Abstract
This paper describes a method for model-based 3D object localization. The object model consists of a triangular surface mesh, model points, and model geometrical features. Model points and model geometrical features are generated using contour generators, which are estimated by the occluding contours of projected images of the triangular surface mesh from multiple viewing directions, and they are maintained depending on the viewing direction. Multiple hypotheses for approximate model position and orientation are generated by comparing model geometrical features and data geometrical features. The multiple hypotheses are limited by using the viewing directions that are used to generate model geometrical features. Each hypothesis is verified and improved by using model points and 3D boundaries, which are reconstructed by segment-based stereo vision. In addition, each hypothesis is improved by using the triangular surface mesh and 3D boundaries. Experimental results show the effectiveness of the proposed method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Johnson, A.E., Hebert, M.: Using spin images for efficient object recognition in cluttered 3D scenes. IEEE Trans. on PAMI 21(5), 433–449 (1999)
Li, G., Tsin, Y., Genc, Y.: Exploiting occluding contours for real-time 3D tracking: A unified approach. In: Proc. ICCV 2007 (2007)
Drummond, T., Cipolla, R.: Real-time visual tracking of complex structures. IEEE Trans. on PAMI 24(7), 932–946 (2002)
Kotake, D., Satoh, K., Uchiyama, S., Yamamoto, H.: A fast initialization method for edge-based registration using an inclination constraint. In: Proc. ISMAR 2007, pp. 239–248 (2007)
Sethi, A., Renaudie, D., Kriegman, D., Ponce, J.: Curve and surface duals and the recognition of curved 3D objects from their silhouettes. Int. J. of Computer Vision 58(1), 73–86 (2004)
Sumi, Y., Kawai, Y., Yoshimi, T., Tomita, F.: 3D object recognition in cluttered environments by segment-based stereo vision. Int. J. of Computer Vision 46(1), 5–23 (2002)
Sumi, Y., Ishiyama, Y., Tomita, F.: 3D localization of moving free-form objects in cluttered environments. In: Proc. ACCV 2004, vol. I, pp. 43–48 (2004)
Maruyama, K., Kawai, Y., Tomita, T.Y. F.: 3D object localization based on occluding contour using STL CAD model. In: Proc. 19th ICPR, TuBCT8.41 (2008)
Besl, P.J., McKay, N.D.: A method for registration of 3-D shapes. IEEE Trans. on PAMI 14(2), 239–256 (1992)
Chen, Y., Medioni, G.: Object modeling by registration of multiple range image. Image and Vision Computing 10(3), 145–155 (1992)
Vaillant, R., Faugeras, O.D.: Using external boundaries for 3-D object modeling. IEEE Trans. on PAMI 14(2), 157–173 (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Maruyama, K., Kawai, Y., Tomita, F. (2010). Model-Based 3D Object Localization Using Occluding Contours. In: Zha, H., Taniguchi, Ri., Maybank, S. (eds) Computer Vision – ACCV 2009. ACCV 2009. Lecture Notes in Computer Science, vol 5996. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12297-2_39
Download citation
DOI: https://doi.org/10.1007/978-3-642-12297-2_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12296-5
Online ISBN: 978-3-642-12297-2
eBook Packages: Computer ScienceComputer Science (R0)