© The Institution of Engineering and Technology
In computer vision, it is a challenge to compute the relationship of multiple views from scene images. The view relationship can be obtained from the fundamental matrix. Thus, it is very important to compute an accurate fundamental matrix from unevenly distributed features in complex scene images. This study proposes a robust method to estimate the fundamental matrix from corresponding images. First, the authors introduce how to find matched features from scene images efficiently. The epipolar geometry can restrict the point correspondences to the polar line, but cannot cope with the false points lying on the line. To eliminate such mismatches, the authors present an affine constraint which can also merge the uniform regions produced by mean-shift segmentation. Second, inspired by the success of random sample consensus, the authors moderately improve the weighting function based on M-estimator to increase the accuracy of the fundamental matrix estimation. Experimental results on simulated data and real images show these works are efficient for estimating fundamental matrix. The authors also evaluated the accuracy of their method on computing the external parameters of two cameras. The result shows that this method obtains comparable performance to the more sophisticated calibration method.
References
-
-
1)
-
37. Vogel, C., Schindler, K., Roth, S.: ‘Piecewise rigid scene flow’. Proc. of the IEEE Int. Conf. on Computer Vision, Sydney, NSW, December 2013, pp. 1377–1384.
-
2)
-
46. Sumengen, B.: ‘Variational image segmentation and curve evolution on natural images’. PhD thesis, University of California, 2004.
-
3)
-
1. Carrera, G., Angeli, A., Davison, A.J.: ‘SLAM-based automatic extrinsic calibration of a multi-camera rig’. Proc. of the IEEE Int. Conf. on Robotics and Automation, Shanghai, China, May 2011, pp. 2652–2659.
-
4)
-
36. Bleyer, M., Rother, C., Kohli, P.: ‘Surface stereo with soft segmentation’. Proc. of the IEEE Int. Conf. on Computer Vision and Pattern Recognition, San Francisco, CA, June 2010, pp. 1570–1577.
-
5)
-
49. Sonka, M., Hlavac, V., Boyle, R.: ‘Image processing, analysis and machine vision’ (Thomson Press, 2002, 2nd edn.).
-
6)
-
8. Luong, Q.-T., Faugeras, O.D.: ‘The Fundamental matrix: theory, algorithms, and stability analysis’, Int. J. Comput. Vis., 1995, 17, (1), pp. 43–75 (doi: 10.1007/BF00127818).
-
7)
-
22. Kanatani, K., Sugaya, Y.: ‘High accuracy computation of rank-constrained fundamental matrix’. Proc. of the British Machine Vision Conf., Coventry, UK, 2007, pp. 282–291.
-
8)
-
17. Torr, P., Murray, D.: ‘The development and comparison of robust methods for estimating the fundamental matrix’, Int. J. Comput. Vis., 1997, 24, (3), pp. 271–300 (doi: 10.1023/A:1007927408552).
-
9)
-
10. Armangue, X., Salvi, J.: ‘Overall view regarding fundamental matrix estimation’, Image Vis. Comput., 2003, 21, (2), pp. 205–220 (doi: 10.1016/S0262-8856(02)00154-3).
-
10)
-
5. Comaniciu, D., Meer, P.: ‘Mean shift: a robust approach toward feature space analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 2002, 24, (5), pp. 603–619 (doi: 10.1109/34.1000236).
-
11)
-
45. Ren, X., Malik, J.: ‘Learning a classification model for segmentation’. Proc. of the IEEE Int. Conf. on Computer Vision, Nice, France, October 2003, pp. 10–17.
-
12)
-
11. Bugarin, F., Bartoli, A., Henrion, D., et al: ‘Rank-constrained fundamental matrix estimation by polynomial global optimization versus the eight-point algorithm’ (HAL:hal-00723015, 2012).
-
13)
-
30. Torr, P.: ‘Bayesian model estimation and selection for epipolar geometry and generic manifold fitting’, Int. J. Comput. Vis., 2002, 50, (1), pp. 35–61 (doi: 10.1023/A:1020224303087).
-
14)
-
13. Hartley, R.: ‘In defense of the eight-point algorithm’, IEEE Trans. Pattern Anal. Machine Intell., 1997, 19, (6), pp. 580–593 (doi: 10.1109/34.601246).
-
15)
-
7. Tola, E., Lepetit, V., Fua, P.: ‘An efficient dense descriptor applied to wide-baseline stereo’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, (5), pp. 815–830 (doi: 10.1109/TPAMI.2009.77).
