Structure Estimation of 3D Objects by Monocular Analysis Using Plücker Representation. Estimation des Positions D’objets 3D par Analyse Monoculaire en Représentation de Plücker

Structure Estimation of 3D Objects by Monocular Analysis Using Plücker Representation

Estimation des Positions D’objets 3D par Analyse Monoculaire en Représentation de Plücker

C Boucher J-C. Noyer  M. Benjelloun 

Laboratoire d’Analyse des Systèmes du Littoral (EA 2600), Université du Littoral Côte d’Opale 50, rue Ferdinand Buisson, B.P. 699, 62228 Calais Cedex, France

Page: 
113-128
|
Received: 
14 November 2000
|
Accepted: 
N/A
|
Published: 
30 April 2001
| Citation

OPEN ACCESS

Abstract: 

This article deals with a geometric method that estimates the 3D structure of an object from the knowledge of their motion and a monocular image sequence, taking into account the whole acquisition scheme. The estimation of the 3D positions is done via the properties of the Plücker modelization, whose benefit is to ensure an invariant geometric formulation of the 2D and 3D straight line. Besides, this method is well suited to deal with objects which can be described by a polygonal approximation.

Résumé

Cet article présente une méthode géométrique d’estimation de la structure d’objets 3D à partir de la connaissance de leur mouvement et d’une séquence d’images monoculaire, en tenant compte de l’ensemble de la chaîne de perception. L’estimation des positions 3D est ici rendue possible par l’exploitation des propriétés de la représentation de Plücker, dont l’avantage est de présenter une formulation géométrique invariante de la droite 2D et 3D. À noter que cette méthode est bien adaptée à la prise en compte de tout objet que l’on peut décrire par une approximation polygonale.

Keywords: 

Structure estimation from motion, 2D motion analysis, Plücker representation

Mots clés 

Estimation de la structure à partir du mouvement, analyse du mouvement 2D, représentation de Plücker

1. Introduction
2. Suivi des Segments 2D
3. Reconstruction 3D
4. Passage aux Données Rétiniennes
5. Résumé de la Méthode
6. Résultats
7. Conclusion
  References

[AM99] P.M.Q. Aguiar and J.M.F. Moura. A fast algorithm for rigid structure from image sequences. In International Conference on Image Processing, page 27AO2, 1999.

[AS00] S. Avidan and A. Shashua. Trajectory triangulation : 3D reconstruction of moving points from a monocular image sequence. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(4) : 348--357, April 2000. 

[Aya89] N. Ayache. Vision Stéréoscopique et Perception Multisensorielle. InterEditions, Paris, 1989. 

[BAS+87] C. Brown, J. Aloimonos, M. Swain, P. Choup, and A. Basu. Texture, contour, shape and motion. Pattern Recognition Letters, 5 : 151-169, 1987. 

[BG98] C. Ballester and M. Gonzalez. Affine invariant texture segmentation and shape from texture by variational methods. Journal of Mathematical Imaging and Vision, 9 (2) : 141-171, September 1998. 

[BNB99a] C. Boucher, J.-C. Noyer, and M. Benjelloun. 3D structure and motion estimation using range and intensity images. In Proceedings of the 33rd IEEE Asilomar Conference on Signals, Systems and Computers, pages 1431-1435, Pacific Grove, USA, October 1999. 

[BNB99b] C. Boucher, J.-C. Noyer, and M. Benjelloun. Estimation des positions d'objets 3D à partir d’une séquence d’images monoculaire. In Actes du 17ème Colloque GRETSI, pages 407-410, Vannes, FRANCE, September 1999. 

[BNB00] C. Boucher, J.-C. Noyer, and M. Benjelloun. 3D structure and motion recovery by fusing range and intensity image sequences. In Proceedings of the 3rd International Conference on Information Fusion, Paris, France, July 2000. 

[Bou00] C. Boucher. Contribution à la fusion d’informations par filtrage nonlinéaire : application à l’estimation de la structure du mouvement 3D dans un contexte multi-capteurs. PhD thesis, Université du Littoral Côte d’Opale, Octobre 2000. 

[BSC95] M. Benjelloun, A. Sdigui, and F. Chavand. Moving object tracking and reconstruction from {3D} straight lines using a mobile camera. In Motion Control, pages 745-752. LBM, October 1995.

[BSL93] Y. Bar-Shalom and X.-R. Li. Estimation and tracking: principles, techniques and software. Artech House, 1993. 

[BSL95] Y. Bar-Shalom and X. R. Li. Multitarget multisensor tracking. YBS Publication, 1995. 

[BZM97] P.A. Beardsley, A.~Zisserman, and D.W. Murray. Sequential updating of projective and affine structure from motion. International Journal of Computer Vision, 23(3):235--259, 1997. 

[Csu96] G. Csurka. Modélisation projective des objets tridimensionnels en vision par ordinateur. PhD thesis, Université de Nice Sophia Antipolis, Avril 1996. 

