Recognition, pose and tracking of modelled polyhedral objects by multi-ocular vision
We developped a fully automated algorithmic chain for the tracking of polyhedral objects with no manual intervention. It uses a multi-cameras calibrated system and the 3D model of the observed object.
The initial phase of the tracking is done according to an automatic location process using graph theoretical methods. The originality of the approach resides mainly in the fact that compound structures (triple junction and planar faces with four vertices) are used to construct the graphs describing scene and model. The association graph construction and the search of maximal cliques are greatly simplified in this way. The final solution is selected among the maximal cliques by a predictionverification scheme.
During the tracking process, it is noticeable that our model based approach does not use triangulation although the basis of the multi-ocular system is available. The knowledge of calibration parameters (extrinsic as well as intrinsic) of the cameras enables to express the various equations related to each images shot in one common reference system. The aim of this paper is to prove that model based methods are not bound to monocular schemes but can be used in various multi-ocular situations in which they can improve the overall robustness.
Keywords3D model multi-cameras graph theory prediction-verification localisation without triangulation tracking
Unable to display preview. Download preview PDF.
- [AN93]M. Anderson and P. Nordlund. A model based system for localization and tracking. In Workshop on Computer Vision for Space Applications, pages 251–260, September 1993.Google Scholar
- [Aya89]N. Ayache. Vision stéréoscopique et perception multisensorielle. InterEditions, Science Informatique, 1989.Google Scholar
- [Bar85]S.T. Barnard. Choosing a basis for perceptual space. Computer Vision Graphics and Image Processing, 29(1):87–99, 1985.Google Scholar
- [BDL96]P. Braud, M. Dhome, and J.-T. Lapresté. Reconnaissance d'objets polyédriques par vision multi-oculaire. In 10ème Congrès Reconnaissance des Formes et Intelligence Artificielle, Rennes, France, January 1996.Google Scholar
- [BDLD94]P. Braud, M. Dhome, J.T. Lapresté, and N. Daucher. Modelled object pose estimation and tracking by a multi-cameras system. In Int. Conf., on Computer Vision and Pattern Recognition, pages 976–979, Seattle, Washington, June 1994.Google Scholar
- [Bra96]P. Braud. Reconnaissance, localisation et suivi d'objets polyédriques modélisés par vision multi-oculaire. PhD thesis, Université Blaise Pascal de Clermont-Ferrand, France, January 1996.Google Scholar
- [CD86]R.T. Chin and C.R. Dyer. Model-based recognition in robot vision. ACM Computing Surveys, 18(1):67–108, March 1986.Google Scholar
- [DB93]R. Deriche and T. Blaszka. Recovering and characterizing image features using an efficient model based approach. In Int. Conf. on Computer Vision and Pattern Recognition, pages 530–535, New-York, June 1993.Google Scholar
- [DDLR93]N. Daucher, M. Dhome, J.T. Lapresté, and G. Rives. Modelled object pose estimation and tracking by monocular vision. In British Machine Vision Conference, volume 1, pages 249–258, October 1993.Google Scholar
- [DRLR89]M. Dhome, M. Richetin, J.T. Lapresté, and G. Rives. Determination of the attitude of 3d objets from a single perspective image. IEEE Trans. on Pattern Analysis and Machine Intelligence, 11(12):1265–1278, December 1989.Google Scholar
- [Fau93]O.D. Faugeras. Three Dimensional Computer Vision: A Geometric View-Point, chapter 12. MIT Press, Boston, 1993.Google Scholar
- [FB81]M.A. Fischler and R.C. Bolles. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Com. of the ACM, 24(6):381–395, June 1981.Google Scholar
- [Gen92]D.B. Gennery. Tracking of known three-dimensional objects. International Journal of Computer Vision, 7(3):243–270, April 1992.Google Scholar
- [Gri89]W.E.L. Grimson. On the recognition of parameterized 2d objects. International Journal of Computer Vision, 2(4):353–372, 1989.Google Scholar
- [HCLL89]R. Horaud, B. Conio, O. Leboulleux, and B. Lacoll. An analytic solution for the perspective 4 points problem. In Computer Vision Graphics and Image Processing, 1989.Google Scholar
- [Hor87]R. Horaud. New methods for matching 3-d objects with single perspective view. IEEE Trans. on Pattern Analysis and Machine Intelligence, 9(3):401–412, May 1987.Google Scholar
- [HS88]C.G. Harris and M. Stephens. A combined corner and edge detector. In Fourth Alvey Vision Conference, pages 189–192, Manchester, United Kingdom, August 1988.Google Scholar
- [HU90]D.P. Huttenlocher and S. Ullman. Recognizing solid objects by alignment with an image. International Journal of Computer Vision, 5(2): 195–212, 1990.Google Scholar
- [Kan81]T. Kanade. Recovery of the three dimensional shape of an object from a single view. Artificial Intelligence, Special Volume on Computer Vision, 17(1–3), August 1981.Google Scholar
- [Low85]D.G. Lowe. Perceptual Organization and Visual Recognition, chapter 7. Kluwer Academic Publishers, Boston, 1985.Google Scholar
- [Ols94]C.F. Olson. Time and space efficient pose clustering. In Int. Conf. on Computer Vision and Pattern Recognition, pages 251–258, Seattle, Washington, June 1994.Google Scholar
- [PPMF87]S.B. Pollard, J. Porrill, J. Mayhew, and J. Frisby. Matching geometrical descriptions in three space. Image and Vision Computing, 5(2):73–78, 1987.Google Scholar
- [RBPD81]P. Rives, P. Bouthemy, B. Prasada, and E. Dubois. Recovering the orientation and position of a rigid body in space from a single view. Technical report, INRS-Télécommunications, 3, place du commerce, Ile-des-soeurs, Verdun, H3E 1H6, Quebec, Canada, 1981.Google Scholar
- [Rei91]P. Reis. Vision Monoculaire pour la Navigation d'un Robot Mobile dans un Univers Partiellement Modélisé. PhD thesis, Université Blaise Pascal de Clermont-Ferrand, March 1991.Google Scholar
- [SK86]T. Shakunaga and H. Kaneko. Perspective angle transform and its application to 3-d configuration recovery. In Int. Conf. on Computer Vision and Pattern Recognition, pages 594–601, Miami Beach, Florida, June 1986.Google Scholar
- [Sko88]T. Skordas. Mise en correspondance et reconstruction stéréo utilisant une description structurelle des images. PhD thesis, Institut National Polytechnique de Grenoble, October 1988.Google Scholar
- [ZDFL94]Z. Zhang, R. Deriche, O. Faugeras, and Q.-T. Luong. A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry. Technical Report 2273, INRIA Sophia-Antipolis, France, May 1994.Google Scholar