Skip to main content Accessibility help
×
Home

Mirage: an O(n) time analytical solution to 3D camera pose estimation with multi-camera support

  • Semih Dinc (a1), Farbod Fahimi (a2) and Ramazan Aygun (a1)

Summary

Mirage is a camera pose estimation method that analytically solves pose parameters in linear time for multi-camera systems. It utilizes a reference camera pose to calculate the pose by minimizing the 2D projection error between reference and actual pixel coordinates. Previously, Mirage has been successfully applied to trajectory tracking (visual servoing) problem. In this study, a comprehensive evaluation of Mirage is performed by particularly focusing on the area of camera pose estimation. Experiments have been performed using simulated and real data on noisy and noise-free environments. The results are compared with the state-of-the-art techniques. Mirage outperforms other methods by generating fast and accurate results in all tested environments.

Copyright

Corresponding author

*Corresponding author. E-mail: sd0016@uah.edu

References

Hide All
1. Petersen, T., A Comparison of 2D-3D Pose Estimation Methods Master's Thesis (Lautrupvang: Aalborg University-Institute for Media Technology Computer Vision and Graphics, 2008).
2. Nöll, T., Pagani, A. and Stricker, D., “Real-Time Camera Pose Estimation using Correspondences with High Outlier Ratios,” VISAPP 2010: International Conference on Computer Vision Theory and Applications, Angers, France (2010) pp. 381386.
3. Jaramillo, C., Dryanovski, I., Valenti, R. G. and Xiao, J., “6-DOF Pose Localization in 3D Point-Cloud Dense Maps Using a Monocular Camera,” Proceedings of the IEEE International Conference on Robotics and Biomimetics (ROBIO), IEEE, Shenzhen, China, (2013) pp. 17471752.
4. Ferraz, L., Binefa, X. and Moreno-Noguer, F., “Very Fast Solution to the PnP Problem with Algebraic Outlier Rejection,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Columbus, Ohio, USA, (2014) pp. 501508.
5. Tron, R., Zhou, X. and Daniilidis, K., “A Survey on Rotation Optimization in Structure from Motion,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Las Vegas, Nevada, USA (2016) pp. 7785.
6. Ansar, A. and Daniilidis, K., “Linear pose estimation from points or lines,” Pattern IEEE Trans. Anal. Mach. Intell. 25 (5), 578589 (2003).
7. Lepetit, V., Moreno-Noguer, F. and Fua, P., “EPnP: An Accurate O(n) Solution to the PnP Problem,” Int. J. Comput. Vis. 81 (2), 155166 (2009).
8. Kneip, L., Furgale, P. and Siegwart, R., “Using Multi-Camera Systems in Robotics: Efficient Solutions to the nPnP Problem,” Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), IEEE, Karlsruhe, Germany, (2013) pp. 37703776.
9. Chen, C. and Schonfeld, D., “Robust 3D pose estimation from multiple video cameras,” Proceedings of the 16th IEEE International Conference on Image Processing (ICIP), IEEE, Cairo Egypt (2009) pp. 541544.
10. Stewenius, H., Engels, C. and Nistér, D., “Recent developments on direct relative orientation,” ISPRS J. Photogramm. Remote Sens. 60 (4), 284294 (2006).
11. Lee, G. H., Li, B., Pollefeys, M. and Fraundorfer, F., “Minimal Solutions for Pose Estimation of a Multi-Camera System,” Proceedings of the International Symposium on Robotics Research (ISRR), Singapore (2013) pp. 116.
12. Chang, W. Y. and Chen, C. S., “Pose estimation for multiple camera systems,” Proceedings of the 17th International Conference on Pattern Recognition, ICPR, vol. 3, IEEE, Cambridge, UK (2004) pp. 262265.
13. Dinc, S., Fahimi, F. and Aygun, R., “Vision-based trajectory tracking for mobile robots using mirage pose estimation method,” IET Computer Vision (Institution of Engineering and Technology) 10 (5), 450458 (2016).
14. Dinc, S., Fahimi, F. and Aygun, R., “Vision-Based Trajectory Tracking Approach for Mobile Platforms in 3D World using 2D Image Space,” Proceedings of the ASME International Mechanical Engineering Congress and Exposition, (IMECE), vol. 4 B, San Diego, CA, United States (2013).
