An Affine SIFT Matching Algorithm Based on Local Patch Shape Estimation

Abstract:

In this paper we present an affine SIFT matching method to achieve reliable correspondence points in stereo matching with large viewpoint changes. We extended the affine invariant of the conventional SIFT approach by estimating the shape of the local patch around the interest point. Since we can obtain the scale information by SIFT detector, a second moment matrix (SMM) descriptor was employed to describe the shape. Furthermore, by comparing the shapes of the potential matches, we can normalize the template of SIFT descriptor and obtain the initial affine transformation. At last, we applied the iterative based method to achieve a fine registration with the estimated initial transformation parameters. The experiment results show that the proposed method is more robust to viewpoint changes and the accuracy of registration is better than feature based methods.

• Periodical: Applied Mechanics and Materials (Volumes 519-520)
• Pages: 553-556
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.519-520.553
• Online since: February 2014
• Authors: Zun Shang Zhu*, Yue Qiang Zhang, Xiang Zhou, Yang Shang
• Keywords: Affine Invariant, Affine SIFT, Second Moment Matrix

References

[1] David G. Lowe. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60: 91–110, (2004).

DOI: 10.1023/b:visi.0000029664.99615.94

[2] Harris C. and Stephens M. A combined corner and edge detector. 147–151. In Proc. 4th Alvey Vision, (1998).

[3] A. Baumberg. Reliable feature matching across widely separated views. In Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on, volume 1, pages 774 –781 vol. 1, (2000).

DOI: 10.1109/cvpr.2000.855899

[4] Lindeberg, T. Feature detection with automatic scale selection. International Journal of Computer Vision, 30(2): 79–116.

[5] Krystian Mikolajczyk and Cordelia Schmid. An affine invariant interest point detector. 2350: 128–142, (2002).

[6] K. Mikolajczyk and C. Schmid. A performance evaluation of local descriptors. 2(1): 257–263 , (2003).

[7] K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir, and L. Gool. A comparison of affine region detectors. International Journal of Computer Vision, 65: 43–72, (2005).

DOI: 10.1007/s11263-005-3848-x

[8] Guoshen Yu and Jean-Michel Morel. Asift, a new framework for fully affine invariant image comparison. SIAM Journal on Imaging Sciences, 2(2): 438-469, (2009).

DOI: 10.1137/080732730

[9] Wei Liu, Yongtian Wang, Jing Chen, Junwei Guo, and Yang Lu. A completely affine invariant image-matching method based on perspective projection. Machine Vision and Applications, 23: 231–242, (2012).

DOI: 10.1007/s00138-011-0347-7

[10] F. Ackermann. Digital image correlation: Performance and potential application in photogrammetry. The Photogrammetric Record, 11(64): 429–439, (1984).

DOI: 10.1111/j.1477-9730.1984.tb00505.x