Identification of Highly Similar 3D Objects Using Model Saliency
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.
KeywordsPoint Cloud Salient Region Range Sensor Model Saliency Iterate Close Point Algorithm
Unable to display preview. Download preview PDF.
- 2.Besl, P., McKay, N.: A method for registration of 3d shapes. PAMI 18, 540–547 (1992)Google Scholar
- 3.Chen, Y., Medioni, G.: Object modeling by registration of multiple range images. In: IVC, pp. 145–155 (1992)Google Scholar
- 7.Ferencz, A., Learned-Miller, E.G., Malik, J.: Learning hyper-features for visual identification. In: NIPS (2004)Google Scholar
- 9.Gelfand, N., Ikemoto, L., Rusinkiewicz, S., Levoy, M.: Geometrically stable sampling for the ICP algorithm. In: 3DIM 2003 (2003)Google Scholar
- 11.Hoppe, H., DeRose, T., Duchamp, T., McDonald, J., Stuetzle, W.: Surface reconstruction from unorganized points. In: ACM SIGGRAPH, pp. 71–78 (1992)Google Scholar
- 12.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)Google Scholar
- 14.Kadir, T., Zisermann, A.: Scale, saliency and image description. Commun. Assoc. Comp. Mach. 24, 381–395 (1981)Google Scholar
- 15.Lee, C.H., Varshney, A., Jacobs, D.W.: Mesh saliency. In: ACM SIGGRAPH, pp. 659–666 (2005)Google Scholar
- 17.Rusinkiewicz, S., Levoy, M.: Efficient variants of the icp algorithm. In: Third International Conference on 3D Digital Imaging and Modeling (3DIM 2001) (2001)Google Scholar
- 18.Wasserman, L.: All of statistics. A concise course in statistical inferrence. Springer, Heidelberg (2003)Google Scholar