全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

运用特征点匹配的柱面全景图像快速拼接算法

DOI: 10.11834/jig.20090628

Keywords: 图像拼接,聚类法,最佳路径,亮度权重函数

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对大幅面图像的拼接问题,提出了一种新的基于特征点的柱面全景图像快速拼接算法。该算法在Harris角检测算法提取特征点的基础之上,针对传统RANSAC(randomsamplingconsensus)算法在提纯匹配点时计算极其复杂,难以实现快速拼接的问题,设计了专门的聚类预筛选的方法进行图像特征点的预匹配,显著提高了特征点匹配的效率;在图像融合部分提出了最佳路径与HSI颜色空间的亮度权重函数相结合的算法,既有效消除了拼接图像中的鬼影现象,又使拼接图像达到了平滑融合效果。实验结果表明,该算法具有匹配精度高、鲁棒性强、计算效率高的特点。

References

[1]  Zomet A. Mosaicing from a Translating Camera with Efficient Application of Super-Resolution [D], Jerusalem: The Hebrew University of Jerusalem ,2000.
[2]  Szeliski R. Image Alignment and Stitching,Technical Report [R]. MSR-TR-2004-92, Redmond, Washington DC, USA: Microsoft Research, 2004.
[3]  Shum H Y ,Szeliski R. Panoramic image mosaicing. Technical Report [R]. MSR-TR- 97- 23, Redmond, Washington DC, USA: Microsoft Research, 1997.
[4]  Zoghlami I,Faugeras O,Deriche R. Using geometric comers to build a 2D mosaic from a set of images [ A ]. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition ( CVPR \\' 97 ) [C], San Juan, Puerto Rico, 1997: 420-425.
[5]  Harris C,Stephens M J. A combined comer and edge detector [A]. In: Proceedings of The Fourth Alvey Vision Conference [C], Manchester, UK, 1988 : 147-152.
[6]  Maas H G,Schneider D. A geometric model for linear-array-based terrestrial panoramic cameras [ J ]. The Photogrammetric Record , 2006,21 (115) :198-210.
[7]  孙立峰 钟立 李云浩等.虚拟实景空间的实时漫游[J].中国图象图形学报,1999,4(6):507-513.
[8]  Faille F. A Fast method to improve the stability of interest point detection under illumination changes [ A ]. In : Proceedings of IEEE International Conference on Image Processing [C], Singapore, 2004 : 2673 -2676.
[9]  Lacey A J, Pinitkarn N, Thacker N A. An evaluation of the performance of RANSAC algorithms for stereo camera calibration [ A ]. In : Proceedings of The 11 th British Machine Vision Conference [C] , Bristol, UK ,2000,2 : 646-655.
[10]  Di Stefano L, Mattoccia S, Mola M. An efficient algorithm for exhaustive template matching based on normalized cross correlation [A]. In: Proceedings of the 12th International Conference on Image Analysis and Processing[C],Mantova,Italy,2003: 322-327.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133