Numerical Estimation of Epipolar Curves for Omnidirectional Sensors. Estimation Numérique des Courbes Épipolaires pour les Capteurs Omnidirectionnels

Numerical Estimation of Epipolar Curves for Omnidirectional Sensors

Estimation Numérique des Courbes Épipolaires pour les Capteurs Omnidirectionnels

Jonathan Fabrizio Jean Devars 

UPMC/LISIF, 4 place Jussieu, case courrier 203, 75252 Paris cedex 05

Corresponding Author Email: 
fabrizio@lis.jussieu.fr
Page: 
527-535
|
Received: 
27 May 2005
| |
Accepted: 
N/A
| | Citation

OPEN ACCESS

Abstract: 

The epipolar geometry of couples of omnidirectional sensors is often difficult to express analytically.We propose an algorithm to estimate numerically epipolar curves from omnidirectional pairs of stereovision.This algorithm is not limited to this type of sensors and works, for example, with a combination of a panoramic sensor and a traditional camera.Although the load of calculation necessary for this algorithm is heavy, it works with every kind of sensor (provided that the stereovision pair is completely calibrated) especially with sensor that do not respect the single viewpoint constraint.

Résumé

La géométrie épipolaire des paires de capteurs omnidirectionnels est souvent difficile à exprimer analytiquement. Nous proposons un algorithme pour estimer numériquement les courbes épipolaires des paires de capteurs omnidirectionnels. Cet algorithme n'est toutefois pas limité à ce type de capteur et fonctionne,par exemple,avec une combinaison d'un capteur panoramique et d'une caméra classique. Bien que la charge de calcul requise soit lourde,cet algorithme a l'avantage de fonctionner avec tous les types de capteurs,si la paire de capteurs est complètement calibrée (tous paramètres déterminés). En particulier l'algorithme est applicable pour les capteurs catadioptriques ne respectant pas la contrainte du foyer de projection unique.

Keywords: 

Epipolar geometry, Stereovision, Omnidirectional sensors.

Mots clés 

Géométrie épipolaire,Stéréovision,Capteurs omnidirectionnels. 

1. Introduction
2. Principe de la Méthode
3. Validation de l'Algorithme
4. Application à des Images Réelles
5. Conclusion
  References

[Ben97] Ryad BENOSMAN, Reconstruction d'environnements percus par un capteur panoramique de stéréovision et détermination des modèles CAO. PhD thesis, 1997. 

[BM92] Paul J. BESL and Neil MCKAY, A methode for registration of 3d shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2):239-256, February 1992. 

[BN99] Simon BAKER and Shree K. NAYAR,A theory of single-viewpoint catadioptric image formation. International Journal of Computer Vision, 35(2):175 - 196, 1999. 

[FB02] Mark FIALA and Anup BASU, Feature extraction and calibration for stereo reconstruction using non-svp optics in a panoramic stereovision sensor. Proceedings of the 3rd IEEE Workshop on Omnidirectionnal Vision, pages 79-86, June 2002. 

[FD04] Jonathan FABRIZIO and Jean DEVARS, The perspective-n-point problem for catadioptric sensors: An analytical approach. Internationnal conference on computer vision and graphics, September 2004. 

[FTB02] Jonathan FABRIZIO, Jean-Philippe TAREL and Ryad BENOSMAN, Calibration of panoramic catadioptric sensors made easier. In  Proceedings of IEEE Workshop on Omnidirectional Vision (Omnivis'02), pages 45-52, Copenhagen, Denmark, 2002. IEEE Computer Society. 

[GBL03] Jose-Joel GONZALEZ-BARBOSA and Simon LACROIX, Un algorithme rapide de stéréovision panoramique dense. Technical Report 03561, LAAS-CNRS, 2003. 

[GD03] Christopher GEYER and Kostas DANIILIDIS, Conformal rectification of omnidirectional stereo pairs. Proceedings of the 4th Workshop on Omnidirectionnal Vision, June 2003. 

[GTN98] Joshua M. GLUCKMAN, Keith THOREK and Shree K. NAYAR, Real time panoramic stereo. Proc. of Image Understanding Workshop, 1998. 

[Har93] R. HARTLEY, Cheirality invariants, pages 745-753, 1993. 

[IYT92] Hiroshi ISHIGURO, Masashi YAMAMOTO and Saburo TSUJI, Omni-directional stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2):257-262, 1992. 

[LB03] S. S. LIN and R. BAJCSY, High resolution catadioptric omni-directional stereo sensor for robot vision. Proceedings of the IEEE International Conference on Robotics and Automation, pages 16941699, September 2003. 

[NN98] Sameer A. NENE and Shree NAYAR, Stereo with mirrors. Proceedings of the 6th International Conference on Computer Vision, Bombay, January 1998. 

[SBFR96] D. SOUTHWELL, A. BASU, M. FIALA and J. REYDA, Panoramic stereo. International Conference on Pattern Recognition, 1996. 

[SGK01] R. SWAMINATHAN, M. D. GROSSBERG and NAYAR S. K., Caustics of catadioptric cameras. In IEEE International Conference on Computer Vision, Vancouver, Canada, 2001. 

[Sma03] Laurent SMADJA, Génération d'environnements 3D denses à partir d'images panoramiques cylindriques. PhD thesis, 2003. 

[SR04] Peter STURM and Srikumar RAMALINGAM, A generic concept for camera calibration. European Conference on Computer Vision, May 2004. 

[Stu02] Peter STURM, Mixing catadioptric and perspective cameras. Proceedings of the 3rd IEEE Workshop on Omnidirectionnal Vision, pages 37-44, June 2002. 

[Svo99] Tomᡠs SVOBODA, Central Panoramic Cameras Design, Geometry, Egomotion. PhD thesis, 1999. 

[WP01] T. WERNER and T. PAJDLA, Cheirality in epipolar geometry. pages 548-553, July 2001.