Affine Category Shape Model을 이용한 형태 기반 범주 물체 인식 기법
A New Shape-Based Object Category Recognition Technique using Affine Category Shape Model
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
This paper presents a new shape-based algorithm using affine category shape model for object category recognition and model learning. Affine category shape model is a graph of interconnected nodes whose geometric interactions are modeled using pairwise potentials. In its learning phase, it can efficiently handle large pose variations of objects in training images by estimating 2-D homography transformation between the model and the training images. Since the pairwise potentials are defined on only relative geometric relationship between features, the proposed matching algorithm is translation and in-plane rotation invariant and robust to affine transformation. We apply spectral matching algorithm to find feature correspondences, which are then used as initial correspondences for RANSAC algorithm. The 2-D homography transformation and the inlier correspondences which are consistent with this estimate can be efficiently estimated through RANSAC, and new correspondences also can be detected by using the estimated 2-D homography transformation. Experimental results on object category database show that the proposed algorithm is robust to pose variation of objects and provides good recognition performance.
Abstract
This paper presents a new shape-based algorithm using affine category shape model for object category recognition and model learning. Affine category shape model is a graph of interconnected nodes whose geometric interactions are modeled using pairwise potentials. In its learning phase, it can efficiently handle large pose variations of objects in training images by estimating 2-D homography transformation between the model and the training images. Since the pairwise potentials are defined on only relative geometric relationship between features, the proposed matching algorithm is translation and in-plane rotation invariant and robust to affine transformation. We apply spectral matching algorithm to find feature correspondences, which are then used as initial correspondences for RANSAC algorithm. The 2-D homography transformation and the inlier correspondences which are consistent with this estimate can be efficiently estimated through RANSAC, and new correspondences also can be detected by using the estimated 2-D homography transformation. Experimental results on object category database show that the proposed algorithm is robust to pose variation of objects and provides good recognition performance.
참고문헌 (9)
- A. Kushal, "Flexible Object Models for Category-Level 3D Object Recognition", pp.1~8 (2007), In Proc. of IEEE Int’l Conference on Computer Vision and Pattern Recognition
- G. Kim, "Unsupervised Modeling of Object Categories using Link Analysis Techniques", pp.1~8 (2008), In Proc. of IEEE Int’l Conference on Computer Vision and Pattern Recognition
- H. Zhang, "SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition", pp.2126~2136 (2006), In Proc. of IEEE Int’l Conference on Computer Vision and Pattern Recognition
- O. Chum, "An Exemplar Model for Learning Object Classes", pp.1~8 (2007), in Proc. of IEEE Int’l Conference on Computer Vision and Pattern Recognition
- M. Leordeanu, "Beyond Local Appearance: Category Recognition from Pairwise Interactions of Simple Features", pp.1~8 (2007), In Proc. of IEEE Int’l Conference on Computer Vision and Pattern Recognition
- M. Leordeanu, "A Spectral Technique for Correspondence Problems Using Pairwise Constraints", in Proc. of IEEE Int’l Conference on Computer Vision, 2, pp.1482~1489 (2005)
- M. A. Fischler, "Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography", Comm. Assoc. Comp. Mach, 24(6), pp.381~395 (1981)
- R. Hartley, "Multiple View Geometry in Computer Vision, 2nd Ed" (2003), Cambridge University Press
- ROC Graphs: Notes and Practical Considerations for Data Mining Researchers, "T. Fawcett", HP Labs Tech. Report HPL-2003-4, ~ (2003)