Abstract
For SIFT(Scale Invariant Feature Transform) has poor real-time and low match rate problem in large-scale image registration, a improved registration algorithm based on SIFT algorithm is proposed in this paper, which down-sample the large-scale image with Cubic interpolation algorithm, and under the restriction that the minimum size of down-sampling image should be meet image registration requirement. We can calculate the transformation matrix of down-sampling image with SIFT algorithm, and then we can get transformation matrix of original large-scale image through the relationship of transformation matrix between down-sampling image and original image, so the registration of large-scale image can be got more rapidly. The experiment results show the effectiveness and feasibility of the proposed method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Xiong, L.: A survey of image matching in computer vision. Journal of Hubei University Technology 21(3), 171–173 (2006)
Qi, Z., Cooperstock, J.R.: Toward Dynamic Image Mosaic Generation With Robustness to Parallax. IEEE Transactions on Image Processing 21(1), 366–378 (2012)
Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal on Computer Vision 60(2), 91–110 (2004)
Wang, H., Wang, C., Li, P.: Review of multi-source remote sensing image techniques registration. Computer Engineering 37(19), 17–21 (2011)
Li, F., Xiao, B., Jia, Y.: Improved SIFT algorithm and its application in automatic registration of remotely-sensed imagery. Geomatics and Information Science of Wuhan Unniversity 34(10), 1245–1249 (2009)
Quelhas, P., Monay, F., Odobez, L.M.: D. Gatica-Perez, T. Tuytelaars, L. Van Gool.: Modeling scenes with local descriptors and latent aspect. In: Proceedings of the Tenth IEEE International Conference on Computer Vision, ICCV 2005 (2005)
Xiong, Z., Wan, G.: Unmanned aerial vehicle serial image automatic registration base on improved SIFT algorithm. Journal of Geomatics Science and Technology 29(2), 153–156 (2012)
Ke, Y., Sukthankar, R.: PCA-SIFT:A more distinctive representation for local image descriptors. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, Washington, USA, pp. 511–517 (2004)
Zhu, Z., Shen, Z., Luo, J.: Parallel remote sensing image registration based on improved SIFT point feature. Journal of Remote Sensing 15(5), 1024–1031 (2011)
Yu, L., Dai, Q.: Improved SIFT Feature Matching Algorithm. Algorithm.Computer Engineering 37(2), 210–212 (2011)
Zheng, Y., Huang, X., Feng, S.: An Image Matching Algorithm Based on Combination of SIFT and the Rotation Invariant LBP. Journal of Computer-Aided Design & Computer Graphics 22(2), 286–292 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wei, L., Zhou, S. (2014). Research on Novel Optimization SIFT Algorithm Based Fast Mosaic Method. In: Ma, S., Jia, L., Li, X., Wang, L., Zhou, H., Sun, X. (eds) Life System Modeling and Simulation. ICSEE LSMS 2014 2014. Communications in Computer and Information Science, vol 461. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-45283-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-662-45283-7_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-45282-0
Online ISBN: 978-3-662-45283-7
eBook Packages: Computer ScienceComputer Science (R0)