Abstract
Traditionally, in machine vision images are represented using cartesian coordinates with uniform sampling along the axes. On the contrary, biological vision systems represent images using polar coordinates with non-uniform sampling. For various advantages provided by space-variant representations many researchers are interested in space-variant computer vision. In this direction the current work proposes a novel and simple space variant representation of images. The proposed representation is compared with the classical log-polar mapping. The log-polar representation is motivated by biological vision having the characteristic of higher resolution at the fovea and reduced resolution at the periphery. On the contrary to the log-polar, the proposed new representation has higher resolution at the periphery and lower resolution at the fovea. Our proposal is proved to be a better representation in navigational scenarios such as driver assistance systems and robotics. The experimental results involve analysis of optical flow fields computed on both proposed and log-polar representations. Additionally, an egomotion estimation application is also shown as an illustrative example. The experimental analysis comprises results from synthetic as well as real sequences.
Similar content being viewed by others
References
Adato, Y., Zickler, T., Ben-Shahar, O.: A polar representation of motion and implications for optical flow. In: IEEE Int. Conference on Computer Vision and Pattern Recognition, Colorado Springs, USA, pp. 1145–1152 (2011)
Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M., Szeliski, R.: A database and evaluation methodology for optical flow. In: IEEE Int. Conference on Computer Vision, Rio de Janeiro, Brazil, pp. 1–8 (2007)
Barnes, N., Sandini, G.: Direction control for an active docking behaviour based on the rotational component of log-polar optic flow. In: European Conference on Computer Vision, Dublin, Ireland, pp. 167–181 (2000)
Barron, J.L., Fleet, D.J., Beauchemin, S.S.: Performance of optical flow techniques. Int. J. Comput. Vis. 12(1), 43–77 (1994)
Bolduc, M., Levine, M.D.: A review of biologically motivated space-variant data reduction models for robotic vision. Comput. Vis. Image Underst. 69(2), 170–184 (1998)
Boluda, J.A., Domingo, J., Pardo, F., Pelechano, J.: Detecting motion independent of the camera movement through a log-polar differential approach. In: Computer Analysis of Images and Patterns, Kiel, Germany, pp. 702–709 (1997)
Bruhn, A.: Variational optic flow computation: accurate modelling and efficient numerics. Ph.D. thesis, Department of Mathematics and Computer Science, Saarland University, Saarbrcken (2006)
Cheda, D., Ponsa, D., Lopez, A.: Camera egomotion estimation in the ADAS context. In: IEEE Int. Conference on Intelligent Transportation Systems, Madeira Island, Portugal, pp. 1415–1420 (2010)
Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley-Interscience, New York (1991)
Daniilidis, K.: Computation of 3-d-motion parameters using the log-polar transform. In: Computer Analysis of Images and Patterns, Prague, Czech Republic, pp. 82–89 (1995)
Daniilidis, K., Krüger, V.: Optical flow computation in the log-polar-plane. In: Computer Analysis of Images and Patterns, Prague, Czech Republic, pp. 65–72 (1995)
Dias, J., Araújo, H., Paredes, C., Batista, J.: Optical normal flow estimation on logpolar images. A solution for real-time binocular vision. Real-Time Imaging 3(3), 213–228 (1997)
Fischl, B., Cohen, M.A., Schwartz, E.L.: Rapid anisotropic diffusion using space-variant vision. Int. J. Comput. Vis. 28, 199–212 (1998)
Fischler, M., Bolles, R.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Graph. Image Process. 24(6), 381–395 (1981)
Guiasu, S.: Information Theory with Applications. McGraw-Hill Inc., New York (1977)
Horn, B.K.P., Schunk, B.G.: Determining optical flow. Artif. Intell. 17, 185–203 (1981)
