Log-Polar Stereo for Anthropomorphic Robots
Stereoscopic vision has a fundamental role both for animals and humans. Nonetheless, in the computer vision literature there is limited reference to biological models related to stereoscopic vision and, in particular, to the functional properties and the organization of binocular information within the visual cortex.
In this paper a simple stereo technique, based on a space variant mapping of the image data and a multi-layered cortical stereoscopic representation, mimicking the neural organization of the early stages of the human visual system, is proposed. Radial disparity computed from a stereo pair is used to map the relative depth with respect to the fixation point. A set of experiments demonstrating the applicability of the devised techniques is also presented.
KeywordsHuman Visual System Stereo Image Stereo Match Cortical Representation Stereoscopic Vision
- 3.Ming Xu, T. Akatsuka, “Detecting head pose from stereo image sequence for active face recognition,” Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition, Nara, Japan 1998.Google Scholar
- 4.D. H. Hubel, “Eye, Brain, and Vision,” Scientific American Library, 1988.Google Scholar
- 6.E. Grosso and M. Tistarelli, “Active/Dynamic Stereo Vision,” IEEE Trans. on PAMI, Vol. 17, Num. 9, pp. 868–889, 1995.Google Scholar
- 7.M. Xie and C.M. Lee and Z.Q. Li and S.D. Ma, “Depth assessment by using qualitative stereo-vision,” 1997 IEEE International conference on intelligent processing System, Beijing, China, 1997.Google Scholar
- 8.G. Sandini and V. Tagliasco, “An Anthropomorphic Retina-like Structure for Scene Analysis,” CGIP, Vol. 14, Num. 3, pp. 365–372, 1980.Google Scholar
- 9.C. Capurro, F. Panerai and G. Sandini, “Vergence and tracking fusing log-polar images,” Proceedings of the 13th International Conference on Pattern Recognition, Wien, Austria 1996.Google Scholar
- 10.C. F. R. Weiman, “Binocular stereo via log-polar retinas,” Proceedings of the SPIE-the International Society for Optical Engineering, Vol 2488, pp. 309–320, 1995.Google Scholar
- 11.N. Oshiro and A. Nishikawa and N. Maru and F. Miyazaki, “Binocular tracking based on retino-cortical mapping,” Transactions of the Institute of Systems, Control and information Engineers, Vol. 10, Num. 6, pp. 287–296, 1997.Google Scholar
- 13.M. Tistarelli and G. Sandini, “On the Advantages of Polar and Log-Polar Mapping for Direct Estimations of Time-to-Impact from Optical Flow,” IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 15, Num. 4, 1993.Google Scholar