An Insect-Inspired Active Vision Approach for Orientation Estimation with Panoramic Images

We present an insect-inspired approach to orientation estimation for panoramic images. It has been shown by Zeil et al. (2003) that relative rotation can be estimated from global image differences, which could be used by insects and robots as a visual compass [1]. However the performance decreases gradually with the distance of the recording positions of the images. We show that an active vision approach based on local translational movements can significantly improve the orientation estimation. Tests were performed with a mobile robot equipped with a panoramic imaging system in a large entrance hall. Our approach is minimalistic insofar as it is solely based on image differences.

[1]  Andrew Vardy,et al.  Biologically plausible visual homing methods based on optical flow techniques , 2005, Connect. Sci..

[2]  M. Land.  Visual acuity in insects. , 1997, Annual review of entomology.

[3]  M. Srinivasan,et al.  Reflective surfaces for panoramic imaging. , 1997, Applied optics.

[4]  M. Lehrer.  Why do bees turn back and look? , 1993, Journal of Comparative Physiology A.

[5]  Andrew Vardy,et al.  Local visual homing by matched-filter descent in image distances , 2006, Biological Cybernetics.

[6]  Bernhard Schölkopf,et al.  Where did I take that snapshot? Scene-based homing by image matching , 1998, Biological Cybernetics.

[7]  R. Tibshirani,et al.  An Introduction to the Bootstrap , 1995 .

[8]  M. Srinivasan,et al.  Range estimation with a panoramic visual sensor , 1997 .

[9]  S. Shankar Sastry,et al.  Radon-based structure from motion without correspondences , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Wolfgang Stürzl,et al.  Going Wild: Toward an Ecology of Visual Information Processing , 2007 .

[11]  Dr. habil. Gábor Horváth,et al.  Polarized Light in Animal Vision , 2004, Springer Berlin Heidelberg.

[12]  Jochen Zeil,et al.  Catchment areas of panoramic snapshots in outdoor scenes. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

[13]  T. S. Collett,et al.  Landmark maps for honeybees , 1987, Biological Cybernetics.

[14]  Hanspeter A. Mallot,et al.  Efficient visual homing based on Fourier transformed panoramic images , 2006, Robotics Auton. Syst..

[15]  J. Zeil,et al.  Structure and function of learning flights in bees and wasps , 1996 .

[16]  Shree K. Nayar,et al.  Catadioptric omnidirectional camera , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.