Stereo Image Matching Based on SURF Descriptor

Abstract:

In order to improve the robustness performance of SURF descriptor applied to stereo image matching, a new matching method is proposed. By using the ratio of minimum to second min Euclidean distance of corresponding features, we can get the coarse matching points aggregation. Then, the epipolar line is computed from calibration parameters. Correspondences are taken as correct correspondences, only if they fall into a small neighborhood of their epipolar line. Taken errors into account, the neighborhood is set (-3, 3). Using this restriction, we can get the correct matching points aggregation. The experimental results show that the correct matches and matching efficiency are better than RANSAC.

• Periodical: Advanced Materials Research (Volume 1083)
• Pages: 142-147
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1083.142
• Online since: January 2015
• Authors: Luan Zeng*, You Zhai
• Keywords: Image Matching, SURF Descriptor, Vision Measurement

References

[1] Herbert Bay, Andreas Ess, Tinne Tuytelaars, et al., Speeded up robust features, Computer Vision and Image Understanding (CVIU), Papers 110(3), 346-359(2008).

DOI: 10.1016/j.cviu.2007.09.014

[2] H. Bay, T. Tuytelaars, and L. J. V. Gool. Surf: Speeded up robust features[C]. In A. Leonardis, H. Bischof, and A. Pinz, editors, ECCV (1), volume 3951 of Lecture Notes in Computer Science, pages 404–417. Springer, (2006).

DOI: 10.1007/11744023_32

[3] Zeng Luan, Zhai You, Xiong Wei. Improved SURF descriptor based on triangle partition[J]. Advanced Materials Research, Papers 718-720: 2296-2301 (2013).

DOI: 10.4028/www.scientific.net/amr.718-720.2296

[4] Zeng Luan, Zhai You, Fang, Xiu-Hua. An improved SURF descriptor based on sector area partitioning[C]. Sixth International Symposium on Precision Mechanical Measurements, Proc SPIE 8916: 89163K(2013).

DOI: 10.1117/12.2035753

[5] Zeng Luan, Wang Yuanqin, Tan Jiubin, Improved algorithm for SIFT feature extraction and matching, Optics and Precision Engineering, Papers 19(6): 1391-1397( 2011).

DOI: 10.3788/ope.20111906.1391

[6] F. Zhou, Y. Wang, Y. Cui, H. Tan. Camera calibration approach using circle-square-combined target. CHINESE OPTICS LETTERS, 2012. 10(2): 1-4.

DOI: 10.3788/col201210.021003

[7] B. Hui, G. Wen, X. Zhang, R. Li. Accurate geometric camera calibration technique using multi-views of a non-metric planar grid[J]. Optics and Lasers in Engineering, 2013, 51: 432–439.

DOI: 10.1016/j.optlaseng.2012.11.008

[8] C. Zhuang, Z. Li, D. Gu. Arithmetic for camera calibration based on epipolar geometry and active vision[J]. Journal of Beijing university of technology, 2009, 35(9): 1175-1180.

[9] LIU Chao, Gao Jing-xiang, YANG Hua-chao. Research on camera calibration algorithm using planar control grid[J]. Science of Surveying and Mapping, 2009, 34(4): 50-52.