Similar articles

Abstract: Multi-sensor image registration has been widely used in remote sensing and medical image field, but registration performance is degenerated when heterogeneous images are involved. An image registration method based on multi-resolution shape analysis is proposed in this paper, to deal with the problem that the shape of similar objects is always invariant. The contours of shapes are first detected as visual features using an extended contour search algorithm in order to reduce effects of noise, and the multi-resolution shape descriptor is constructed through Fourier curvature representation of the contour’s chain code. Then a minimum distance function is used to judge the similarity between two contours. To avoid the effect of different resolution and intensity distribution, suitable resolution of each image is selected by maximizing the consistency of its pyramid shapes. Finally, the transformation parameters are estimated based on the matched control-point pairs which are the centers of gravity of the closed contours. Multi-sensor Landsat TM imagery and infrared imagery have been used as experimental data for comparison with the classical contour-based registration. Our results have been shown to be superior to the classical ones.

[1] Belongie, S., Malik, J., Puzicha, J., 2001. Matching Shapes. International Conference on Computer Vision (ICCV’01), Canada, 1:454-462.

[2] Brown, L.G., 1992. A survey of image registration techniques. ACM Computing Surveys, 24(4):325-376.

[3] Dai, X., Khorram, S., 1999. A feature-based image registration algorithm using improved chain-code representation combined with invariant moments. IEEE Trans. on Geoscience and Remote Sensing, 37(5):2351-2362.

[4] Dudek, G., Tsotsos, J., 1997. Shape representation and recognition from multiscale curvature. Computer Vision and Image Understanding, 68(2):170-189.

[5] Fonseca, L.M.G., Manjunath, B.S., 1996. Registration techniques for multisensor remotely sensed imagery. Photogrammetry Engineering and Remote Sensing Journal, 562(9):1049-1056.

[6] Haralick, R.M., Shapiro, L.G., 1993. Computer and Robot Vision. Addison-Wesley, MA, 1:57-68.

[7] Irani, M., Anandan, P., 1998. Robust Multi-Sensor Image Alignment. Sixth International Conference on Computer Vision, Bombay, India, p.959-966.

[8] Li, H.H., Zhou, Y.T., 1996. Automatic visual/IR image registration. Optical Engineering, 35(2):391-400.

[9] Li, H., Manjunath, B.S., Mitra, S.K., 1995. A contour based approach to multisensor image registration. IEEE Trans. on Image Processing, 4(3):320-334.

[10] Li, Q., Zheng, N.N., Ma, L., Cheng, H., 2004. Principal Component Analysis Neural Network Based Probabilistic Tracking of Unpaved Road. International Symposium on Neural Networks, Dalian, China, p.792-797.

[11] Rui, Y., He, L.W., Gupta, A., Liu, Q., 2001. Building an Intelligent Camera Management System. Proceedings of the Ninth ACM International Conference on Multimedia, Ottawa, Canada, p.2-11.

[12] Rignot, E.J.M., Kowk, R., Curlander, J.C., Pang, S., 1991. Automated multisensor registration: Requirements and techniques. Photogrammetry Engineering and Remote Sensing Journal, 57(8):1029-1038.

[13] Reddy, B.S., Chatterji, B.N., 1996. An FFT-based technique for translation, rotation, and scale-invariant image registration. IEEE Trans. on Image Processing, 5(8):1266-1271.

[14] Viola, P., Wells, W.M., 1997. Alignment by maximization of mutual information. International Journal of Computer Vision, 24(2):137-154.

[15] Worring, M., 1993. Shape Analysis of Digital Curves. Ph.D Thesis. University of Amsterdam.