Title: Efficient active monocular fixation using the log-polar sensor

Authors: Albert Yeung, Nick Barnes

Addresses: Department of Computer Science and Software Engineering, University of Melbourne, Victoria 3010, Australia. ' National ICT Australia, Locked Bag 8001, Canberra, ACT 2601, Australia Research School for Information Sciences and Engineering, The Australian National University, ACT, 0200, Australia

Abstract: This paper applies a sensor which has been developed based on a model of primate vision to corner fixation. Fixation is critical for the log-polar sensor as many of the sensor|s advantages are demonstrated only under fixation. This paper presents a fast corner fixation algorithm using the log-Hough transform to find the dominant centremost corner and align the optical axis with the corner. The algorithm has been implemented in a real-time closed-loop control system on a pan-tilt platform. This paper demonstrates an important benefit of the log-polar sensor with vote-based algorithms, an emphasis of foveal pixels. This removes the need for searching explicitly through all detected corner positions in order to locate the most central. In addition, since the sensor has a large field of view for a given number of pixels compared to space-invariant cameras, it shows increased computational performance, while still supporting accurate fixation.

Keywords: primate vision; biorobotics; biologically inspired robots; biologically inspired sensing; fast corner fixation; log-polar sensors; closed loop control; vote-based algorithms; robotic perceptuo-motor loops; robot sensors; robot vision; biomechatronics.

DOI: 10.1504/IJISTA.2005.007313

International Journal of Intelligent Systems Technologies and Applications, 2005 Vol.1 No.1/2, pp.157 - 173

Published online: 05 Jul 2005 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article