Multi-Sensor Image Registration by Combination of Relaxation Optimization Matching and Partitioning RANSAC

Abstract:

This paper presents a multi-sensor image registration method by combination of relaxation optimization matching and Partitioning RANSAC. Firstly, the global coarse registration is performed to establish the approximate relationship of reference and slave image. Secondly, in each pyramid level, the normalized MI and relaxation optimization technique are adopted to get the matching points, and partitioning RANSAC is used to delete the existing false matches. The coarse-to-fine strategy is integrated to refine the results, and finally the rubber sheeting method is used to realize the image registration. Two datasets have been experimented, and it can be found that satisfactory registration method can be obtained.

• Periodical: Advanced Materials Research (Volumes 765-767)
• Pages: 2882-2885
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.765-767.2882
• Online since: September 2013
• Authors: Ying Dan Wu, Yang Ming
• Keywords: Image Registration, Multi-Sensor, RANSAC, Relaxation Optimization

References

[1] B. Zitova , J. Flusser, Image registration methods: A survey, Image Vis. Comput. 21(2003) 977–1000.

[2] L. Fonseca, B. Manjunath, Registration techniques for multisensory remotely sensed imagery, Photogramm. Eng. Remote Sens. 62(1996) 1049–1056.

[3] Y. SunKim, J. HakLee, J. BeomRa, Multi-sensor image registration based on intensity and edge orientation information, Pattern Recognition. 41 (2008) 3356–3365.

DOI: 10.1016/j.patcog.2008.04.017

[4] F. Maes, A. Collignon, D. Vandermeulen, G. Marchal, P. Suetens, Multimodality image registration by maximization of mutual information, IEEE Trans. Med. Imaging. 16 (1997) 187-198.

DOI: 10.1109/42.563664

[5] J. Pluim, J. Maintz, M. Viergever, Mutual-information-based registration of medical images: A survey, IEEE Trans. Med. Imag. 22 (2003) 986–1004.

DOI: 10.1109/tmi.2003.815867

[6] C.R. Maurer Jr., R.J. Maciunas, J.M. Fitzpatrick, Registration of head CT images to physical space using a weighted combination of points and surfaces, IEEE Trans. Med. Imaging. 17 (1998) 753-761.

DOI: 10.1109/42.736031

[7] W.H. Press, B.P. Flannery, S.A. Teukolsky, W.T. Vetterling, Numerical recipes in C, Cambridge University Press, Cambridge, UK, (1992).

DOI: 10.1017/s0263574700010675

[8] P. Viola and W. M. Wells, Alignment by maximization of mutual information, Int. J. Comput. Vis. 24 (1997) 137–154.

[9] C. Studholme, D.L.G. Hill, D.J. Hawkes, An overlap invariant entropy measure of 3D medical image alignment, Pattern Recognition. 32 (1999) 71–86.

DOI: 10.1016/s0031-3203(98)00091-0

[10] E.R. Hancock, J. Kittler, Discrete relaxation. Pattern Recognition, 23 (1990) 711-733.

DOI: 10.1016/0031-3203(90)90094-2

[11] Y.D. Wu, Y. Ming, A robust registration method for high resolution remote sensing images, Geoinformatics 2008 and Joint Conference on GIS and Built Environment: Classification of Remote Sensing Images, 7147 (2008) 71470Y-1-71470Y-9.

DOI: 10.1117/12.813235

[12] M.A. Fischler, R.C. Bolles, Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography, Communications of the Association of Computing Machinery, 24 (1981) 381-395.

DOI: 10.1145/358669.358692