[DA89] U.R. Dhond and J.K. Aggarwal. Structure from stereo: A review. IEEE Transactions on systems, man and cybernetics, 19(6):1489-1510, November 1989. 

[Der87] R. Deriche. Using Canny’s criteria to derive an optimal edge detector recursively implemented. The International Journal of Computer Vision, April 1987. 

[DF90] R. Deriche and O. Faugeras. Tracking line segments. Image and Vision Computing, 8(4) : 261-270, 1990. 

[DRLR89]M. Dhome, M. Richetin, J. T. Lapeste, and G. Rives. Determination of the attitude of {3D} objects from a single perspective view. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11 : 1265-1278, December 1989. 

[DZB92] S. Demey, A. Zisserman, and P.A. Beardsley. Affine and projective structure from motion. In British Machine Vision Conference, pages 4958, 1992. 

[ER87] B. Espiau and P. Rives. Estimation récursive de primitives 3D au moyen d’une caméra mobile. Technical Report 0652, INRIA, 1987. 

[FA97] C. Fermuller and Y. Aloimonos. On the geometry of visual correspondence. International Journal of Computer Vision, 21(3) : 223-247, February 1997. 

[Fau93] O. Faugeras. Three-Dimensionnal Computer Vision : A Geometric Viewpoint. MIT Press, 1993.

[FIH99] D. A. Forsyth, S. Ioffe, and J. Haddon. Bayesian structure from motion. In Proceedings of the IEEE International Conference on Computer Vision, pages 660-665, 1999. 

[Gar93] J. Garding. Direct estimation of shape from texture. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(11) : 1202-1208, November 1993. 

[Gir87] G. Giraudon. Chaînage efficace de contour. Technical Report 605, INRIA, Février 1987. 

[HM95] R. Horaud and O. Monga. Vision par ordinateur : outils fondamentaux. Hermès, Paris, 1995. 

[HN94] T. S. Huang and A. N. Netravali. Motion and structure from feature correspondences : A review. Proceedings of the IEEE, 82(2) : 252-268, February 1994. 

[HS87] B. K. P. Horn and B. G. Schunck. New methods for matching 3D objects with single prespective views. IEEE Transactions on Pattern Analysis and Machine Intelligence, 3 : 401-412, May 1987.

[JJ84] C. Jerian and R. C. Jain. Determining motion parameters for scenes with translation and rotation. PAMI, 6(4) : 523-530, July 1984. 

[KC89] K.I. Kanatani and T.C. Chou. Shape from texture: General principle. In IEEE Computer Vision and Pattern Recognition, pages 578-583, 1989. 

[Krü98] Stephan Krüger. Motion Analysis and Estimation Using Multiresolution Affine Models. PhD thesis, University of Bristol, July 1998. 

[LH88] Y. Liu and T. S. Huang. A linear algorithm for determining motion and structure from line correspondences. Computer Vision, Graphics, and Image Processing, 44(1)  :35-57, 1988. 

[LHP80] H. C. Longuet-Higgins and K. Prazdney. The interpretation of moving retinal image. Proc. Roy. Soc. London, 208:385-397, July 1980. 

[MDMC91]O. Monga, R. Deriche, G. Malandain, and J.-P. Cocquerez. Recursive filtering and edge tracking : Two primary tools for 3D edge detection. Image and Vision Computing, 9 : 203-214, 1991.

[OG99] J. Oliensis and Y. Genc. New algorithms for two-frame structure from motion. In Proceedings of the IEEE International Conference on Computer Vision, pages 737-744, 1999. 

[PTh97] POV-Team and C. J. Cason (http://www.povray.org). POV-Ray(tm) rendering engine for Windows, 1991-1997. Version 3.02. 

[Sdi93] A. Sdigui. Contribution à l’analyse de scènes dynamiques par approche monoculaire : Application au suivi temporel 2D et à la reconstruction 3D de segments. PhD thesis, Université d’Evry Val d’Essone, Octobre 1993. 

[Sha95] L. S. Shapiro. Affine Analysis of Image Sequences. Cambridge University Press, 1995. 

[TK95] C. J. Taylor and D. J. Kriegman. Structure and motion from line segments in multiple images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(11) : 1021-1032, November 1995. 

[VLF94] T. Viéville, Q.-T. Luong, and O. Faugeras. Motion of points and lines in the uncalibrated case. International Journal of Computer Vision, 1994. 

[Xie89] M. Xie. Contribution à la vision dynamique: reconstruction d’objets 3D polyédriques par une Caméra mobile. PhD thesis, Université de Rennes I, Juin 1989. 

[Zel96] C. Zeller. Calibration projective affine et euclidienne en vision par ordinateur et application à la perception tridimensionnelle. PhD thesis, Ecole Polytechnique, Février 1996. 

[Zha95] Z. Zhang.Estimating motion and structure from correspondences of line segments between two perspective images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(12) : 1129--1139, December 1995.