期刊文献+

CUDA技术及其在数字图像拼接中的应用 被引量:3

CUDA and its application in digital image mosaic
在线阅读 下载PDF
导出
摘要 将CUDA技术应用于数字图像拼接领域,阐述了图像拼接的基本理论及其关键技术、多分辨率图像融合的关键算法以及CUDA技术的基本原理和开发方法,并编写了软件以实现图像快速拼接。采用对于尺度具有鲁棒性的SIFT算法进行特征点的提取与匹配,使用稳健的RANSAC算法求出图像间变换矩阵的值,并将图像映射到拼接平面,最后使用基于CUDA的SIFT算法实现了图像的无缝拼接。该方法提高了图像拼接的效率,克服了传统图像拼接方法因计算量大而等待时间长的缺点。实验结果表明,CUDA在数字图像处理的实际应用中卓有成效,有广阔的应用前景。 This paper presents an application for digital image mosaic by using CUDA technology. The basic theory and key technology of image mosaic and CUDA are illustrated in this paper. Then, CUDA is used in the software to parallel the process of image mosaic. A scale-invariant feature extracting algorithm SIFT is used for feature extraction and matching. The transforming matlix is computed with RANSAC algorithm and the image is mapped to the mosaic plane. Finally, image mosaic is completed with CUDA based on SIFT method. This method achieves a seamless image mosaic and improves the efficiency of image process, which also overcomes long waiting time because of huge computations in traditional ways. Experiment results show that digital image processing combined with CUDA is much more efficient in practical applications and has bright potential applications in the future.
出处 《微型机与应用》 2013年第2期34-36,40,共4页 Microcomputer & Its Applications
关键词 CUDA 图像拼接 SIFT 多分辨率融合 CUDA image mosaic SIFT muhiresolution spline mosaic
  • 相关文献

参考文献9

  • 1HARRIS C,STEPHENS M. A combined corner and edge detector[A].1988.147-151.
  • 2张小洪,李博,杨丹.一种新的Harris多尺度角点检测[J].电子与信息学报,2007,29(7):1735-1738. 被引量:80
  • 3LOWED G. Object recognition from local scale-invariant features[A].1999.1150-1157.
  • 4骞森,朱剑英.基于改进的SIFT特征的图像双向匹配算法[J].机械科学与技术,2007,26(9):1179-1182. 被引量:45
  • 5Peng Xiaoming,Ding Mingyue,Zhou Chengping. Improved approach for object location under affine transformation using the Hausdorff distance[J].Optical Engineering,2003,(10):2794-2795.
  • 6张毓晋.图像工程(上册)图像处理[M]北京:清华大学出版社,2006.
  • 7LINDEBERG T. Detecting salient blob.like image structures and their scales with a scale-space primal sketch[J].International Journal of Computer Vision,1993,(03):283-318.
  • 8NVIDIA. NVIDIA CUDA Programming Guide[M].
  • 9张舒;褚艳利.GPU高性能运算之CUDA[M]北京:中国水利水电出版社,2009.

二级参考文献16

  • 1陈乐,吕文阁,丁少华.角点检测技术研究进展[J].自动化技术与应用,2005,24(5):1-4. 被引量:45
  • 2Lee J S,Sun Y N,and Chen C H.Multiscale corner detection by using wavelet transform.IEEE Trans.on Image Proc.,1995,4(1):100-104.
  • 3Hua J P and Liao Q M.Wavelet-based multiscale corner detection.IEEE Proc.of ICSP,Bering,2000:341-344.
  • 4Freeman H and Davis L S.A corner-finding algorithm for chain-coded curves.IEEE Tuns.on Comput.,1977,26(3):297-303.
  • 5Mokhtarian F and Suomela R.Curvature scale space based image corner detection.Proc.European Signal Processing Conference,Island of Rhodes,Greece,1998:2549-2552.
  • 6Harris C and Satephens M J.A combined corner and edge detector.In Alvey Vision Conference,Manchester,1988:147-152.
  • 7Smith S M and Brady J M.SUSAN:A new approach to low level image processing.Internetional Journal of Computer Vision,1997,23(1):45-78.
  • 8Harris C.Stephens M.A combined corner and edge detector[A].Proc.of The Fourth Alvey Vision Conference[C],Manchestsr,UK,1988:147-151
  • 9Tomasi C,Kanade T.Detection and Tracking of Point Features[R].Carnegie Mellon University Technical Report CMU-CS-91-132,Pittsburgh,USA,Apr 1991
  • 10Lowe D G.Object recognition from local scale-invariant features[A].International Conference on Computer Vision[C],Corfu,Greece,Sep 1999:1150-1157

共引文献123

同被引文献17

引证文献3

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部