An efficient vision-based pose determination method of five coplanar points

Publication in Journal of Optical Technology

For Russian citation (Opticheskii Zhurnal):

Zimiao Zhang, Shihai Zhang, Qiu Li An efficient vision-based pose determination method of five coplanar points (Эффективный способ визуального определения ориентации объекта с помощью пяти компланарных точек) [на англ. яз.] // Оптический журнал. 2017. Т. 84. № 4. С. 35–41.

Zimiao Zhang, Shihai Zhang, Qiu Li An efficient vision-based pose determination method of five coplanar points (Эффективный способ визуального определения ориентации объекта с помощью пяти компланарных точек) [in English] // Opticheskii Zhurnal. 2017. V. 84. № 4. P. 35–41.

For citation (Journal of Optical Technology):

Zimiao Zhang, Shihai Zhang, and Qiu Li, "Efficient vision-based pose determination method of five coplanar points," Journal of Optical Technology. 84(4), 246-251 (2017). https://doi.org/10.1364/JOT.84.000246

Abstract:

The existing approaches to a solution of object pose fall into two distinct categories: analytical solutions and iterative solutions. In this paper, a two-step pose estimation method based on five coplanar points by combining the advantages of the above two methods is studied. In the first step, after the image coordinates of points are extracted through image processing the pose of object is determined with two affine invariants formed by the five points. In the second step, an iterative method is introduced, and the results of the first step are passed to the current step being used as initial values of the iterative process to ensure the accuracy and convergence rate of non-linear algorithm. The proposed method is then compared with other two existing methods. Experimental results demonstrate that the proposed method has the advantage of lower computational cost. The accuracy, which is the main concerns during the real-time applications, is also improved.

Keywords:

pose estimation, affine invariants, coplanarity, non-linear

Acknowledgements:

This research was supported by the Tianjin application foundation and advanced technology research program (the youth fund project), No.14JCQNJC05500, Innovation Team Training Plan of Tianjin Universities and Colleges (grant no. TD12-5043), National Natural Science Foundation of China (No.11302149), Tianjin application foundation and advanced technology research program (the youth fund project), No. 15JCQNJC02400.

OCIS codes: 330.4060; 330.5000; 330.0100

References:

1. Hao Ying-ming, Wu Qing-xiao, Zhou chuan. Technique and implementation of underwater vehicle station keeping based on monocular vision [J] // ROBOT. 2006. V. 28. No. 6. P. 656–661.
2. Huang Feng-shan, Qian Hui-fen. Single camera 3D coordinate vision measuring system using a light pen [J] // Opto-Electronic Engineering. 2007. V. 34. No. 4. P. 69–72.
3. Hao S., Chai Z., Zhang Z., Hu Y. Application of electro-optic aiming system in INS correction [J] // Electronics optics and control. 2002. V. 9. No. 1. P. 19–22.
4. Xu Liang-fa, Wang Jian-jun. Building of mathematical model of sight line for laser helmet mounted display and sight system [J] // Fire Control and Command Control. 2006. V. 31. No. 7. P. 80–82.
5. Chen Shan. Study on the monocular vision measurement system of the position and orientation of object // College of Precision Instrument and Opto-Electronics Engineering. Tianjin University. 2007.
6. Zhang Jin-feng, Sun Cheng, Cai Wei. Monocular vision-based relative position and attitude measurement algorithm between spacecrafts [J] // Optical Technique. 2010. V. 36. No. 2. P. 187–192.
7. Chao Zhi-chao, Jiang Guang-wen, Huang Wei, Song Shi-jun, Yu Qi-feng. Vision measuring system for soft-landing drop test of unmanned lunar explorer [J] // Optics and Precision Engineering. 2010. V. 18. No. 9. P. 2044–2052.
8. Tao Jin, Hongzhi Jia, Wenmei Hou, Ryo Yamamoto, Norihiro Nagai, Yusaku Fujii, Koichi Maru, Naoya Ohta, Kazuhito Shimada. Evaluating 3D position and velocity of subject in parabolic flight experiment by use of the binocular stereo vision measurement [J] // Chinese Optics Letters. 2010. V. 8. No. 6. P. 601–605.
9. Fischler M.A., Bolles R.C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography [C] // Communications of the ACM. 1981. V. 24. P. 6. P. 381–395.
10. Horaud R., Conio B., Leboulleux O., Lacolle B. An analytic solution for the perspective 4-point problem [J] // Computer Vision Graphics Image Process. 1989. V. 47. No. 1. P. 33–44.
11. Nister D., Stewenius H. Minimal solution to the generalized 3-point pose problem [J] // Mathematical Imaging and Vision. 2007. V. 27. No. 1. P. 67–79.
12. Hu Z.Y., Wu F.C. A note on the number solution of the non-coplanar P4P problem [C] // IEEE Trans. Pattern Anal. Mach. Intell. 2002. V. 24. No. 4. P. 550–555.
13. Jianliang Tang, Wen-Sheng Chen, Jie Wang. A novel linear algorithm for p5p problem [J] // Applied Mathematics and Computation. 2008. V. 205. No. 2. P. 628–634.
14. Wang Peng, Sun Changku, Zhang Zhimiao. Linear pose estimation with a monocular vision system [J] // Chinese Journal of Scientific Instrument. 2011. V. 32. No. 5. P. 1126–1131.
15. Ansar A., Daniilidis K. Linear pose estimation from points or lines [J] // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2003. V. 25. No. 5. P. 578–589.
16. Duan F.Q., Wu F.C., Hu Z.Y. Pose determination and plane measurement using a trapezium [J] // Pattern Recognition Letters. 2008. V. 29. No. 3. P. 223–231.
17. DeMenthon D.F., Davis L.S. Model-based object pose in 25 lines of code [J] // International Journal on Computer Vision. 1995. V. 15. No.1. P. 123–141.
18. Tommaso Gramegna, Author Vitae, Lea Venturino Author Vitae, Grazia Cicirelli Author Vitae, Giovanni Attolico Author Vitae, Arcangelo Distante. Optimization of the POSIT algorithm for indoor autonomous navigation [J] // Robotics and Autonomous Systems. 2004. V. 48. No. 2. P. 145–162.
19. Chen Shan, Zhou Tao, Zhang Xiaodong. Monocular vision measurement system of the position and attitude of the object [J] // Chinese journal of Sensors and Actuators. 2007. V. 20. No. 9. P. 2011–2015.
20. Peng Wang, Xu Xiao, Zimiao Zhang, Changku Sun. Study on the position and orientation measurement method with monocular vision system [J] // Chinese Optics Letters. 2010. V. 8. No. 1. P. 55–58.
21. Chester Wildey, Duncan L. MacFarlane, Aman Goyal, Kaundinya Gopinath, Sergey Cheshkov, Richard Briggs. Single-camera motion measurement and monitoring for magnetic resonance applications [J] // Applied Optics. 2011. V. 50. No. 14. P. 2088–2097.
22. Liu M.L., Wong K.H. Pose estimation using four corresponding points [J] // Pattern Recognition Letters. 1999. V. 20. No. 1. P. 69–74.
23. Shuping Zhang,Yongsheng Ding, Kuangrong Hao, Dan Zhang. An efficient two-step solution for vision-based pose determination of a parallel manipulator [J] // Robotics and Computer-Integrated Manufacturing. 2011. V. 28. No. 2. P. 182–189.