Dealing with 2D translation estimation in log-polar imagery

Abstract Log-polar mapping has been proposed as a very appropriate space-variant imaging model in active vision applications. This biologically inspired model has several advantages, and facilitates some visual tasks. For example, it provides an efficient data reduction, and simplifies rotational and scaling image transformations. However, simple translations become a difficult transform due to the log-polar geometry. There is no doubt about the importance of translation estimation in active visual tracking. Therefore, in this work, the problem of translation estimation in log-polar images is tackled. Two different approaches are presented, and their performances are evaluated and compared. One approach uses a gradient descent for minimizing a dissimilarity measure, while the other converts the 2D problem into two simpler 1D problems, by using projections. As the experimental results reveal, this second approach, besides being more efficient, can deal with larger translations than the gradient-based search can.

[1]  Jan Paredaens,et al.  Finite stochastic automata with variable transition probabilities , 1973, Computing.

[2]  Helder Araújo,et al.  Optical Normal Flow Estimation on Log-polar Images. A Solution for Real-Time Binocular Vision , 1997, Real Time Imaging.

[3]  Alexandre Bernardino,et al.  Visual behaviours for binocular tracking , 1998, Robotics Auton. Syst..

[4]  Kostas Daniilidis,et al.  Optical Flow Computation in the Log-Polar-Plane , 1995, CAIP.

[5]  Alexandre Bernardino,et al.  Binocular tracking: integrating perception and control , 1999, IEEE Trans. Robotics Autom..

[6]  Giulio Sandini,et al.  Dynamic Vergence Using Log-Polar Images , 1997, International Journal of Computer Vision.

[7]  Kostas Daniilidis,et al.  Attentive Visual Motion Processing: Computations in the Log-Polar Plane , 1994, Theoretical Foundations of Computer Vision.

[8]  Yiannis Aloimonos,et al.  Active vision , 2004, International Journal of Computer Vision.

[9]  Marco Balsi.  CELLULAR NEURAL NETWORKS DEFINED ON LOG-POLAR GRIDS FOR ARTIFICIAL VISION , 1997 .

[10]  Frédéric Jurie,et al.  A new log-polar mapping for space variant imaging.: Application to face detection and tracking , 1999, Pattern Recognit..

[11]  E. L. Schwartz,et al.  Spatial mapping in the primate sensory projection: Analytic structure and relevance to perception , 1977, Biological Cybernetics.

[12]  Svetha Venkatesh,et al.  Tracking in a space variant active vision system , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[13]  Fumio Miyazaki,et al.  Binocular tracking using log polar mapping , 1996, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS '96.

[14]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

[15]  William H. Press,et al.  Numerical recipes in C , 2002 .

[16]  Giulio Sandini,et al.  A retina-like CMOS sensor and its applications , 2000, Proceedings of the 2000 IEEE Sensor Array and Multichannel Signal Processing Workshop. SAM 2000 (Cat. No.00EX410).

[17]  Giulio Sandini,et al.  Space-variant vision for an active camera mount , 1995, Defense, Security, and Sensing.

[18]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[19]  David S. Young,et al.  Dynamic Fixation of a Moving Surface Using Log Polar Sampling , 1994, BMVC.

[20]  Carl F. R. Weiman,et al.  Tracking Algorithms Using Log-Polar Mapped Image Coordinates , 1990, Other Conferences.

[21]  John Harris,et al.  Handbook of mathematics and computational science , 1998 .

[22]  Ze-Nian Li,et al.  Reciprocal-Wedge Transform for Space-Variant Sensing , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  F. Pardo,et al.  A new foveated space-variant camera for robotic applications , 1996, Proceedings of Third International Conference on Electronics, Circuits, and Systems.

[24]  Alexandre Bernardino.  Tracking Planar Structures With Log-Polar Images , 2000 .

[25]  Andrea Giachetti,et al.  Matching techniques to compute image motion , 2000, Image Vis. Comput..

[26]  HIROYUKI YAMAMOTO,et al.  An Active Foveated Vision System: Attentional Mechanisms and Scan Path Covergence Measures , 1996, Comput. Vis. Image Underst..

[27]  Martin D. Levine,et al.  Information Processing in Primate Retinal Cone Pathways: A Model , 1993 .

[28]  R. M. Hodgson,et al.  Biologically inspired image processing , 1995 .

[29]  William H. Press,et al.  Numerical recipes in C. The art of scientific computing , 1987 .

[30]  Richard Alan Peters,et al.  On the Computation of the Log-Polar Transform , 1996 .

[31]  Singiresu S. Rao,et al.  Optimization Theory and Applications , 1980, IEEE Transactions on Systems, Man, and Cybernetics.

[32]  Nicolai Petkov,et al.  Computer Analysis of Images and Patterns , 2003, Lecture Notes in Computer Science.

[33]  M. Bober,et al.  Estimating Translation/Deformation Motion through Phase Correlation , 1997, ICIAP.

[34]  Martin D. Levine,et al.  A Review of Biologically Motivated Space-Variant Data Reduction Models for Robotic Vision , 1998, Comput. Vis. Image Underst..

[35]  John L. Barron,et al.  Image Reconstruction Error for Optical Flow , 1995, Research in Computer and Robot Vision.

[36]  Luca Lucchese,et al.  A Frequency Domain Technique Based on Energy Radial Projections for Robust Estimation of Global 2D Affine Transformations , 2001, Comput. Vis. Image Underst..