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 . 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.
KeywordsMobile Robot Reference Image Scale Invariant Feature Transform Active Vision Rotation Error
Unable to display preview. Download preview PDF.
- 3.Zeil, J., Kelber, A., Voss, R.: Structure and function of learning flights in bees and wasps. J. Exp. Biol. 199, 245–252 (1996)Google Scholar
- 5.Zeil, J., Boeddeker, N., Hemmi, J.M.: Going wild: Towards an ecology of visual information processing. In: North, G., Greenspan, R. (eds.) Invertebrate Neurobiology, Cold Spring Harbor Laboratory Press, in press (2007)Google Scholar
- 11.Nayar, S.K.: Catadioptric omnidirectional camera. In: Computer Vision and Pattern Recognition, pp. 482–488 (1997)Google Scholar
- 12.Horvath, G., Varju, D.: Polarized Light in Animal Vision. Springer, Heidelberg (2004)Google Scholar
- 15.Efron, B., Tibshirani, R.: An Introduction to the Bootstrap. Chapman & Hall / CRC, Boca Raton (1998)Google Scholar
- 16.Schatz, A.: Visuelle Navigation mit “Scale Invariant Feature Transform”. Master’s thesis, Computer Engineering, Faculty of Technology, Bielefeld University (2006)Google Scholar
- 17.Makadia, A., Geyer, C., Daniilidis, K.: Radon-based structure from motion without correspondences. In: Computer Vision and Pattern Recognition, pp. 796–803 (2005)Google Scholar