Abstract
This article describes an architecture for the recognition of three-dimensional objects on the basis of viewer centred representations and temporal associations. Considering evidence from psychophysics, neurophysiology, as well as computer science we have decided to use a viewer centred approach for the representation of three-dimensional objects. Even though this concept quite naturally suggests utilizing the temporal order of the views for learning and recognition, this aspect is often neglected. Therefore we will pay special attention to the evaluation of the temporal information and embed it into the conceptual framework of biological findings and computational advantages. The proposed recognition system consists of four stages and includes different kinds of artificial neural networks: Preprocessing is done by a Gabor-based wavelet transform. A Dynamic Link Matching algorithm, extended by several modifications, forms the second stage. It implements recognition and learning of the view classes. The temporal order of the views is recorded by a STORE network which transforms the output for a presented sequence of views into an item- and-order coding. A subsequent Gaussian-ARTMAP architecture is used for the classification of the sequences and for their mapping onto object classes by means of supervised learning. The results achieved with this system show its capability to autonomously learn and to recognize considerably similar objects. Furthermore the given examples illustrate the benefits for object recognition stemming from the utilization of the temporal context. Ambiguous views become manageable and a higher degree of robustness against misclassifications can be accomplished.
Chapter PDF
References
Biederman, I. (1985): Human image understanding: Recent research and a theory. Comput. Vision Graphics Image Processing 32: 29–73.
Bradski, G.; Carpenter, G. and Grossberg, S. (1992): Working memory networks for learning temporal order with application to three-dimensional visual object recognition. Neural Comput. 4: 270–286.
Bradski, G. and Grossberg, S. (1993): Fast learning VIEWNET architectures for recognizing 3-D objects from multiple 2-D views. Technical Report CAS/CNS-TR-93-053, Boston Univ., Boston, MA.
Carpenter, G.; Grossberg, S.; Markuzon, N.; Reynolds, J. and Rosen, D. (1992): Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Trans. Neural Networks 3(5): 698–713.
Darrell, T. and Pentland, A. (1993): Recognition of space-time gestures using a distributed representation. In R. Mammone (ed.), Artificial neural networks for speech and vision. London: Chapman & Hall, pp. 502–519.
Edelman, S. and Weinshall, D. (1991): A self-organizing multiple-view representation of 3D objects. Biol. Cybern. 64: 209–219.
Grossberg, S. and Bradski, G. (1995): VIEWNET architectures for invariant 3-D object recognition from multiple views. In B. Bouchon-meunier; R. Yager and L. Zadeh (eds.), Fuzzy logic and soft computing. Singapore: World Scientific Publishing.
Koenderink, J. and van Doorn, A. (1979): The internal representation of solid shape with respect to vision. Biol. Cybern. 32: 211–216.
Konen, W.; Maurer, T. and von der Malsburg, C. (1994): A fast link matching algorithm for invariant pattern recognition. Neural Networks 7: 1019–1030.
Lowe, D. G. (1986): Perceptual organization and visual recognition. Boston: Kluwer.
Marr, D. and Nishihara, H. K. (1978): Representation and recognition of the spatial organization of three-dimensional shapes. Proc. R. Soc. Lond. 200: 269–294.
Matsakis, Y.; Berthoz, A.; Lipschits, M. and Gurfinkel, V. (1990): Mental rotation of three-dimensional shapes in microgravity. In Proc. Fourth European Symposium on Life Sciences in Space. ESA, pp. 625–629.
Metzler, J. and Shepard, R. (1974): Transformational studies of the internal representaion of three-dimensional objects. In R. Solso (ed.), Theories in cognitive psychology: The Loyola Symposium. Erlbaum.
Miyashita, Y. (1988): Neuronal correlate of visual associative long-term memory in the primate temporal cortex. Nature 335: 817–820.
Perrett, D.; Harries, M.; Benson, P.; Chitty, A. and Mistlin, A. (1990): Retrieval of structure from rigid and biological motion: An analysis of the visual responses of neurones in the Macaque temporal cortex. In A. Blake and T. Troscianko (eds.), AI and the Eye, chap. 8. Wiley & Sons, pp. 181–200.
Perrett, D.; Oram, M.; Harries, M.; Bevan, R.; Hietanen, J.; Benson, P. and Thomas, S. (1991): Viewer-centred and object-centred coding of heads in the macaque tempral cortex. Experimental Brain Research 86: 159–173.
Poggio, T. and Edelman, S. (1990): A network that learns to recognize three-dimensional objects. Nature 343: 263–266.
Sakai, K. and Miyashita, Y. (1991): Neural organization for the long-term memory of paired associates. Nature 354: 152–155.
Sarle, W. (1995): Why statisticians should not FART. ftp://ftp.sas.com/pub/ neural/fart.doc.
Seibert, M. and Waxman, A. (1992): Adaptive 3-D object recognition from multiple views. IEEE Trans. Pattern Anal. and Machine Intel. 14(2): 107–124.
Stryker, M. P. (1991): Temporal associations. Nature 354: 108–109.
Sumi, S. (1984): Upside-down presentation of the Johansson moving light-spot pattern. Perception 13: 283–286.
Tanaka, K. (1996): Inferotemporal cortex and object vision. Annu. Rev. Neurosci. 19: 109–139.
Thompson, D. W. and Mundy, J. L. (1987): Three dimensional model matching from an unconstrained viewpoint. In Proc. IEEE Int. Conf. Robotics and Automation. Raleigh, NC: IEEE, pp. 208–220.
Ullman, S. and Basri, R. (1991): Recognition by linear combinations of models. IEEE Trans. Pattern Anal. and Machine Intel. 13(10): 992–1006.
von der Malsburg, C. (1981): The correlation theory of brain function. Internal report, Max-Planck-Institut für Biophysikalische Chemie, Göttingen.
von der Malsburg, C. and Reiser, K. (1995): Pose invariant object recognition in a neural system. In Proc. Int. Conf. on Artificial Neural Networks ICANN. pp. 127–132.
Wallis, G. (in press): Temporal order in human object recognition learning. To appear in Journal of Biological Systems.
Williamson, J. (1996): Gaussian ARTMAP: A neural network for fast incremental learning of noisy multidimensional maps. Neural Networks 9(5): 881–897.
Wiskott, L. and von der Malsburg, C. (1996): Face recognition by Dynamic Link Matching. Internal Report IR-INI 96-05, Inst. f. Neuroinformatik, Ruhr-Univ. Bochum.
Würtz, R. (1994): Multilayer dynamic link networks for establishing image point correspondences and visual object recognition. Ph.D. thesis, Ruhr-Univ. Bochum.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Massad, A., Mertsching, B., Schmalz, S. (1998). Combining multiple views and temporal associations for 3-D object recognition. In: Burkhardt, H., Neumann, B. (eds) Computer Vision — ECCV’98. ECCV 1998. Lecture Notes in Computer Science, vol 1407. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0054774
Download citation
DOI: https://doi.org/10.1007/BFb0054774
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64613-6
Online ISBN: 978-3-540-69235-5
eBook Packages: Springer Book Archive