Optical remote sensing image registration based on SG-SIFT

被引：0
作者：
机构：
[1] College of Information Science and Technology, Beijing Normal University, Beijing
来源：
| 1600年 / Beijing University of Posts and Telecommunications卷 / 37期
关键词：
Feature matching; Feature points distribution; Optical remote sensing image; Registration; Scale invariant feature transform;
D O I：
10.13190/j.jbupt.2014.06.004
中图分类号：
学科分类号：
摘要：
A new optical remote sensing image registration method signal gridding-scale invariant feature transform (SG-SIFT) based on signal theory and gridding is proposed. According to relationships among the image layers in the difference of Gaussians scale space, the feature points' number of each image is set in proportion to make the their distribution uniform in the scale space. In addition, a regular gridding method is introduced to achieve the well distribution of feature points in the image space. Then, error matching pairs are eliminated by a correspondence error checking. Statistical and visual results show that SG-SIFT is superior to standard scale invariant feature transform (SIFT) according to the feature points distribution, while the number of correct matching pairs from SG-SIFT is 17.47% more than that of uniform robust-scale invariant feature transform (UR-SIFT) in average and the evaluation indicator of root-mean square error confirms its superior performance to SIFT and UR-SIFT. ©, 2014, Beijing University of Posts and Telecommunications. All right reserved.
引用
收藏
页码：17 / 22
页数：5
相关论文
共 5 条
  • [1] Barbara Z., Jan F., Image registration methods: a survey, Image and Vision Computing, 21, 11, pp. 977-1000, (2003)
  • [2] Yu X., Lu Z., Hu D., Review of remote sensing image registration techniques, Optics and Precision Engineering, 21, 11, pp. 2960-2972, (2013)
  • [3] David L., Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 60, 2, pp. 91-110, (2004)
  • [4] Sedaghat A., Mokhtarzade M., Ebadi H., Uniform robust scale-invariant feature matching for optical remote sensing images, IEEE Transactions on Geoscience and Remote Sensing, 49, 11, pp. 4516-4527, (2011)
  • [5] Yu L., Zhang D., Holden E.-J., A fast and fully automatic registration approach based on point features for multi-source remote-sensing images, Computers and Geosciences, 34, pp. 838-848, (2008)
1