Ground control point (GCP) extraction is an essential step in automatic registration of remote sensing images. However the lack of quantitative and objective methods for analyzing GCP quality becomes the bottleneck that prevents the broad development of automatic image registration. Although several measurements for evaluating the number, accuracy and distribution of GCPs have been proposed in recent years, some of them are redundant and the evaluation of dispersion is not effective enough. In this paper, a method for an objective and quantitative evaluation of GCP quality is proposed. The proposed method consists of three parts: measurement calculation, cost function calculation and final validation. In the first part, two new measurements are proposed to evaluate the number, dispersion and isotropy of GCPs, and the root mean square of GCP residuals using leave-one-out method (RMSloo) is used to evaluate the accuracy. In the second part, seed cost functions are utilized to transform the measurements into a limited value range as well as to be desired on the ascending direction. Subsequently, all the seed cost functions are combined by a total cost function to provide an integrated evaluation. In the third part, the GCP scenario is validated by the accepted threshold depending on the value of the total cost function. To evaluate the performance of the proposed method, experiments using four typical emulated scenarios of GCP distribution and two sets of real GCPs in SAR images are considered. The results demonstrate that the proposed GCP evaluation method performs more effectively than the existing methods, especially in the evaluation of dispersion quality.
2. Moser, G. and S. B. Serpico, "Unsupervised change detection from multichannel SAR data by Markovian data fusion," IEEE Trans. on Geosci. Remote Sens, Vol. 47, No. 7, 2114-2128, 2009.
3. Alparone, L., S. Baronti, A. Garzelli, and F. Nencini, "Landsat ETM+ and SAR image fusion based on generalized intensity modulation," IEEE Trans. on Geosci. Remote Sens., Vol. 42, No. 12, 2832-2839, 2004.
4. Du, L., H. Liu, Z. Bao, and M. Xing, "Radar HRRP target recognition based on higher order spectra," IEEE Trans. on Signal Process., Vol. 53, No. 7, 2359-2368, 2005.
5. Ma, W. and J. Yang, "Target detection algorithm for polarimetric SAR images using GOPCE," Proc. IEEE CIE Int. Conf. Radar, 507-509, 2011.
6. Chureesampant, K. and J. Susaki, "Automatic GCP extraction of fully polarimetric SAR images," IEEE Trans. on Geosci. Remote Sens., Vol. 52, No. 1, 137-148, 2014.
7. Gon»calves, H., J. A. Gon»calves, and L. Corte-Real, \, "Measures for an objective evaluation of the geometric correction process quality," IEEE Geosci. Remote Sens. Lett., Vol. 6, No. 2, 292-296, 2009.
8. Buiten, H. J. and B. van Putten, "Quality assessment of remote sensing image registration --- Analysis and testing of control point residuals," ISPRS J. Photogramm. Remote Sens., Vol. 52, No. 2, 57-73, 1997.
9. Goncalves, H., L. Corte-Real, and J. A. Goncalves, "Automatic image registration through image segmentation and SIFT," IEEE Trans. on Geosci. Remote Sens, Vol. 49, No. 7, 2589-2600, 2011.
10. Gon»calves, H., J. A. Gon»calves, and L. Corte-Real, "Automatic image registration based on correlation and Hough transform," Proc. SPIE Image Signal Process. Remote Sens. XIV, 71090J, 2008.
11. Wang, S., H. You, and K. Fu, "Wang, S., H. You, and K. Fu, \BFSIFT: A novel method to find feature matches for SAR image registration," IEEE Geosci. Remote Sens. Lett., Vol. 9, No. 4, 649-653, 2012.
12. Bradley, P. and U. Fayyad, "Refining initial points for K-means clustering," Proc. 15th Int. Conf. Machine Learning, 91-99, 1998.
13. HÄoppner, F., F. Klawonn, and R. Kruse, HÄoppner, F., F. Klawonn, and R. Kruse, Fuzzy Cluster Analysis: Methods for Classification, Data Analysis, and Image Recognition, Wiley, New York, 1999.
14. Hartuv, E. and R. Shamir, "A clustering algorithm based on graph connectivity," Inf. Process. Lett., Vol. 76, No. 4--6 , 6175-6181, 2000.