Modeling 3D Objects from Stereo Views and Recognizing Them in Photographs
Local appearance models in the neighborhood of salient image features, together with local and/or global geometric constraints, serve as the basis for several recent and effective approaches to 3D object recognition from photographs. However, these techniques typically either fail to explicitly account for the strong geometric constraints associated with multiple images of the same 3D object, or require a large set of training images with much overlap to construct relatively sparse object models. This paper proposes a simple new method for automatically constructing 3D object models consisting of dense assemblies of small surface patches and affine-invariant descriptions of the corresponding texture patterns from a few (7 to 12) stereo pairs. Similar constraints are used to effectively identify instances of these models in highly cluttered photographs taken from arbitrary and unknown viewpoints. Experiments with a dataset consisting of 80 test images of 9 objects, including comparisons with a number of baseline algorithms, demonstrate the promise of the proposed approach.
KeywordsTest Image Training Image Interest Point Partial Model Equal Error Rate
Unable to display preview. Download preview PDF.
- 1.Tuytelaars, T., Van Gool, L.J.: Content-based image retrieval based on local affinely invariant regions. In: Visual Information and Information Systems, pp. 493–500 (1999)Google Scholar
- 2.Lowe, D.G.: Local feature view clustering for 3d object recognition. In: Conference on Computer Vision and Pattern Recognition (2001)Google Scholar
- 4.Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: British Machine Vision Conference, vol. I, pp. 384–393 (2002)Google Scholar
- 5.Lowe, D.G.: Object recognition from local scale-invariant features. In: International Conference on Computer Vision, Corfu, Greece, pp. 1150–1157 (1999)Google Scholar
- 7.Ferrari, V., Tuytelaars, T., Gool, L.V.: Integrating multiple model views for object recognition. In: Conference on Computer Vision and Pattern Recognition (2004)Google Scholar
- 8.Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3d object modeling and recognition using affine-invariant patches and multi-view spatial constraints. In: Conference on Computer Vision and Pattern Recognition, vol. II, pp. 272–277 (2003)Google Scholar
- 9.Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3d object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints. International Journal of Computer Vision (in press, 2005)Google Scholar
- 10.Rothganger, F.: 3D object modeling and recognition in photographs and video. PhD thesis, University of Illinois, Urbana Champaign (2004)Google Scholar
- 11.Benjemaa, R., Schmitt, F.: A solution for the registration of multiple 3D point sets using unit quaternions. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 34–50. Springer, Heidelberg (1998)Google Scholar