Efficient Fundamental Matrix Estimation for Robotic Visual Servoing Based on Continuous-time Optimization

Qiang Fu

doi:10.6180/jase.201903_22(1).0018

Efficient Fundamental Matrix Estimation for Robotic Visual Servoing Based on Continuous-time Optimization

Qiang Fu This email address is being protected from spambots. You need JavaScript enabled to view it.^1,2

¹School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, P.R. China
²Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing 100083, P.R. China

Received: August 6, 2018
Accepted: November 13, 2018
Publication Date: March 1, 2019

Download Citation: ||https://doi.org/10.6180/jase.201903_22(1).0018

ABSTRACT

This paper deals with the problem of estimating the fundamental matrix in real time for robotic visual servoing. In order to improve the efficiency of the fundamental matrix estimation,anew method incorporating the rank-2 constraint directly is proposed based on continuous-time optimization. By designing a proper projection matrix, the estimation is transformed into an integration process of a continuous-time dynamical equation. Simulation and real experiments show that, compared to conventional discrete-time optimization methods, the proposed method could achieve similar accuracy while converging faster(more than 7 times faster when the number of point correspondences is 1000).

Keywords: Fundamental Matrix, Epipolar Geometry, Equality Constraint, Continuous-time Optimization

REFERENCES

[1] Chaumette, F., and S. Hutchinson (2007) Visual servo control, part II: Advanced approaches, IEEE Robotics and Automation Magazine 14(1), 109118. doi: 10. 1109/MRA.2007.339609
[2] Sebastián, J. M., L. Pari, L. Angel, and A. Traslosheros (2009) Uncalibrated visual servoing using the fundamental matrix, Robotics and Autonomous Systems 57(1), 110. doi: 10.1016/j.robot.2008.04.002
[3] Liang, X., H. Wang, W. Chen, D. Guo, and T. Liu (2015) Adaptive image-based trajectory tracking control of wheeled mobile robots with an uncalibrated fixed camera, IEEE Transactions on Control Systems Technology 23(6), 22662282. doi: 10.1109/TCST. 2015.2411627
[4] Li, B., Y. Fang, and X. Zhang (2016) Visual servo regulation of wheeled mobile robots with an uncalibrated onboard camera, IEEE/ASME Transactions on Mechatronics 21(5), 23302342. doi: 10.1109/TMECH. 2015.2504098
[5] Fischler, M. A., and R. C. Bolles (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography, Communications of the ACM 24(6), 381395.
[6] Zhang, Z. (1998) Determining the epipolar geometry and its uncertainty: a review, International Journal of Computer Vision 27(2), 161195. doi: 10.1023/A: 1007941100561
[7] Hartley, R. (1997) In defense of the eight-point algorithm, IEEE Transactions on Pattern Analysis and Machine Intelligence 19(6), 580593. doi: 10.1109/ 34.601246
[8] Chesi, G., A. Garulli, A. Vicino, and R. Cipolla (2002) Estimating the fundamental matrix via constrained least-squares: a convex approach, IEEE Transactions on Pattern Analysis and Machine Intelligence 24(3), 397401. doi: 10.1109/CVPR.2013.203
[9] Zheng, Y., S. Sugimoto, and M. Okutomi (2013) A practical rank-constrained eight-point algorithm for fundamental matrix estimation, Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Portland, USA, Jun. 2328, 15461553. doi: 10.1109/34.990139
[10] Bugarin, F., A. Bartoli, D. Henrion, J. B. Lasserre, J. J. Orteu, and T. Sentenac (2015) Rank-constrained fundamental matrix estimation by polynomial global optimization versus the eight-point algorithm, Journal of Mathematical Imaging and Vision 53(1), 4260. doi: 10.1007/s10851-014-0545-9
[11] Kanatani, K., and Y. Sugaya (2007) High accuracy fundamental matrix computation and its performance evaluation, IEICE TRANSACTIONS on Information and Systems E90D(2), 579585. doi: 10.1093/ietisy/ e90-d.2.579
[12] Sugaya, Y., and K. Kanatani (2007) High accuracy computation of rank-constrained fundamental matrix, Proc. of British Machine Vision Conference, Coventry, UK, Sep. 1013, 110. doi: 10.5244/C.21.19
[13] Zheng, Y., S. Sugimoto, and M. Okutomi (2011) A branch and contract algorithm for globally optimal fundamental matrix estimation, Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, USA, Jun. 2025, 29532960. doi: 10.1109/CVPR.2011.5995352
[14] Hartley, R. and A. Zisserman (2004) Multiple View Geometry in Computer Vision, 2nd ed., Cambridge University Press, Cambrige, 284288.
[15] Migita, T. and T. Shakunaga (2007) Evaluation of epipole estimation methods with/without rank-2 constraint across algebraic/geometric error functions, Proc. of IEEE Conference on Computer Vision and Pattern Recognition,Minneapolis,USA, Jun. 1722, 17.doi: 10.1109/CVPR.2007.383116
[16] Tanabe, K. (1980) A geometric method in nonlinear programming, Journal of Optimization Theory and Applications 30(2), 181210. doi: 10.1007/BF00934495
[17] Brown, A. A., and M. C. Bartholomew-Biggs (1989) ODE versus SQP methods for constrained optimization, Journal of Optimization Theory and Applications 62(3), 371386. doi: 10.1007/BF00939812
[18] Absi, P. A. (2005) Computation with continuous-time dynamical systems, Proc. of the Grand Challenge in Non-Classical Computation International Workshop, York, UK. Apr. 1819, 57.
[19] Quan, Q., and K. Y. Cai (2016) A new continuous-time equality-constrained optimization to avoid singularity, IEEE Transactions on Neural Networks and Learning Systems 27(2), 262272. doi: 10.1109/TNNLS.2015. 2476348
[20] Armangué, X., and J. Salvi (2003) Overall view regarding fundamental matrix estimation, Image and Vision Computing 21(2), 205220. doi: 10.1016/ S02628856(02)00154-3
[21] Lowe, D. G. (2004) Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision 60(2), 91110. doi: 10.1023/B:VISI. 0000029664.99615.94