Qiang Fu1,2, Zi-Liang Zheng1,2, Shu-Yu Zhang1,2
1School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China
2Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing 100083, China
Received:
October 29, 2019
Accepted:
December 11, 2019
Download Citation:
||https://doi.org/10.6180/jase.202003_23(1).0006
ABSTRACT
This paper deals with the problem of reconstructing the three-dimensional (3D) feature points for robotic visual servoing. Based on the epipolar geometry constraint and the ray distance constraint, a 3D feature point reconstruction method is proposed based on multiple cameras. Simulation and real experiments are performed to show the effectiveness of the proposed method (the reconstruction accuracy reaches millimeter level). Compared to traditional feature point reconstruction methods, the proposed method is not only suitable for conventional cameras but also suitable for fish-eye cameras, which expands the application range.
Keywords:
3D reconstruction, point matching, epipolar geometry, ray distance, multiple cameras
REFERENCES
- [1]He, W., Li, Z., Chen, C. L. P. (2017). A survey of human-centered intelligent robots: issues and challenges, IEEE/CAA Journal of Automatica Sinica 4(4), 602- doi: 10.1109/JAS.2017.7510604
- [2]Fu, Q., Chen, X.-Y., He, W. (2019). A survey on 3D visual tracking of multicopters, International Journal of Automation and Computing 16(6), 707- doi: 10.1007/s11633-019-1199-2
- [3]Wang, Y., Wang, R., Wang S., et al. (2019). Underwater bio-inspired propulsion: from inspection to manipulation, IEEE Transactions on Industrial Electronics, early doi: 10.1109/TIE.2019.2944082
- [4]Mariottini, G. L., Oriolo, G., Prattichizzo, D. (2007). Image-based visual servoing for nonholonomic mobile robots using epipolar geometry, IEEE Transactions on Robotics 23(1), 87- doi: 10.1109/TRO.2006.886842
- [5]Zhang, Z. (1998). Determining the epipolar geometry and its uncertainty: a review, International Journal of Computer Vision 27(2), 161- doi: 10.1023/A: 1007941100561
- [6]Cui, X. F., Wang, X. M., Wang, X. (2004). A method of automatically recognizing and matching artificial signs. Computer Engineering and Applications, (21): 79-81. doi:10.3321/j.issn:1002-8331.2004.21.024
- [7]Wang, Z., Yu, Y. L., Zhang, D. (1998). Best neighborhood matching: an information loss restoration technique for block-based image coding systems. IEEE Transactions on Image Processing, 7(7), 1056- doi: 10.1109/83.701166
- [8]Yoon, K. J., Kweon, I. S. (2006). Adaptive support-weight approach for correspondence search. IEEE Transactions on Pattern Analysis and Machine Intelligence, (4), 650- doi: 10.1109/TPAMI.2006.70
- [9]Heo, Y. S., Lee, K. M., Lee, S. U. (2010). Robust stereo matching using adaptive normalized cross-correlation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(4), 807- doi: 10.1109/TPAMI.2010.136
- [10]Lin, Q., Yang, R., Zhang, Z., et al. (2018). Robust stereo-match algorithm for infrared markers in image-guided optical tracking system. IEEE Access, 6, 52421- doi: 10.1109/ACCESS.2018.2869433
- [11]Cai, M., Wang, Y., Wang, S., et al. (2019). Prediction-based seabed terrain following control for an underwater vehicle-manipulator system. IEEE Transactions on Systems, Man, and Cybernetics: Systems, early doi: 10.1109/TSMC.2019.2944651
- [12]Vicon Motion Capture Systems, 2019. [Online]. Available: https://www.vicon.com/
- [13]OptiTrack Motion Capture Systems, 2019. [Online]. Available: http://optitrack.com/
- [14]Papadimitriou, D. V., Dennis, T. J. (1996). Epipolar line estimation and rectification for stereo image pairs. IEEE Transactions on Image Processing, 5(4), 672-676. doi: 10.1109/83.491345
- [15]Ramalingam, S., Sturm, P., Lodha, S. K. (2005). Towards complete generic camera calibration. Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, USA, Jun. 20-26, 1093-1098. doi: 10.1109/CVPR.2005.347
- [16]He, W., Dong, Y. (2018). Adaptive fuzzy neural network control for a constrained robot using impedance learning. IEEE Transactions on Neural Networks and Learning Systems, 29(4), 1174-1186. doi: 1109/TNNLS.2017.2665581
- [17]Kannala, J., Brandt, S. S. (2006). A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(8), 1335- doi: 10.1109/TPAMI.2006.153
- [18]Hartley, R., Zisserman, A. (2004). Multiple View Geometry in Computer Vision, 2nd ed., Cambridge University Press, Cambridge, 312-313
- [19]Fu, Q., Quan, Q., Cai, K.-Y (2015). Calibration of multiple fish-eye cameras using a wand, IET Computer Vision, 9(3), 378 doi: 10.1049/iet-cvi.2014.0181
- [20]Fu Q. (2019). Efficient fundamental matrix estimation for robotic visual servoing based on continuous-time optimization, Journal of Applied Science and Engineering, 22(1), 179 doi: 10.6180/jase.201903_22(1).0018
- [21]Assa, A., Janabi-Sharifi, F. (2015). Virtual visual servoing for multicamera pose estimation, IEEE/ASME Transactions on Mechatronics, 20(2), 789–798. doi: 10.1109/TMECH.2014.2305916
