volume | PIER Journals

Abstract

The selection of matching method is critical to the scene matching navigation system, as it determines the accuracy of navigation. A coarse-to-fine matching method, which combines the area-based and feature-based matching method, is presented to meet the requirements of navigation, including the real-time performance, the sub-pixel accuracy and the robustness. In the coarse matching stage, the real-time performance is achieved by a pyramid multi-resolution technique, and the robustness is improved by multi-scale circular template fusion. In the precise matching stage, an improved SIFT method is introduced to calculate the matching position and the rotation angle. To validate the method, some experiments are completed. The results show that the proposed method can achieve the sub-pixel matching accuracy and improve the angle accuracy to 0.1°.

1. Ren, S., W. Chang, T. Jin, and Z. Wang, "Automated SAR reference image preparation for navigation," Progress In Electromagnetics Research, Vol. 121, 535-555, 2011.
doi:10.2528/PIER11091405 Google Scholar

2. Inglada, J. and F. Adragna, "Automatic multi-sensor image registration by edge matching using genetic algorithms," IEEE Int. Geosci. Remote Sens. Symposium, Vol. 5, 2313-2315, Sydney, NSW, Australia, 2001. Google Scholar

3. Liu, H. Z., B. L. Guo, and Z. Z. Feng, "Pseudo-log-polar Fourier transform for image registration," IEEE Signal Processing Letters, Vol. 13, No. 1, 17-20, 2006.
doi:10.1109/LSP.2005.860549 Google Scholar

4. You, J. and P. A. Bhattacharya, "Wavelet-based coarse-to-fine image matching scheme in a parallel virtual machine environment," IEEE Trans. Image Processing, Vol. 9, No. 9, 1547-1559, 2000.
doi:10.1109/83.862635 Google Scholar

5. Kusiek, A. and J. Mazur, "Analysis of scattering from arbitrary configuration of cylindrical objects using hybrid finite-difference mode-matching method," Progress In Electromagnetics Research, Vol. 97, 105-127, 2009.
doi:10.2528/PIER09072804 Google Scholar

6. Riabi, M. L., R. Thabet, and M. Belmeguenai, "Rigorous design and efficient optimization of quarter-wave transformers in metallic circular waveguides using the mode-matching method and the genetic algorithm," Progress In Electromagnetics Research, Vol. 68, 15-33, 2007.
doi:10.2528/PIER06072103 Google Scholar

7. Ren, S., W. Chang, and X. Liu, "SAR image matching method based on improved SIFT for navigation system," Progress In Electormagnetics Research M, Vol. 18, 259-269, 2011. Google Scholar

8. Lowe, D. G., "Distinctive image features from scale-invariant keypoints," International Journal of Computer Vision, Vol. 60, No. 2, 91-110, 2004.
doi:10.1023/B:VISI.0000029664.99615.94 Google Scholar

9. Yang, Y., Y. X. Song, F. W. Zhai, et al. "A high-precision localization algorithm by improved SIFT key-points," 2nd Int. Congress on Image and Signal Processing, 1-6, Tianjin, 2009.
doi:10.5815/ijigsp.2009.01.01 Google Scholar

10. Mikolajczyk, K. and C. Schmid, "A performance evaluation of local descriptors," IEEE Trans. Pattern Anal. Mach. Intell., Vol. 27, No. 10, 1615-1630, 2005.
doi:10.1109/TPAMI.2005.188 Google Scholar

11. Ehlers, M., "Multi-sensor image fusion techniques in remote sensing," ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 46, No. 1, 19-30, 1991.
doi:10.1016/0924-2716(91)90003-E Google Scholar

12. Dai, X. L. and S. Khorram, "A feature-based image registration algorithm using improved chain- code representation combined with invariant moments," IEEE Trans. Geosci. Remote Sens., Vol. 37, No. 5, 2351-2362, 2002. Google Scholar

13. Zhang, Y. C., P. Wang, and G. Y. Zhang, "An information fusion approach and its application based on D-S evidence theory and neural network," 27th Chinese Control Conference Proceedings, 623-626, Kunming, 2008. Google Scholar

14. Grabner, M., H. Grabner, and H. Bischof, "Fast approximated SIFT," Asian Conferonce on Comput. Vis., 918-927, Hyderabad, India, 2006. Google Scholar

15. Ke, Y. and R. Sukthankar, "PCA-SIFT: A more distinctive representation for local image descriptors," Proceedings of IEEE Comput. Soci. Conference on Comput. Vis. Pattern. Recog., 506-513, Washington DC, USA, 2004. Google Scholar

16. Yi, Z., Z. G. Cao, and X. Yang, "Multi-spectral remote image registration based on SIFT," Electronics Letters, Vol. 44, No. 2, 107-108, 2008.
doi:10.1049/el:20082477 Google Scholar

17. Bastanlar, Y., A. Temizel, and Y. Yardimci, "Improved SIFT matching for image pairs with scale di®erence," Electronics Letters, Vol. 46, No. 5, 346-348, 2010.
doi:10.1049/el.2010.2548 Google Scholar

18. Xie, H., L. Pierce, and F. Ulaby, "Statistical properties of logarithmically transformed speckle," IEEE Trans. Geosci. Remote Sens., Vol. 40, No. 3, 721-727, 2002.
doi:10.1109/TGRS.2002.1000333 Google Scholar

19. He, F. F., J. Y. Sun, and W. P. Guo, "A practical method for evaluating capability of scene matching algorithms," 7th Int. Conf. Computer-Aided Industrial Design and Conceptual Design, 1-6, Hangzhou, 2006. Google Scholar

20. Shi, H. L. and B. Hu, "Image registration using a new scheme of wavelet decomposition," IEEE Instrumentation and Measurement Technology Conference, 235-239, Victoria, 2008.

21. Li, D. and Y. H. Zhang, "Geometric feature-based image co-registration approach for InSAR," 2nd Asian-Paci¯c Conf. Synthetic Aperture Radar Proceedings, 1026-1030, Xi'an, 2009.

Dr. Sanhai Ren

Dr. Wenge Chang