Volume XXXIX-B1
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XXXIX-B1, 179-183, 2012
https://doi.org/10.5194/isprsarchives-XXXIX-B1-179-2012
© Author(s) 2012. This work is distributed under
the Creative Commons Attribution 3.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XXXIX-B1, 179-183, 2012
https://doi.org/10.5194/isprsarchives-XXXIX-B1-179-2012
© Author(s) 2012. This work is distributed under
the Creative Commons Attribution 3.0 License.

  23 Jul 2012

23 Jul 2012

OPTICAL-TO-SAR IMAGE REGISTRATION BASED ON GAUSSIAN MIXTURE MODEL

H. Wang2,1, C. Wang2, P. Li2,1, Z. Chen2, M. Cheng2, L. Luo3, and Y. Liu4 H. Wang et al.
  • 1School of Electronic Science and Engineering, National University of Defense Technology, Changsha, China
  • 2Department of Computer Science, School of Information Science and Technology, Xiamen University, Xiamen, China
  • 3China Transport Telecommunication & information Center, Beijing, China
  • 4Hunan Provincial Transport Technical Information Center, Changsha, China

Keywords: Remote Sensing, Image Registration, SAR, Optical, Gaussian Mixture Model, EM Algorithm, Line Support Region

Abstract. Image registration is a fundamental in remote sensing applications such as inter-calibration and image fusion. Compared to other multi sensor image registration problems such as optical-to-IR, the registration for SAR and optical images has its specials. Firstly, the radiometric and geometric characteristics are different between SAR and optical images. Secondly, the feature extraction methods are heavily suffered with the speckle in SAR images. Thirdly, the structural information is more useful than the point features such as corners. In this work, we proposed a novel Gaussian Mixture Model (GMM) based Optical-to-SAR image registration algorithm. The feature of line support region (LSR) is used to describe the structural information and the orientation attributes are added into the GMM to avoid Expectation Maximization (EM) algorithm falling into local extremum in feature sets matching phase. Through the experiments it proves that our algorithm is very robust for optical-to- SAR image registration problem.