15. Leonard, S., Learning Feed-Forward Control for Vision-Guided Robotics PhD Thesis (University of Alberta, Computing Science, Alberta, Canada, 2008).
16. Chum, O. and Matas, J., “Matching with Prosac - Progressive Sample Consensus,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, vol. 1, San Diego, CA, USA, (2005) pp. 220226.
17. Rosenhahn, B., Pose Estimation Revisited PhD Thesis (Inst. für Informatik und Praktische Mathematik, Kiel, Germany, 2003).
18. Grest, D., Petersen, T. and Krüger, V., “A Comparison of Iterative 2D-3D Pose Estimation Methods for Real-Time Applications,” In: Image Analysis (Salberg, A., Hardeberg, J. Y. and Jenssen, R., eds.), (Springer, Oslo, Norway, 2009) pp. 706715.
19. Nöll, T., Pagani, A. and Stricker, D., “Markerless Camera Pose Estimation-an Overview,” In: OASIcs-OpenAccess Series in Informatics (Middel, A., Scheler, I. and Hagen, H., eds.) vol. 19 (Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik, Dagstuhl, Germany, 2011) pp. 4554.
20. Besl, P. J. and McKay, H. D., “A method for registration of 3-d shapes,” IEEE Trans. Pattern Anal. Mach. Intell. 14 (2), 239256 (1992).
21. Dementhon, D. F. and Davis, L. S., “Model-based object pose in 25 lines of code,” Int. J. Comput. Vis. 15 (1–2), 123141 (1995).
22. Guo, Y., “A novel solution to the p4p problem for an uncalibrated camera,” J. Math. Imaging Vis. 45 (2), 186198 (2013).
23. Tang, J., Chen, W.-S. and Wang, J., “A novel linear algorithm for P5P problem,” Appl. Math. Comput. 205 (2), 628634 (2008).
24. Zheng, Y., Kuang, Y., Sugimoto, S., Astrom, K. and Okutomi, M., “Revisiting the pnp Problem: A Fast, General and Optimal Solution,” Proceedings of the IEEE International Conference on Computer Vision (ICCV), IEEE, Sydney, Australia (2013) pp. 23442351.
25. Lu, C.-P., Hager, G. D. and Mjolsness, E., “Fast and globally convergent pose estimation from video images,” IEEE Trans. Pattern Anal. Mach. Intell. 22 (6), 610622 (2000).
26. Vandenhouten, R., Kistel, T. and Wendlandt, O., “A method for optical indoor localization of mobile devices using multiple identifiable landmarks,” Trans. IoT Cloud Comput. 1 (1) 110 (2015).
27. Quan, L. and Lan, Z., “Linear n-point camera pose determination,” IEEE Trans. Pattern Anal. Mach. Intell. 21 (8), 774780 (1999).
28. Choi, C. and Christensen, H. I., “3D Pose Estimation of Daily Objects using An rgb-d Camera,” Proceedings of the 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Vilamoura, Portugal (2012) pp. 33423349.
29. Szeliski, R., Computer Vision: Algorithms and Applications (Springer Science & Business Media, Springer-Verlag, NY, USA 2010).
30. Hesch, J., Roumeliotis, S., “A Direct Least-Squares (DLS) Method for PnP,” Proceedings of the IEEE International Conference on Computer Vision (ICCV), IEEE, Barcelona, Spain (2011) pp. 383390.
31. Li, S., Xu, C. and Xie, M., “A robust O(n) solution to the perspective-n-point problem,” IEEE Trans. Pattern Anal. Mach. Intell. 34 (7), 14441450 (2012).
32. Fabian, J. and Clayton, G., “Error analysis for visual odometry on indoor, wheeled mobile robots with 3-d sensors, Mechatronics,” IEEE/ASME Trans. 19 (6), 18961906 (2014).
33. Dryanovski, I., Valenti, R. G. and Xiao, J., “Fast Visual Odometry and Mapping from RGB-D Data,” Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), IEEE, Shenzhen, China (2013) pp. 23052310.
34. Svarm, L., Enqvist, O., Oskarsson, M. and Kahl, F., “Accurate Localization and Pose Estimation for Large 3D Models,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, USA, (2014) pp. 532539.
35. Engels, C., Stewénius, H. and Nistér, D., “Bundle adjustment rules,” Photogramm. Comput. Vis. 2 124131 (2006).

Keywords

Related content

Powered by UNSILO

Mirage: an O(n) time analytical solution to 3D camera pose estimation with multi-camera support

  • Semih Dinc (a1), Farbod Fahimi (a2) and Ramazan Aygun (a1)

Metrics

Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed.