Abstract
Image projections provide an effective way of describing image contents or estimate particular kinds of motion. However, most (if not all) of previous literature on projections has been done on Cartesian images. In contrast, the work described in this paper is aimed at exploring how projections can be defined on log-polar images and how they perform in estimating motion. In the proposed algorithm, a set of projection signals is computed in two consecutive frames. Then, 1D affine motion between each pair of corresponding projection signals is estimated. Finally, 2D image affine motion is derived from the set of estimated 1D motion parameters, using a 2D-1D motion mapping model (MMM). A reduced, 5-parameter, affine motion model can be estimated with this MMM. The algorithm is implemented in both, log-polar and Cartesian images. Synthetic motion is used for a careful analysis of the strengths and weaknesses of the algorithm. The comparison of the results with log-polar and Cartesian images reveal that the limitations of the approach are due to the MMM, rather than to the inherent difficulties and distortions introduced by the space-variant nature of log-polar images. Another significant finding is that Cartesian images require much more pixels than log-polar images to get comparable estimation performance.
Similar content being viewed by others
References
Ahrns, I., Neumann, H.: A view-based approach for real-time fixation using log-polar mapping. In: Freksa, C. (ed.) Proc. in Artificial Intelligence, pp. 89–96, June 1998
Barnes, N., Sandini, G.: Direction control for an active docking behavior based on the rotational component of log-polar optic flow. In: Tsai, W.-H., Lee, H.-J. (eds.) European Conf. on Computer Vision, vol. 2, pp. 167–181. Dublin, Ireland, June 2000
Bazin, P.-L., Vézien, J.-M.: Integration of geometric elements, euclidean relations, and motion curves for parametric shape and motion estimation. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 27(12), 1960–1976 (2005)
Bernardino, A., Santos-Victor, J.: Visual behaviors for binocular tracking. Robot. Auton. Syst. 25, 137–146 (1998)
Bernardino, A., Santos-Victor, J., Sandini, G.: Foveated active tracking with redundant 2D motion parameters. Robot. Auton. Syst. 39(3–4), 205–221 (2002)
Bolduc, M., Levine, M.D.: A review of biologically motivated space-variant data reduction models for robotic vision. Comput. Vis. Image Underst. (CVIU) 69(2), 170–184 (1998)
Capurro, C., Panerai, F., Sandini, G.: Dynamic vergence using log-polar images. Int. J. Comput. Vis. 24(1), 79–94 (1997)
Daniilidis, K., Krüger, V.: Optical flow computation in the log-polar plane. In: Hlaváč, V., Šára, R. (eds.) Int. Conf. on Computer Analysis of Images and Patterns (CAIP), pp. 65–72. Springer, Berlin (1995)
Dias, J., Araujo, H., Paredes, C., Batista, J.: Optical normal flow estimation on log-polar images. A solution for real-time binocular vision. Real-Time Imaging 3(3), 213–228 (1997)
Fermüller, C., Aloimonos, Y.: Qualitative egomotion. Int. J. Comput. Vis. 15, 7–29 (1995)
Hager, G.D., Belhumeur, P.N.: Efficient region tracking with parametric models of geometry and illumination. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 20(10), 1025–1039 (1998)
Harris, J., Stocker, H.: Handbook of Mathematics and Computation Science. Springer, New York (1998)
Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004)
Huang, Y., Palaniappan, K., Zhuang, X., Cavanaugh, J.E.: Optic flow field segmentation and motion estimation using a robust genetic partitioning algorithm. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 17(12), 1177–1190 (1995)
Kadyrov, A., Petrou, M.: Affine parameter estimation from the Trace transform. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 28(10), 1631–1645 (2006)
Kang, S., Lee, S.-W.: Real-time tracking of multiple objects in space-variant vision based on magnocellular visual pathway. Pattern Recognit. 35(10), 2031–2040 (2002)
Kim, Y.-H., Martínez, A.M., Kak, A.C.: Robust motion estimation under varying illumination. Image Vis. Comput. (IVC) 23(4), 365–375 (2005)
