Abstract
In this paper, we present an ANN hybrid ensemble scheme for simultaneous object recognition and pose estimation from 2D multiple-view image sequence, and realized human vision simulation within an intelligent machine. Based on the notion of similarity measure at various metrics, the paradox between information simplicity and accuracy is balanced by a model view generation procedure. An ANN hierarchical hybrid ensemble framework, much like a decision tree, is then set up, with multiple weights and radial basis function neural networks respectively employed for different tasks. The strategy adopted not only determines object identity by spatial geometrical cognition and omnidirectional accumulation through connectivity, but also assigns an initial pose estimation on a viewing sphere in a coarse to fine process. Simulation experiment has achieved encouraging results, proved the approach effective, superior and feasible in large-scale database and parallel computation.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
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
Besl, P., Jain, R.: Three-dimensional object recognition. Surveys 17(1), 75–145 (1985)
Pope, A., Lowe, D.: Learning object recognition models from images. In: ICCV 1993, pp. 296–301 (1993)
Bradski, G., Grossberg, S.: Fast-Learning VIEWNET Architectures for Recognizing Three-dimensional Objects from Multiple Two-dimensional Views. Neural Networks 8, 1053–1080 (1995)
Cyr, C.M., Kimia, B.B.: A Similarity-Based Aspect-Graph Approach to 3D Object Recognition. International Journal of Computer Vision 57(1) (2004)
Fauselt, L.: Fundamentals of Neural Networks. Prentice-Hall, International Inc., Englewood Cliffs (1994)
Huang, D.S.: Systematic Theory of Neural Networks for Pattern Recognition, pp. 70–78. Publishing House of Electronic Industry of China, Beijing (1996)
Wunsch, P., Winkler, S., Hirzinger, G.: Real-time pose estimation of 3-D objects from camera images using neural networks. In: Proc. IEEE International Conference on Robotics and Automation, vol. 4, pp. 3232–3237 (1997)
Yuan, C., Niemann, H.: Neural networks for the recognition and pose estimation of 3D objects from a single 2D perspective view. Image and Vision Computing 19(9-10), 585–592 (2001)
Wang, S.J.: Biomimetics pattern recognition. INNS, ENNS, JNNS Newletters Elseviers (2003)
Liu, Z., Kersten, D.: 2D observers for human 3D object recognition? In: Jordan, M.I., Kearns, M.J., Solla, S.A. (eds.) Advances in Neural Information Processing Systems, vol. 10 (1997)
Basri, R., Weinshall, D.: Distance Metric between 3D Models and 2D Images for Recognition and Classification. Mathematics & Computer Science (1994)
Klein, P., Sebastian, T., Kimia, B.: Shape matching using edit-distance: an implementation. In: Twelfth Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), pp. 781–790 (2001)
Xing, E.P., Ng, A.Y., Jordan, M.I., Russell, S.: Distance metric learning, with application to clustering with side information. In: Advances in Neural Information Processing Systems (2002)
Wang, S.J., Wang, B.N.: Analysis and theory of high-dimension spatial geometry for Artificial Neural Networks. Acta Electronica Sinica 30(1), 1–4 (2002)
Wang, S.J., Xu, J., Wang, X.B., Qin, H.: Multi-camera human-face personal identification system based on the biomimetics pattern recognition. Acta Electronica Sinica 31(1), 1–4 (2003)
Katsuhiko, T., Shogo, N.: Implementation and refinement of decision trees using neural networks for hybrid knowledge acquisition. Artificial Intelligence in Engineering 9(4), 265–276 (1995)
Wang, S.J., Li, Z.Z., Chen, X.D., Wang, B.N.: Discussion on the basic mathematical models of Neurons in General purpose Neurocomputer. Acta Electronica Sinica 29(5) (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nian, R., Ji, G., Zhao, W., Feng, C. (2005). ANN Hybrid Ensemble Learning Strategy in 3D Object Recognition and Pose Estimation Based on Similarity. In: Huang, DS., Zhang, XP., Huang, GB. (eds) Advances in Intelligent Computing. ICIC 2005. Lecture Notes in Computer Science, vol 3644. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11538059_68
Download citation
DOI: https://doi.org/10.1007/11538059_68
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28226-6
Online ISBN: 978-3-540-31902-3
eBook Packages: Computer ScienceComputer Science (R0)