Abstract
We present a novel approach for identifying 3D objects from a database of models, highly similar in shape, using range data acquired in unconstrained settings from a limited number of viewing directions. We are addressing also the challenging case of identifying targets not present in the database. The method is based on learning offline saliency tests for each object in the database, by maximizing an objective measure of discriminability with respect to other similar models. Our notion of model saliency differs from traditionally used structural saliency that characterizes weakly the uniqueness of a region by the amount of 3D texture available, by directly linking discriminability with the Bhattacharyya distance between the distribution of errors between the target and its corresponding ground truth, respectively other similar models. Our approach was evaluated on thousands of queries obtained by different sensors and acquired in various operating conditions and using a database of hundreds of models. The results presented show a significant improvement in the recognition performance when using saliency compared to global point-to-point mismatch errors, traditionally used in matching and verification algorithms.
Chapter PDF
Similar content being viewed by others
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.
References
Arun, K., Huang, T., Blostein, S.: Least-squares fitting of two 3D point sets. PAMI 9, 698–700 (1987)
Besl, P., McKay, N.: A method for registration of 3d shapes. PAMI 18, 540–547 (1992)
Chen, Y., Medioni, G.: Object modeling by registration of multiple range images. In: IVC, pp. 145–155 (1992)
Comaniciu, D., Visvanath, R., Meer, P.: Kernel-based object tracking. PAMI 25(5), 564–577 (2003)
Domeniconi, C., Peng, J., Gunopulos, D.: Ocally adaptive metric nearest neighbor classification. PAMI 24(9), 1281–1285 (2002)
Efron, B., Tibshirani, R.: An Introduction to the Bootstrap. Chapman & Hall, New York (1993)
Ferencz, A., Learned-Miller, E.G., Malik, J.: Learning hyper-features for visual identification. In: NIPS (2004)
Fukunaga, K.: Introduction to Statistical Pattern Recognition, 2nd edn. Academic Press, London (1990)
Gelfand, N., Ikemoto, L., Rusinkiewicz, S., Levoy, M.: Geometrically stable sampling for the ICP algorithm. In: 3DIM 2003 (2003)
Hastie, T., Tibshirani, R., Friedman, J.: The elements of statistical learning. Data mining inference and prediction. Springer, Heidelberg (2001)
Hoppe, H., DeRose, T., Duchamp, T., McDonald, J., Stuetzle, W.: Surface reconstruction from unorganized points. In: ACM SIGGRAPH, pp. 71–78 (1992)
Huber, D., Kapuria, A., Donamukkala, R., Hebert, M.: Part-based 3D object classification. In: CVPR, Washington, DC, June 2004, vol. 2, pp. 82–89 (2004)
Johnson, A., Hebert, M.: Surface matching for object recognition in complex three-dimensional scenes. IVC 16, 635–651 (1998)
Kadir, T., Zisermann, A.: Scale, saliency and image description. Commun. Assoc. Comp. Mach. 24, 381–395 (1981)
Lee, C.H., Varshney, A., Jacobs, D.W.: Mesh saliency. In: ACM SIGGRAPH, pp. 659–666 (2005)
Neisser, U.: Visual search. Scientific American 20(12), 94–102 (1964)
Rusinkiewicz, S., Levoy, M.: Efficient variants of the icp algorithm. In: Third International Conference on 3D Digital Imaging and Modeling (3DIM 2001) (2001)
Wasserman, L.: All of statistics. A concise course in statistical inferrence. Springer, Heidelberg (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Matei, B.C., Sawhney, H.S., Spence, C.D. (2006). Identification of Highly Similar 3D Objects Using Model Saliency. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3954. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11744085_37
Download citation
DOI: https://doi.org/10.1007/11744085_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-33838-3
Online ISBN: 978-3-540-33839-0
eBook Packages: Computer ScienceComputer Science (R0)