An Optimization Approach for Translational Motion Estimation in Log-Polar Domain
Log-polar imaging is an important topic in space-variant active vision, and facilitates some visual tasks. Translation estimation, though essential for active tracking, is more difficult in (log-)polar coordinates. We propose here a novel, conceptually simple, effective, and efficient method for translational motion estimation. It is based on a gradient-based minimization procedure. Experimental results with log-polar images using a software-based log-polar remmapper are presented.
Keywordsmotion estimation log-polar domain
Unable to display preview. Download preview PDF.
- 1.Ahrns, I., Neumann, H.: Real-time monocular fixation control using the log-polar transformation and a confidence-based similarity measure. In: Jain, A.K., Venkatesh, S., Lovell, B.C. (eds.): Intl. Conf. on Pattern Recognition (ICPR). Brisbane, Australia (Aug. 1998) 310–315Google Scholar
- 2.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. Dublin, Ireland (Jun 2000) 167–181Google Scholar
- 4.Bolduc, M., Levine, M.D.: A review of biologically motivated space-variant data reduction models for robotic vision. Computer Vision and Image Understanding (CVIU) 69(2) (Feb 1998) 170–184Google Scholar
- 6.Brown, L.G.: A survey of image registration techniques. ACM Computing Surveys 24(4) (Dec 1992) 325–376Google Scholar
- 7.Jurie, F.: A new log-polar mapping for space variant imaging. Application to face detection and tracking. Pattern Recognition 32 (1999) 865–875Google Scholar
- 8.Okajima, N., Nitta, H., Mitsuhashi, W.: Motion estimation and target tracking in the log-polar geometry. 17th Sensor Symposium. Kawasaki, Japan (May 2000) chihara3.aist-nara.ac.jp/gakkai/sensor17Google Scholar