Kukelova, Z., Bujnak, M., Pajdla, T.: Polynomial eigenvalue solutions to the 5-pt and 6-pt relative pose problems. In: British Machine Vision Conference, Leeds, UK (2008)
Liu, C., Freeman, W.T., Adelson, E.H., Weiss, Y.: Human-assisted motion annotation. In: IEEE International Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska, USA, pp. 1–8 (2008)
Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision (darpa). In: DARPA Image Understanding Workshop, pp. 121–130 (1981)
Onkarappa, N., Sappa, A.D.: On-board monocular vision system pose estimation through a dense optical flow. In: Int. Conference on Image Analysis and Recognition, Póvoa de Varzim, Portugal, pp. 230–239 (2010)
Onkarappa, N., Sappa, A.D.: An empirical study on optical flow accuracy depending on vehicle speed. In: IEEE Intelligent Vehicles Symposium, Alcalá de Henares, Spain, pp. 1138–1143 (2012)
Roth, S., Black, M.J.: On the spatial statistics of optical flow. In: IEEE Int. Conference on Computer Vision, Beijing, China, pp. 42–49 (2005)
Schwartz, E.L., Greve, D.N., Bonmassar, G.: Space-variant active vision: definition, overview and examples. Neural Netw. 8(7–8), 1297–1308 (1995)
Sun, D., Roth, S., Black, M.J.: Secrets of optical flow estimation and their principles. In: IEEE Int. Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, pp. 2432–2439 (2010)
Tian, T.Y., Tomasi, C., Heeger, D.J.: Comparison of approaches to egomotion computation. In: IEEE Int. Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, pp. 315–320 (1996)
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. 15(4), 401–410 (1993)
Traver, V.J., Bernardino, A.: A review of log-polar imaging for visual perception in robotics. Robot. Auton. Syst. 58(4), 378–398 (2010)
Traver, V.J., Pla, F.: The log-polar image representation in pattern recognition tasks. In: Iberian Conference on Pattern Recognition and Image Analysis, pp. 1032–1040 (2003)
Traver, V.J., Pla, F.: Motion analysis with the radon transform on log-polar images. J. Math. Imaging Vis. 30(2), 147–165 (2008)
Tunley, H., Young, D.: First order optic flow from log-polar sampled images. In: European Conference on Computer Vision, Stockholm, Sweden, vol. 1, pp. 132–137 (1994)
Vaudrey, T., Rabe, C., Klette, R., Milburn, J.: Differences between stereo and motion behaviour on synthetic and real-world stereo sequences. In: Proc. Image and Vision Computing New Zealand, Christchurch, New Zealand, pp. 1–6 (2008)
Wallace, R.S., Ong, P.W., Bederson, B.B., Schwartz, E.L.: Space variant image processing. Int. J. Comput. Vis. 13, 71–90 (1994)
Yeasin, M.: Optical flow in log-mapped image plane-a new approach. IEEE Trans. Pattern Anal. Mach. Intell. 24(1), 125–131 (2002)
Yeung, A., Barnes, N.: Efficient active monocular fixation using the log-polar sensor. Int. J. Intell. Syst. Technol. Appl. 1, 157–173 (2005)
Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-L 1 optical flow. In: Annual Symposium of the German Association for Pattern Recognition, Heidelberg, Germany, pp. 214–223 (2007)
Adiv, G.: Inherent ambiguities in recovering 3-D motion and structure from a noisy flow field. IEEE Trans. Pattern Anal. Mach. Intell. 11(5), 477–489 (1989)
Fermuller, C., Aloimonos, Y.: Ambiguity in structure from motion: sphere versus plane. Int. J. Comput. Vis. 28(2), 137–154 (1998)
Acknowledgements
This work has been partially supported by the Spanish Government under Research Program Consolider Ingenio 2010: MIPRCV (CSD2007-00018) and Project TIN2011-25606. Naveen Onkarappa is supported by FI grant of AGAUR, Catalan Government. Authors gratefully acknowledge discussions with Henning Zimmer and Prof. Joachim Weickert. The authors would like to thank Oisin Mac Aodha for providing the Python code for raytracing with Maya, and Diego Cheda for the help in egomotion estimation.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Onkarappa, N., Sappa, A.D. A Novel Space Variant Image Representation. J Math Imaging Vis 47, 48–59 (2013). https://doi.org/10.1007/s10851-012-0384-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-012-0384-5