Efficient Pose Estimation Using View-Based Object Representations
We present an efficient method for estimating the pose of a three-dimensional object. Its implementation is embedded in a computer vision system which is motivated by and based on cognitive principles concerning the visual perception of three-dimensional objects. Viewpoint-invariant object recognition has been subject to controversial discussions for a long time. An important point of discussion is the nature of internal object representations. Behavioral studies with primates, which are summarized in this article, support the model of view-based object representations. We designed our computer vision system according to these findings and demonstrate that very precise estimations of the poses of real-world objects are possible even if only a few number of sample views of an object is available. The system can be used for a variety of applications.
Unable to display preview. Download preview PDF.
- 2.M. J. Tarr. Orientation Dependence in Three-Dimensional Object Recognition. Ph.D. Thesis, MIT, 1989.Google Scholar
- 8.J. P. Jones and L. A. Palmer. An evaluation of the two-dimensional gabor filter model of simple receptive fields in cat striate cortex. Journal of Neurophysiology, 58(6):1233–1258, 1987.Google Scholar
- 9.C. Eckes and J. C. Vorbrüggen. Combining Data-Driven and Model-Based Cues for Segmentation of Video Sequences. In Proc. WCNN96, pages 868–875, 1996.Google Scholar
- 10.T. Maurer and C. von der Malsburg. Tracking and Learning Graphs and Pose on Image Sequences of Faces. In Proc. Int. Conf. on Automatic Face-and Gesture-Recognition, pages 176–181, 1996.Google Scholar
- 14.R. M. Haralick, C. Lee, K. Ottenberg, and M. Nölle. Analysis and Solutions of the Three Point Perspective Pose Estimation Problem. In Proc. of the IEEE Comp. Society Conf. on Computer Vision and Pattern Recognition, pages 592–598, 1991.Google Scholar
- 17.M. Pötzsch. Die Behandlung der Wavelet-Transformation von Bildern in der Nähe von Objektkanten. Technical Report IRINI 94-04, Institut für Neuroinformatik, Ruhr-Universität Bochum, Germany, 1994.Google Scholar
- 19.G. Peters and C. von der Malsburg. View Reconstruction by Linear Combination of Sample Views. In Proc. BMVC 2001, pages 223–232, 2001.Google Scholar
- 21.G. Peters. A View-Based Approach to Three-Dimensional Object Perception. Ph.D. Thesis, Shaker Verlag, Aachen, Germany, 2002.Google Scholar