基于预定位图像框架策略的全景图配准拼接算法研究
The Research of Panorama Matching Stitching Algorithm Based on a Predetermined Image Framework Strategy

DOI: 10.12677/JISP.2015.44013, PP. 111-118

Keywords: 壁画拼接，图像配准，SFM，预定位框架
Mural Mosaic, Image Registration, SFM, Predetermined Framework

Full-Text   Cite this paper   Add to My Lib

Abstract:

由于壁画拼接在图像拼接应用场景的特殊性，采用传统的单应性投射矩阵配准算法无法满足。通过SFM流程对壁画三维重建，预定位全景图的框架图片，调整非框架图片的投射顺序，采用滑动窗口直接线性变换算法进行投射。通过全景图的主观评价，误差数值的客观评价以及与商业拼接软件作实验对比验证了本课题算法的可行性。
Because of the particularity of the mural mosaic work in the panorama stitching, the existing algorithms can’t satisfy the needs. We set up three-dimensional reconstruction by a structure-from- motion (SFM) system to obtain the framework, and then project the no-frame images to the frame by Moving DLT in order to refine the transformations. The experiment shows a better result between objectivity and subjectivity compared with commercial softwares.

References

[1]	刘之翌 (2010) 图像拼接中图像特征匹配算法研究与设计. 硕士论文, 天津工业大学, 天津.
[2]	Brown, M. and Lowe, D.G. (2007) Automatic panoramic image stitching using invariant features. International Journal of Computer Vision, 74, 59-73. http://dx.doi.org/10.1007/s11263-006-0002-3
[3]	Bay, H., Tuytelaars, T. and Van Gool, L. (2006) SURF: Speeded up robust features. Computer Vision-ECCV 2006, Springer, Berlin Heidelberg, 404-417. http://dx.doi.org/10.1007/11744023_32
[4]	Szeliski, R. (2006) Image alignment and stitching: A tutorial. Foundations and Trends in Computer Graphics and Vision, 2, 1-104. http://dx.doi.org/10.1561/0600000009
[5]	Agarwala, A., Agrawala, M., Cohen, M., et al. (2006) Photographing long scenes with multi-viewpoint panoramas. ACM Transactions on Graphics (TOG), 25, 853-861. http://dx.doi.org/10.1145/1141911.1141966
[6]	Szeliski, R. (2010) Computer vision: Algorithms and applications. Springer Science & Business Media, Berlin.
[7]	沈武魁 (2011) 基于SFM 的大幅面壁画图像高保真拼接技术. 硕士论文, 浙江大学, 杭州.
[8]	徐玉华, 龚文全, 苏昂, 等 (2014) 近似平面场景多视点图像拼接算法. 国防科技大学学报, 2, 148-155.
[9]	Gao, J., Kim, S.J. and Brown, M.S. (2011) Constructing image panoramas using dual-homography warping. 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado, 20-25 June 2011, 49-56. http://dx.doi.org/10.1109/CVPR.2011.5995433
[10]	Lin, W.Y., Liu, S., Matsushita, Y., et al. (2011) Smoothly varying affine stitching. 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado, 20-25 June 2011, 345-352. http://dx.doi.org/10.1109/CVPR.2011.5995314
[11]	Zaragoza, J., Chin, T.J., Tran, Q.H., et al. (2014) As-projective-as-possible image stitching with moving DLT. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36, 1285-1298. http://dx.doi.org/10.1109/TPAMI.2013.247
[12]	Hartley, R. and Zisserman, A. (2003) Multiple view geometry in computer vision. Cambridge University Press, Cambridge.
[13]	Zhang, L., Zhang, L., Mou, X., et al. (2011) FSIM: A feature similarity index for image quality assessment. IEEE Transactions on Image Processing, 20, 2378-2386. http://dx.doi.org/10.1109/TIP.2011.2109730
[14]	杨琬, 吴乐华, 范晔 (2008) 数字图像客观质量评价方法研究. 通信技术, 41, 244-246.

Full-Text