Normalized Cross-Correlation for Spherical Images
Abstract
Recent advances in vision systems have spawned a new generation of image modalities. Most of today’s robot vehicles are equipped with omnidirectional sensors which facilitate navigation as well as immersive visualization. When an omnidirectional camera with a single viewpoint is calibrated, the original image can be warped to a spherical image. In this paper, we study the problem of template matching in spherical images. The natural transformation of a pattern on the sphere is a 3D rotation and template matching is the localization of a target in any orientation. Cross-correlation on the sphere is a function of 3D-rotation and it can be computed in a space-invariant way through a 3D inverse DFT of a linear combination of spherical harmonics. However, if we intend to normalize the cross-correlation, the computation of the local image variance is a space variant operation. In this paper, we present a new cross-correlation measure that correlates the image-pattern cross-correlation with the autocorrelation of the template with respect to orientation. Experimental results on artificial as well as real data show accurate localization performance with a variety of targets.
Keywords
Spherical Harmonic Template Match Real Position Fourier Descriptor Normalize CorreReferences
- 1.Nayar, S.: Catadioptric omnidirectional camera. In: IEEE Conf. Computer Vision and Pattern Recognition, Puerto Rico, June 17-19, pp. 482–488 (1997)Google Scholar
- 2.Baker, S., Nayar, S.: A theory of catadioptric image formation. In: Proc. Int. Conf. on Computer Vision, Bombay, India, January 3-5, pp. 35–42 (1998)Google Scholar
- 3.Brunelli, R., Poggio, T.: Template matching: Matched spatial filters and beyond. Pattern Recognition 30, 751–768 (1997)CrossRefGoogle Scholar
- 4.Turk, M., Pentland, A.: Eigenfaces for recognition. Journal of Cognitive Neuroscience 3, 72–86 (1991)CrossRefGoogle Scholar
- 5.Hall, E.: Computer Image Processing and Recognition. Academic Press, London (1979)zbMATHGoogle Scholar
- 6.Sato, J., Cipolla, R.: Extracting group transformations from image moments. Computer Vision and Image Understanding 73, 29–42 (1999)zbMATHCrossRefGoogle Scholar
- 7.Zahn, C., Roskies, R.: Fourier descriptors for plane close curves. IEEE Trans. Computers 21, 269–281 (1972)zbMATHCrossRefMathSciNetGoogle Scholar
- 8.Lenz, R.: Rotation-invariant operators. In: Proc. Int. Conf. on Pattern Recognition, Paris, France, September 28-3, pp. 1130–1132 (1986)Google Scholar
- 9.Tanaka, M.: On the representation of the projected motion group in 2+1d. Pattern Recognition Letters 14, 671–678 (1993)zbMATHCrossRefGoogle Scholar
- 10.Segman, J., Rubinstein, J., Zeevi, Y.: The canonical coordinates method for pattern deformation: Theoretical and computational considerations. IEEE Trans. Pattern Analysis and Machine Intelligence 14, 1171–1183 (1992)CrossRefGoogle Scholar
- 11.Arfken, G., Weber, H.: Mathematical Methods for Physicists. Academic Press, London (1966)zbMATHGoogle Scholar
- 12.Driscoll, J., Healy, D.: Computing fourier transforms and convolutions on the 2-sphere. Advances in Applied Mathematics 15, 202–250 (1994)zbMATHCrossRefMathSciNetGoogle Scholar
- 13.Talman, J.D.: Special Funcitons. W.A.Benjamin Inc., Amsterdam (1968)Google Scholar
- 14.Sorgi, L., Daniilidis, K.: Template matching for spherical images. In: SPIE 16 Annual Symposium Electronic Imaging, San Jose, CA, January 18-22 (2004)Google Scholar
- 15.Geyer, C., Daniilidis, K.: Catadioptric projective geometry. International Journal of Computer Vision 43, 223–243 (2001)CrossRefGoogle Scholar