期刊文献+

基于SURF和KLT跟踪的图像拼接算法 被引量:12

Mosaic Algorithm of Image Based on SURF and KLT Track
下载PDF
导出
摘要 针对现有图像拼接精度不高和速度慢的问题,提出一种图像自动拼接算法。采用特征向量实现图像序列完全自动排序,把特征向量作为图像中的运动目标,利用KLT跟踪算法计算特征点的偏移量,从而得到图像之间精确的单应性变换矩阵,给出一种基于视觉特征的色彩融合方法实现图像的无缝拼接。实验证明该算法提高了匹配的精度和速度,能够实现自动排序,并具有较好的鲁棒性。 Aiming at the low precision and slow speed of registration, this paper propose an algorithm for automatic mosaic of image sequence. Using SURF vector is to judge if two images are overlapped and ascertain the relationship of the overlapped images. The detected features are regarded as moving objects, located by the KLT track algorithm, and accurate homography matrix between the two images is obtained. It proposes a color fusion method to achieve seamless splicing based on visual feature. Experimental results show that the precision and speed of registration are improved and the algorithm is robust.
出处 《计算机工程》 CAS CSCD 北大核心 2010年第1期215-217,共3页 Computer Engineering
关键词 图像拼接 图像匹配 SURF算法 图像变换 image mosaic image matching SURF algorithm image transformation
  • 引文网络
  • 相关文献

参考文献7

  • 1Mikolajczyk K, Schmid C. Indexing Based on Scale Invariant Interest Points[C]//Proc. of the 8th IEEE International Conference of Computer Vision. Vancouver, Canada: IEEE Press, 2001: 525-531.
  • 2董瑞,梁栋,唐俊,鲍文霞,何韬.基于颜色梯度的图像特征点匹配算法[J].计算机工程,2007,33(16):178-180. 被引量:4
  • 3Lowe D G. Distinctive Image Features from Scale-invariant Keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
  • 4Bay H, Tuytelaars T, Van G L. SURF: Speeded up Robust Features[EB/OL]. (2006-02-05). http://www.vision.ee.ethz.ch/-surf/ eccv06.pdf.
  • 5Bay H, Ess A, Tuytelaars T, et al. Speeded-up Robust Features(SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359.
  • 6Viola P, Jones M. Rapid Object Detection Using a Boosted Cascade of Simple Features[J]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001, 32(1): 511-518.
  • 7陈付幸,王润生.基于预检验的快速随机抽样一致性算法[J].软件学报,2005,16(8):1431-1437. 被引量:106

二级参考文献15

  • 1梁栋,童强,王年,鲍文霞,屈磊.一种基于Laplacian矩阵的图像匹配算法[J].计算机工程与应用,2005,41(36):31-32. 被引量:4
  • 2王年,范益政,韦穗,梁栋.基于图的Laplace谱的特征匹配[J].中国图象图形学报,2006,11(3):332-336. 被引量:32
  • 3Brandt S. Maximum likelihood robust regression with known and unknown residual models. In: Proc. of the ECCV 2002. 2002.97-102.
  • 4Murray PTD. The development and comparison of robust methods for estimating the fundamental matrix. Int'l Journal of Computer Vision, 1996. 1-33.
  • 5Zhang ZY. Determining the epipolar geometry and its uncertainty: A review. Int'l Journal of Computer Vision, 1998,27(2):161-195.
  • 6Fischler MA, Bolles RC. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. CACM, 1981,24(6):381-395.
  • 7Rousseeuw PJ. Robust Regression and Outlier Detection. New York: John Wiley & Sons, 1987.
  • 8Torr PHS, Murray DW. Outlier detection and motion segmentation. SPIE 93, 1993. 432-443.
  • 9Stewart CV. MINPRAN: A new robust operator for computer vision. IEEE Trans. on Pattern Analysis and Machine Intelligence,1995,17(10):925-938.
  • 10Torr PHS, Zisserman A. MLESAC: A new robust estimator with application to estimating image geometry. Computer Vision and Image Understand, 2000,78:138-156.

共引文献108

同被引文献115

引证文献12

二级引证文献25

;
使用帮助 返回顶部