Skip to main content
SpringerLink
Log in

Model-based 3D object detection

Efficient approach using superquadrics

  • Original Paper
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

Fast detection of objects in a home or office environment is relevant for robotic service and assistance applications. In this work we present the automatic localization of a wide variety of differently shaped objects scanned with a laser range sensor from one view in a cluttered setting. The daily-life objects are modeled using approximated Superquadrics, which can be obtained from showing the object or another modeling process. Detection is based on a hierarchical RANSAC search to obtain fast detection results and the voting of sorted quality-of-fit criteria. The probabilistic search starts from low resolution and refines hypotheses at increasingly higher resolution levels. Criteria for object shape and the relationship of object parts together with a ranking procedure and a ranked voting process result in a combined ranking of hypothesis using a minimum number of parameters. The experimental evaluation of the method and experiments from cluttered table top scenes demonstrate the effectiveness and robustness of the approach, feasible for real world object localization and robot grasp planning.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Bertero M., Poggio T., Torre V.: Ill-posed problems in early vision. Proc. IEEE 76(8), 869–889 (1988)

    Article  Google Scholar 

  2. Ferrari, V., Tuytelaars, T., van Gool, L.: Simultaneous object recognition and segmentation by image exploration. In: Proceedings of the European Conference on Computer Vision, pp. 40–54 (2004)

  3. Kragic D., Bjorkman M., Christensen H., Eklundh J.O.: Vision for robotic object manipulation in domestic settings. Rob. Auton. Syst. 52(1), 85–100 (2005)

    Article  Google Scholar 

  4. Lowe D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)

    Article  Google Scholar 

  5. Katsoulas, D.: Reliable recovery of piled box-like objects via parabolically deformable superquadrics. In: Proceedings of the IEEE 9th International Conference on Computer Vision, vol. 2, pp. 931–938 (2003)

  6. Shipley, T., Kellman, P.: Advances in Psychology: Form Fragments to Objects, vol. 130. Elsevier Science B.V., Amsterdam, ISBN: 0-444-50506-7 (2001)

  7. Hoffman D., Richards W.: Parts of recognition. Cognition 18, 65–96 (1984)

    Article  Google Scholar 

  8. Feddema, J., Little, C.: Rapid world modeling: Fitting range data to geometric primitives. In: Proceedings of the IEEE International Conference on Robotics and Automation, vol. 4, pp. 2807–2812 (1997)

  9. Lukacs, G., Martin, R., Marshall, D.: Faithful least-squares fitting of spheres, cylinders, cones and tori for reliable segmentation. In: Proceedings of the European Conference on Computer Vision, vol. 1, pp. 671–686 (1998)

  10. Marshall D., Lukacs G., Martin R.: Robust segmentation of primitives from range data in the presence of geometric degeneracy. IEEE Trans. Pattern Anal. Mach. Intell. 23(3), 304–314 (2001)

    Article  Google Scholar 

  11. Taylor, G., Kleeman, L.: Robust range data segmentation using geometric primitives for robotic applications. In: Proceedings of the 9th International Conference on Signal and Image Processing, pp. 467–472 (2003)

  12. Binford, T.: Visual perception by a computer. In: Proceedings of the IEEE Conference on Systems and Control, pp. 116–123 (1971)

  13. Barr A.: Superqadrics and angle preserving transformations. IEEE Comput. Graph. Appl. 1(1), 11–23 (1981)

    Article  Google Scholar 

  14. Hanson A.: Smoothly deformable shapes with convex polyhedral bounds. Comput. Vis. Graph. Image Process. 44, 191–210 (1988)

    Article  Google Scholar 

  15. Biederman I.: Recognition-by-components: a theory of human image understanding. Psychol. Rev. 94(2), 115–147 (1987)

    Article  Google Scholar 

  16. Keren D., Cooper D., Subrahmonia J.: Describing complicated objects by implicit polynomials. IEEE Trans. Pattern Anal. Mach. Intell. 16(1), 38–53 (1994)

    Article  Google Scholar 

  17. Staib L., Duncan J.: Model based deformable surface finding for medical images. IEEE Trans. Med. Imaging 15(5), 720–731 (1996)

    Article  Google Scholar 

  18. Solina F., Bajcsy R.: Recovery of parametric models from range images: the case for superquadrics with global deformations. IEEE Trans. Pattern Anal. Mach. Intell. 12(12), 131–147 (1990)

    Article  Google Scholar 

  19. Chevalier, L., Jaillet, F., Baskurt, A.: Segmentation and superquadric modeling of 3D objects. J. WSCG; ISSN 1213–6972, 11(1) (2002)

    Google Scholar 

  20. Ferrie, F., Lagarde, J., Whaite, P.: Recovery of volumetric object descriptions from laser rangefinder images. In: Proceedings of the European Conference on Computer Vision, pp. 387–396 (1990)

  21. Lee, S., Hong, H., Choi, J.: Assembly part recognition using part-based superquadric model. In: Proceedings of the IEEE TENCON, vol. 4, pp. 479–482 (1999)

  22. Salganicoff M., Lyle L., Bajcsy R.: Active learning for vision-based robot grasping. Mach. Learn. 23(2), 251–278 (1996)