Krüger, V.: Optical flow estimation in the complex logarithmic plane. Master’s thesis, University of Kiel, Germany (1995)
Manzotti, R., Gasteratos, A., Metta, G., Sandini, G.: Disparity estimation on log-polar images and vergence control. Comput. Vis. Image Underst. (CVIU) 83, 97–117 (2001)
Milanfar, P.: A model of the effect of image motion in the Radon transform domain. IEEE Trans. Image Process. 8(9), 1276–1281 (1999)
Montoliu, R., Pla, F.: Accurate image registration by combinig feature-based matching and GLS-based motion estimation. In: International Conference on Computer Vision Theory and Applications, pp. 386–389, March 2007
Okajima, N., Nitta, H., Mitsuhashi, W.: Motion estimation and target tracking in the log-polar geometry. In: 17th Sensor Symposium. Kawasaki, Japan, May 2000
Oshiro, N., Maru, N., Nishikawa, A., Miyazaki, F.: Binocular tracking using log polar mapping. In: IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, vol. 2, pp. 791–798. Osaka, Japan, November 1996
Robinson, D., Milanfar, P.: Efficiency and accuracy tradeoffs in using projections for motion estimation. In: 35th Asilomar Conference on Signals, Systems, and Computers, pp. 545–550, November 2001
Robinson, D., Milanfar, P.: Fast local and global projection-based methods for affine motion estimation. J. Math. Imaging Vis. 18(1), 35–54 (2003)
Sandini, G., Metta, G.: Retina-like sensors: motivations, technology and applications. In: Barth, F.G., Humphrey, J.A., Secomb, T.W. (eds.) Sensors and Sensing in Biology and Engineering. Springer, New York (2003)
Schwartz, E.L.: Spatial mapping in the primate sensory projection: Analytic structure and relevance to perception. Biol. Cybern. 25, 181–194 (1977)
Shin, C.W., Inokuchi, S., Kim, K.I.: Retina-like visual sensor for fast tracking and navigation robots. Mach. Vis. Appl. 10, 1–8 (1997)
Silva, C., Santos-Victor, J.: Egomotion estimation using log-polar images. In: Int. Conf. on Computer Vision. Bombay, India, January 1998
Stiller, C., Konrad, J.: Estimating motion in image sequences: A tutorial on modeling and computation of 2D motion. IEEE Signal Process. Mag. 16(4), 70–91 (1999)
Swain, M., Stricker, M.: Promising directions in active vision. Int. J. Comput. Vis. 11(2), 109–126 (1993)
Tistarelli, M., Sandini, G.: On the advantages of polar and log-polar mapping for direct estimation of time-to-impact from optical flow. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 15, 401–410 (1993)
Traver, V.J., Pla, F.: Motion estimation and figure-ground segmentation in log-polar images. In: Int. Conf. on Pattern Recognition (ICPR), pp. 166–169. Québec, Canada, August 2002
Traver, V.J., Pla, F.: Radon-like transforms in log-polar images for affine motion estimation. In: Portuguese Conf. on Pattern Recognition. Aveiro, Portugal, June 2002
Tunley, H., Young, D.: First order optic flow from log-polar sampled images. In: Eklundh, J.-O. (ed.) European Conf. on Computer Vision. LNCS, vol. 800, pp. 132–137. Springer, New York (1994)
Venkatachalapathy, K., Krishnamoorthy, R., Viswanath, K.: A new adaptive search strategy for fast block based motion estimation algorithms. J. Vis. Commun. Image Represent. 15(2), 203–213 (2004)
Wilson, J.C., Hodgson, R.M.: Log-polar mapping applied to pattern representation and recognition. In: Computer Vision and Image Processing, pp. 245–277. Academic Press, New York (1992)
Yeasin, M.: Optical flow in log-mapped image plane: A new approach. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 24(1), 125–131 (2002)
Zokai, S., Wolberg, G.: Image registration using log-polar mappings for recovery of large-scale similarity and projective transformations. IEEE Trans. Image Process. 14(10), 1422–1434 (2005)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Traver, V.J., Pla, F. Motion Analysis with the Radon Transform on Log-Polar Images. J Math Imaging Vis 30, 147–165 (2008). https://doi.org/10.1007/s10851-007-0046-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-007-0046-1