-
16)
-
39. Harris, C., Stephens, M.: ‘A combined corner and edge detector’. Proc. of the Alvey Vision Conf., 1988, pp. 147–151.
-
17)
-
34. Bleyer, M., Rother, C., Kohli, P., et al: ‘Object stereo– joint stereo matching and object segmentation’. Proc. of the IEEE Int. Conf. on Computer Vision and Pattern Recognition, Providence, RI, June 2011, pp. 3081–3088.
-
18)
-
38. Zhang, Z.: ‘Flexible camera calibration by viewing a plane from unknown orientations’. Proc. of the IEEE Int. Conf. on Computer Vision, Kerkyra, Greece, September 1999, pp. 666–673.
-
19)
-
6. Bay, H., Ess, A., Tuytelaars, T., et al: ‘SURF: Speeded up robust features’, Comput. Vis. Image Underst., 2008, 110, (3), pp. 346–359 (doi: 10.1016/j.cviu.2007.09.014).
-
20)
-
27. Ghergherehchi, M., Kim, S.Y., Afarideh, H., et al: ‘RANdom sample consensus (RANSAC) algorithm for enhancing overlapped etched track counting’, IET Image Process., 2012, 9, (2), pp. 97–106 (doi: 10.1049/iet-ipr.2013.0885).
-
21)
-
20. Smith, S.M., Brady, J.M.: ‘SUSAN – a new approach to low level image processing’, Int. J. Comput. Vision, 1997, 23, (1), pp. 45–78 (doi: 10.1023/A:1007963824710).
-
22)
-
26. Huang, J., Lai, S., Cheng, C.: ‘Robust fundamental matrix estimation with accurate outlier detection’, J. Inf. Sci. Eng., 2007, 23, (4), pp. 1213–1225.
-
23)
-
20. Zhang, Z.: ‘On the optimization criteria used in two-view motion analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 1998, 20, (7), pp. 717–729 (doi: 10.1109/34.689302).
-
24)
-
23. Migita, T., Shakunaga, T.: ‘Evaluation of epipole estimation methods with/without rank-2 constraint across algebraic/geometric error functions’. Proc. of the IEEE Conf. Computer Vision and Pattern Recognition, Minneapolis, MN, June 2007, pp. 1–7.
-
25)
-
3. Warren, M., McKinnon, D., Upcroft, B.: ‘Online calibration of stereo rigs for long-term autonomy’. Proc. of the IEEE Int. Conf. on Robotics and Automation, Karlsruhe, Germany, May 2013, pp. 3692–3698.
-
26)
-
16. Steger, C.: ‘Estimating the fundamental matrix under pure translation and radial distortion’, ISPRS J. Photogramm. Remote Sens., 2012, 74, pp. 202–217 (doi: 10.1016/j.isprsjprs.2012.09.012).
-
27)
-
7. Wang, J., Wang, X., Liu, F., et al: ‘Modeling of binocular stereo vision for remote coordinate measurement and fast calibration’, Opt. Lasers Eng., 2014, 54, pp. 269–274 (doi: 10.1016/j.optlaseng.2013.07.021).
-
28)
-
12. Valgaerts, L., Bruhn, A., Mainberger, M.: ‘Dense versus sparse approaches for estimating the fundamental matrix’, Int. J. Comput. Vis., 2012, 96, (2), pp. 212–234 (doi: 10.1007/s11263-011-0466-7).
-
29)
-
2. Tang, A.W.K., Hung, Y.S.: ‘A self-calibration algorithm based on a unified framework for constraints on multiple views’, J. Math Imaging Vis., 2012, 44, (3), pp. 432–448 (doi: 10.1007/s10851-012-0336-0).
-
30)
-
25. Faugeras, O., Luong, Q.: ‘The geometry of multiple images’ (MIT Press, 2001).
-
31)
-
35. Lhuillier, M., Quan, L.: ‘A Quasi-dense Approach to surface reconstruction from uncalibrated images’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (3), pp. 418–433 (doi: 10.1109/TPAMI.2005.44).
-
32)
-
15. Chojnacki, W., Brooks, M., Hengel, A.: ‘Revisiting hartley's normalized eight-point algorithm’, IEEE Trans. Pattern Anal. Machine Intell., 2003, 25, (9), pp. 1172–1177 (doi: 10.1109/TPAMI.2003.1227992).
-
33)
-
6. Chen, Z., Liao, H., Zhang, X.: ‘Telecentric stereo micro-vision system: calibration method and experiments’, Opt. Lasers Eng., 2014, 57, pp. 82–92 (doi: 10.1016/j.optlaseng.2014.01.021).