    Google Scholar 

  23. Taylor, G., Kleeman, L.: Integration of robust visual perception and control for a domestic humanoid robot. In: Proceedings of the IEEE International Conference on Intelligent Robots and Systems, vol. 1, pp. 1010–1015 (2004)

  24. Bolles R., Horaud P.: 3dpo: a three-dimensional part orientation system. Int. J. Rob. Res. 5(3), 3–26 (1986)

    Article  Google Scholar 

  25. Dickinson S.J., Metaxas D., Pentland A.: The role of model-based segmentation in the recovery of volumetric parts from range data. IEEE Trans. Pattern Anal. Mach. Intell. 19(3), 259–267 (1997)

    Article  Google Scholar 

  26. Leonardis A., Jaklic A.: Superquadrics for segmenting and modeling range data. IEEE Trans. Pattern Anal. Mach. Intell. 19(11), 1289–1295 (1997)

    Article  Google Scholar 

  27. Krivic J., Solina F.: Part-level object recognition using superquadrics. Comput. Vis. Image Underst. 95(1), 105–126 (2004)

    Article  Google Scholar 

  28. Tao, L., Castellani, U., Murino, V.: Robust 3d segmentation for underwater acoustic images. In: Proceedings of the 2nd International Symposium on 3D Data Processing, Visualization & Transmission, pp. 813–819 (2004)

  29. Johnson A., Hebert M.: Using spin images for efficient multiple model recognition in cluttered 3-D scenes. IEEE Trans. Pattern Anal. Mach. Intell. 21(5), 433–449 (1999)

    Article  Google Scholar 

  30. Mian, A., Bennamoun, M., Owens, R.: Three-dimensional model-based object recognition and segmentation in cluttered scenes. IEEE Trans. PAMI 28(10) (2006)

  31. Hoover A., Jean-Babtiste G., Jiang X., Flynn P., Bunke H., Goldgof D., Eggert D., Fitzgibbon A., Fisher R.: An experimental comparison of range image segmentation algorithms. IEEE Trans. Pattern Anal. Mach. Intell. 18(7), 1–17 (1996)

    Article  Google Scholar 

  32. Cantoni, V., Lombardi, L.: Hierarchical architectures for computer vision. In: Proceedings of the IEEE Euromicro Workshop on Parallel and Distributed Processing, pp. 392–398 (1995)

  33. Parhami B.: Voting algorithms. IEEE Trans. Reliab. 43(4), 617–629 (1994)

    Article  Google Scholar 

  34. Moré J.: The Levenberg–Marquardt algorithm: Implementation and theory. Numerical Analysis, Lecture Notes in Mathematics, pp. 105–116. Springer, Heidelberg (1995)

    Google Scholar 

  35. Jaklic, A., Leonardis, A., Solina, F.: Segmentation and Recovery of Superquadrics. Kluwer, Dordrecht, ISBN: 0-7923-6601-8 (2000)

  36. Barr A.: Global and local deformations of solid primitives. IEEE Comput. Graph. Appl. 18(3), 21–30 (1984)

    Google Scholar 

  37. Fischler M., Bolles R.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 26(6), 381–395 (1981)

    Article  MathSciNet  Google Scholar 

  38. Oja E., Xu L., Suen C.: Modified hebian learning for curve and surface fitting. Neural Netw. 5(3), 441–457 (1992)

    Article  Google Scholar 

  39. Press, W., Flannery, B., Teukolsky, S., Vetterling, W.: Numerical Recipes in C: The Art of Scientific Computing. Cambridge University Press, Cambridge, ISBN: 0-521-35465-X (1988)

  40. Gupta, A., Bogoni, L., Bajcsy, R.: Quantitative and qualitative measures for the evaluation of the superquadric models. In: Proceedings of the IEEE Workshop on Interpretation of 3D Scenes, vol. 12, pp. 162–196 (1989)

  41. Biegelbauer, G.: Efficient part feature and object detection by fitting geometric models to range image data. Ph.D. thesis, Vienna University of Technology (2006)

  42. Katsoulas, D., Bastidas, C., Kosmopoulos, D.: Superquadric segmentation in range images via fusion of region and boundary information. Trans. Pattern Anal. Mach. Intell. 30(5) (2008)

  43. Pichler, A., Fisher, R., Vincze, M.: Decomposition of range images using markov random fields. In: Proceedings of the IEEE International Conference on Image Processing, vol. 2, pp. 24–27 (2004)

Download references

Author information

Authors and Affiliations

  1. Automation and Control Institute, Vienna University of Technology, Gusshausstrasse 27-29, E376, 1040, Vienna, Austria

    Georg Biegelbauer, Markus Vincze & Walter Wohlkinger

Authors
  1. Georg Biegelbauer
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Markus Vincze
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Walter Wohlkinger
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Markus Vincze.

Additional information

This work was supported by the Austrian Science Foundation Grant S09101-N04.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Biegelbauer, G., Vincze, M. & Wohlkinger, W. Model-based 3D object detection. Machine Vision and Applications 21, 497–516 (2010). https://doi.org/10.1007/s00138-008-0178-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00138-008-0178-3

Keywords

Search

Navigation