ArticlesNo Access

Correcting Distortions in Panoramic Images Using Constructive Neural Networks

Department of Intellectual Information Systems, Faculty of Engineering, Toyama University, 3190 Gofuku, Toyama, 930-8555, Japan

Search for more papers by this author

Masaaki Yoneda

Department of Intellectual Information Systems, Faculty of Engineering, Toyama University, 3190 Gofuku, Toyama, 930-8555, Japan

Search for more papers by this author

, and

Hiroyuki Hase

Department of Information Science, Faculty of Engineering, Fukui University, 3-9-1 Bunkyo, Fukui, 910-8507, Japan

Search for more papers by this author

https://doi.org/10.1142/S0129065703001601Cited by:7 (Source: Crossref)

Abstract

This paper presents a novel approach to the correction of panoramic (wide-angle) image distortions. Unlike traditional methods that separate the distortion of the panoramic image into radial and tangential components and then concentrate on the correction of one type of distortion at a time, the method presented in this paper uses an integrated approach that simultaneously corrects all non-linear distortions of the panoramic image. The system uses data obtained from carefully constructed calibration patterns to automatically build and train a constructive neural network of suitable complexity to approximate the characteristic distortion of the panoramic image. The trained neural network is then used to correct the distortions represented by the sample data. It is demonstrated that by applying the distortion correction method presented in this paper to panoramic images representing real world scenes, perspective-corrected views of the real world scene that are usable in a wide variety of applications can be generated.

Keywords:

References

R. Benosman, Panoramic imaging from 1767 to the present, Proc. International Conference on Advanced Robotics, Workshop1 (2001) pp. 9–10. Google Scholar
R. Szeliski, Computer Graphics and Applications 16(3), 23 (1996). Google Scholar
H. Sawhney, S. Hsu and R. Kumar, Robust video mosaicing through topology inference and local to global alignment, Proc. Fifth European Conference on Computer Vision2 (1998) pp. 103–119. Google Scholar
T. Boult, Remote reality demonstration, Proc. IEEE Conference on Computer Vision and Pattern Recognition (1998) pp. 966–967. Google Scholar
S. Shah and J. Aggarwal, Pattern Recognition 29(11), 1775 (1996). Crossref, Web of Science, Google Scholar
R. Raskaret al., The office of the future: a unified approach to image-based modeling and spatially immersive displays, ACM SIGGRAPH (1998) pp. 179–188. Google Scholar
P. Greguss, Laser and Optoelektronik 28, 43 (1996). Web of Science, Google Scholar
Y. Onoeet al., Computer Vision and Image Understanding 71(2), 154 (1998). Crossref, Web of Science, Google Scholar
C. Fermuller, Y. Aloimonos and T. Brodsky, Computational Geometry: Theory and Applications 15, 3 (2000). Crossref, Web of Science, Google Scholar
Y. Yagi, S. Kawato and S. Tsuji, IEEE Transactions on Robotics and Automation 10(1), 11 (1994). Crossref, Google Scholar
Y. Yagi, S. Nishizawa and S. Tsuji, IEEE Transactions on Robotics and Automation 11(5), 634 (1995). Crossref, Google Scholar
J. Zheng and S. Tsuji, International Journal of Computer Vision 9(1), 55 (1992). Web of Science, Google Scholar
J. Chahl and M. Srinivasan, Applied Optics 36, 8275 (1997). Crossref, Medline, Web of Science, Google Scholar
A. Hicks and R. Bajcsy, Image and Vision Computing 19(11), 773 (2001). Crossref, Web of Science, Google Scholar
C. Geyer and K. Daniilidis, Catadioptric projective geometry, Proc. International Conference on Advanced Robotics1 (2001) pp. 17–30. Google Scholar
D. Drucker and P. Locke, Mathematics Magazine 69, 249 (1996). Crossref, Google Scholar
Y. Yagi, IEICE Transactions on Information & Systems E 82-D(3), 568 (1999). Google Scholar
F. Ekpar, H. Hase and M. Yoneda, Constructing arbitrary perspective-corrected views from panoramic images using neural networks, Proc. 7th International Conference on Neural Information Processing1 (2000) pp. 156–160. Google Scholar
D. E. Rumelhart, Nature 323, 533 (1986). Crossref, Web of Science, Google Scholar
S. E. Fahlman and C. Lebiere, Advances in Neural Information Processing Systems 2, 524 (1990). Google Scholar
S. J. Hanson, Advances in Neural Information Processing Systems 2, 533 (1990). Google Scholar