-
34)
-
47. Golub, G., Reinsch, C.: ‘Singular value decomposition and least squares solutions’, Numerische Mathematik, 1970, 14, (5), pp. 403–420 (doi: 10.1007/BF02163027).
-
35)
-
29. Torr, P., Zisserman, A.: ‘MLESAC: a new robust estimator with application to estimating image geometry’, Comput. Vis. Image Und., 2000, 78, (1), pp. 138–156 (doi: 10.1006/cviu.1999.0832).
-
36)
-
5. Hartley, R.I., Zisserman, A.: ‘Multiple view geometry in computer vision’ (Cambridge University Press, 2004, 2nd edn.).
-
37)
-
48. Zheng, Y., Sugimoto, S., Okutomi, M.: ‘A branch and contract algorithm for globally optimal fundamental matrix estimation’. Proc. of the IEEE Conf. Computer Vision and Pattern Recognition, Providence, RI, June 2011, pp. 2953–2960.
-
38)
-
19. Kanatani, K., Sugaya, Y.: ‘Unified computation of strict maximum likelihood for geometric fitting’, J. Math. Imaging Vis., 2010, 38, (1), pp. 1–13 (doi: 10.1007/s10851-010-0206-6).
-
39)
-
32. Brahmachari, A., Sarkar, S.: ‘Hop-diffusion Monte Carlo for epipolar geometry estimation between very wide-baseline images’, IEEE Trans. Pattern Anal. Mach. Intell., 2013, 35, (3), pp. 755–762 (doi: 10.1109/TPAMI.2012.227).
-
40)
-
21. Chojnacki, W., Brooks, M., Hengel, A., et al: ‘From fns to heiv: a link between two vision parameter estimation methods’, IEEE Trans. Pattern Anal. Mach. Intell., 2004, 26, (2), pp. 264–268 (doi: 10.1109/TPAMI.2004.1262197).
-
41)
-
43. Beis, J., Lowe, D.: ‘Shape indexing using approximate nearest-neighbor search in high-dimensional spaces’. Proc. of the IEEE Conf. Computer Vision and Pattern Recognition, Washington, DC, 1997, p. 1000.
-
42)
-
22. Fischler, M.A., Bolles, R.C.: ‘Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography’, Commun. ACM, 1981, 24, (6), pp. 381–395 (doi: 10.1145/358669.358692).
-
43)
-
20. Lowe, D.G.: ‘Distinctive image features from scale-invariant keypoints’, Int. J. Comput. Vis., 2004, 60, pp. 91–110 (doi: 10.1023/B:VISI.0000029664.99615.94).
-
44)
-
4. Bruckner, M., Bajramovic, F., Denzler, J.: ‘Intrinsic and extrinsic active self-calibration of multi-camera systems’, Mach. Vis. Appl., 2014, 25, (2), pp. 389–403 (doi: 10.1007/s00138-013-0541-x).
-
45)
-
28. Stewart, C.V.: ‘Robust parameter estimation in computer vision’, SIAM Rev., 1999, 41, pp. 513–537 (doi: 10.1137/S0036144598345802).
-
46)
-
31. Goshen, L., Shimshoni, I.: ‘Balanced exploration and exploitation model search for efficient epipolar geometry estimation’, IEEE Trans. Pattern Anal. Mach. Intell., 2008, 30, (7), pp. 1230–1242 (doi: 10.1109/TPAMI.2007.70768).
-
47)
-
9. Zhang, Z.: ‘Determining the epipolar geometry and its uncertainty: a review’, Int. J. Comput. Vis., 1998, 27, (2), pp. 161–198 (doi: 10.1023/A:1007941100561).
-
48)
-
14. Torr, P., Fitzgibbon, A.: ‘Invariant fitting of two view geometry or ‘in defiance of the 8 point algorithm’’. Proc. of the British Machine Vision Conf., Norwich, UK, September 2002, pp. 83–92.
-
49)
-
18. Bartoli, A., Sturm, P.: ‘Nonlinear estimation of fundamental matrix with minimal parameters’, IEEE Trans. Pattern Anal. Mach. Intell., 2004, 26, (3), pp. 426–432 (doi: 10.1109/TPAMI.2004.1262342).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2014.0436
Related content
content/journals/10.1049/iet-cvi.2014.0436
pub_keyword,iet_inspecKeyword,pub_concept
6
6