Accurate mirror-based camera pose estimation with explicit geometric meanings
Source abstract
Abstract
An accurate closed form solution is proposed to estimate camera pose by several mirrored reference object images acquired via a planar mirror under different unknown poses. Compared with state-of-the-art methods, our method is more accurate when there are more than three images and has explicit geometric meanings. This method also properly handles cases in which some of the mirror poses are parallel. The central idea is to minimize an error metric based on all reflections of rotation, which enables the camera rotation to be estimated directly by SVD of sum of mirrored camera rotations. After that, the camera translation is computed by solving a large system of linear equations to minimize object space collinearity error. Both synthesized data and real data experiments show the advantages of our approach.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Robotics and Sensor-Based Localization · Advanced Vision and Imaging · Optical measurement and interference techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (29)
Show source-provided references
1. Lu C P, Hager G D, Mjolsness E. Fast and globally convergent pose estimation from video images. IEEE T Pattern Anal, 2000, 22: 610–62210.1109/34.862199 ↗
2. Li S, Xu C, Xie M. A robust O(n) solution to the perspective-n-point problem. IEEE T Pattern Anal, 2012, 34: 1444–145010.1109/TPAMI.2012.41 ↗
3. Hartley R, Zisserman A. Multiple View Geometry in Computer Vision. 2nd ed. Cambridge: Cambridge University Press, 200410.1017/CBO9780511811685 ↗
4. McGlone J, Mikhail E, Bethel J. Manual of Photogrammetry. 5th ed. Maryland: American Society for Photogrammetry and Remote Sensing, 2004
5. DeSouza G N, Kak A C. Vision for mobile robot navigation: A survey. IEEE T Pattern Anal, 2002, 24: 237–26710.1109/34.982903 ↗
6. Azuma R, Baillot Y, Behringer R, et al. Recent advances in augmented reality. IEEE Comput Graph, 2001, 21: 34–4710.1109/38.963459 ↗
7. Daniilidis K. Hand-eye calibration using dual quaternions. Int J Robot Res, 1999, 18: 286–29810.1177/02783649922066213 ↗
8. Yu Q F, Jiang G W, Fu S H, et al. Fold-ray videometrics method for the deformation measurement of nonintervisible large structures. Appl Optics, 2009, 48: 4683–468710.1364/AO.48.004683 ↗
9. Liu J B, Zhang X H, Liu H B, et al. Correction method for non-landing measuring of vehicle-mounted theodolite based on static datum conversion. Sci China Tech Sci, 2013, 56: 2268–227710.1007/s11431-013-5303-5 ↗
10. Liu J B, Zhang X H, Liu H B, et al. New method for camera pose estimation based on line correspondence. Sci China Tech Sci, 2013, 56: 2787–279710.1007/s11431-013-5361-8 ↗
11. Lebraly P, Deymier C, Ait-Aider O, et al. Flexible extrinsic calibration of non-overlapping cameras using a planar mirror: Application to vision-based robotics. In: Conference on Intelligent Robots and Systems. Taipei, Taiwan: 2010. 5640–5647
12. Sturm P, Bonfort T. How to compute the pose of an object without a direct view? In: 7th Asian Conference on Computer Vision. Hyderabad, India: 2006. 21–31
13. Kumar R, Ilie A, Frahm J M, et al. Simple calibration of non-overlapping cameras with a mirror. In: IEEE Conf Comput Vis Pattern Recognit. Anchorage, 2008. 1–7
14. Hesch J A, Mourikis A I, Roumeliotis S I. Mirror-based extrinsic camera calibration. In: International Workshop on the Algorithmic Foundations of Robotics. Berlin: Springer, 2009. 285–29910.1007/978-3-642-00312-7_18 ↗
15. Hesch J A, Mourikis A I, Roumeliotis S I. Extrinsic camera calibration using multiple reflections. In: 11th European Conference on Computer Vision. Heraklion, Greece: 2010. 311–325
16. Takahashi K, Nobuhara S, Matsuyama T. A new mirror-based extrinsic camera calibration using an orthogonality constraint. In: IEEE Conf Comput Vis Pattern Recognit. Providence, 2012. 1051–1058
17. Rodrigues R, Barreto P, Nunes U. Camera pose estimation using images of planar mirror reflections. In: 11th European Conference on Computer Vision. Heraklion, Greece: 2010. 382–395
18. Panahandeh G, Jansson M. IMU-camera self-calibration using planar mirror reflection. In: International Conference on Indoor Positioning and Indoor Navigation. Guimaraes, Portugal: 2011. 1–7
19. Jang K H, Lee D H, Jung S K. A moving planar mirror based approach for cultural reconstruction. Comput Animat Virt W, 2004, 15: 415–42310.1002/cav.45 ↗
20. Gluckman J, Nayar S K. Catadioptric stereo using planar mirrors. Int J Comput Vision, 2001, 44: 65–7910.1023/A:1011172403203 ↗
21. Ying X, Peng K, Hou Y, et al. Self-calibration of catadioptric camera with two planar mirrors from silhouettes. IEEE T Pattern Anal, 2013, 35: 1206–122010.1109/TPAMI.2012.195 ↗
22. Fillmore J P. A note on rotation matrices. IEEE Comput Graph, 1984, 4: 30–3310.1109/MCG.1984.275935 ↗
23. Umeyama S. Least-squares estimation of transformation parameters between two point patterns. IEEE T Pattern Anal, 1991, 13: 376–38010.1109/34.88573 ↗
24. Kanatani K. Analysis of 3-D rotation fitting. IEEE T Pattern Anal, 1994, 16: 543–54910.1109/34.291441 ↗
25. Arun K S, Huang T S, Blostein S D. Least-squares fitting of two 3-D point sets. IEEE T Pattern Anal, 1987, 698–700
26. Hartley R, Trumpf J, Dai Y, et al. Rotation averaging. Int J Comput Vision, 2013, 103: 267–30510.1007/s11263-012-0601-0 ↗
27. Moakher M. Means and averaging in the group of rotations. Siam J Matrix Anal A, 2002, 24: 1–1610.1137/S0895479801383877 ↗
28. Zhang Z. A flexible new technique for camera calibration. IEEE T Pattern Anal, 2000, 22: 1330–133410.1109/34.888718 ↗
29. Shimizu M, Okutomi M. Calibration and rectification for reflection stereo. In: IEEE Conf Comput Vis Pattern Recognit. Anchorage: 2008. 1–8