Real time image registration based on dictionary feature descriptor

被引：2
作者：
机构：
[1] Key Laboratory of Airborne Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences
[2] University of Chinese Academy of Sciences
[3] Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences
来源：
Zhu, M. (zhu_mingca@163.com) | 1613年 / Chinese Academy of Sciences卷 / 22期
关键词：
Dictionary; Feature description vector; Image registration; K-singular Value Decomposition(KSVD) method;
D O I：
10.3788/OPE.20142206.1613
中图分类号：
学科分类号：
摘要：
As traditional description vector calculation method used in image registration is too complex, time consuming and taking up more memory, a novel dictionary based local feature description algorithm was proposed. The K-singular Value Decomposition( KSVD ) method was used to generate dictionary and the feature descriptor was obtained by comparing the similarity between feature point region in images and elements in the dictionary. By above, the description vector generation algorithm was simplified and a higher feature matching speed was obtained. The matching process could be carried out by using randomized KD(k-dimension)tree algorithm. Then, the Random Sample Consensus (RANSAC) was used to choose the correct matching pairs. Finally, the transform parameters were estimated by using the least square method and the space geometric transformation of two images to be registrated was obtained. Results from experiments show that the proposed method reduces the description vector storage space, speeds up the feature matching and implements the registration process in real time.
引用
收藏
页码：1613 / 1621
页数：8
相关论文
共 17 条
  • [1] Yang X.M., Wu W., Qing L.B., Et al., Image feature extraction and matching technology, Opt. Precision Eng., 17, 9, pp. 2276-2282, (2009)
  • [2] Song Z.L., Li S., George T.F., Remote sensing image registration approach based on a retrofitted SIFT algorithm and Lissajous-curve trajectories, Optics Express, 18, 2, pp. 513-522, (2010)
  • [3] Sun H., Ma T.W., Sub-pixel motion estimation based on phase-only correlation, Chinese Journal of Liquid Crystals and Displays, 26, 6, pp. 858-862, (2011)
  • [4] Qiu W.T., Zhao J., Liu J., Image matching algorithm combing SIFT with region segment, Chinese Journal of Liquid Crystals and Displays, 27, 6, pp. 827-831, (2012)
  • [5] Wong A., An adaptive Monte Carlo approach to phase-based multimodal image registration, IEEE Transactions on Information Technology in Biomedicine, 14, 1, pp. 173-179, (2010)
  • [6] Lowe D.G., Distinctive image features from scale-invariant keypoints, International Joumal of Computer Vision, 60, 2, pp. 91-110, (2004)
  • [7] Qi Y., Wang Y., Wang M.Y., Improved SIFT feature image registration algorithm, Journal of Shenyang Ligong University, 31, 4, pp. 50-53, (2012)
  • [8] Bay H., Tuytellars T., Gool L.V., SURF: speeded up robust features, Computer Vision and Image Understanding, 110, 3, pp. 346-359, (2008)
  • [9] Zhang R.J., Zhang J.Q., Yang C., Image registration approach based on SURF, Infrared and Laser Engineering, 38, 1, pp. 160-165, (2009)
  • [10] Candes E.J., Romberg J., Tao T., Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information, IEEE Transactions on Information Theory, 52, 2, pp. 489-509, (2006)
12