph cut algorithm and blended with a multi-resolution method. It is proven by the experiment results in this paper that the presented approach can effectively construct panoramic mosaics with global end-to-end consistency.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Haiying Wang, Haiying Wang, Kaihuai Qin, Kaihuai Qin, } "A global optimization approach for construction of panoramic mosaics", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74950F (30 October 2009); doi: 10.1117/12.833213; https://doi.org/10.1117/12.833213
PROCEEDINGS
8 PAGES


SHARE
Back to Top