DOI: 10.17586/1023-5086-2021-88-08-54-66

Vision-based pose estimation algorithm with four coplanar feature points via an incident-ray-based camera model

Fu, Anqi, Wang, Zhiwu, Zhang, Shihai, Zhang, Zimiao

Publication in Journal of Optical Technology

For Russian citation (Opticheskii Zhurnal):

Zhang Zimiao, Wang Zhiwu, Zhang Shihai, Fu Anqi Vision-based pose estimation algorithm with four coplanar feature points via an incident-ray-based camera model (Алгоритм оценки положения тела на основе визуальных данных с четырьмя копланарными характерными точками с помощью модели отслеживания падающих лучей) [на англ. яз.] // Оптический журнал. 2021. Т. 88. № 8. С. 54–66. http://doi.org/10.17586/1023-5086-2021-88-08-54-66

Zhang Zimiao, Wang Zhiwu, Zhang Shihai, Fu Anqi Vision-based pose estimation algorithm with four coplanar feature points via an incident-ray-based camera model (Алгоритм оценки положения тела на основе визуальных данных с четырьмя копланарными характерными точками с помощью модели отслеживания падающих лучей) [in English] // Opticheskii Zhurnal. 2021. V. 88. № 8. P. 54–66. http://doi.org/10.17586/1023-5086-2021-88-08-54-66

For citation (Journal of Optical Technology):

Zimiao Zhang, Zhiwu Wang, Shihai Zhang, and Anqi Fu, "Vision-based pose estimation algorithm with four coplanar feature points via an incident-ray-based camera model," Journal of Optical Technology. 88(8), 445-453 (2021). https://doi.org/10.1364/JOT.88.000445

Abstract:

The pinhole imaging model assumes that all the projecting rays intersect at the effective pinhole point. The restriction of this camera model will result in the low accuracy of vision-based pose estimation. Furthermore, the camera calibration gets the global optimal solution of intrinsic and extrinsic parameters, which will affect the calibration accuracy of intrinsic parameters and then pose estimation accuracy is also affected. In this paper we completed the pose estimation with four coplanar feature points via incident-ray-based camera model. Two parallel planes are used to perform the ray-pixel mapping. The projecting ray could be defined by its two intersections with the two planes. In this way, the camera is parametrized by the image plane and the two parallel planes. Based on this camera model, through four coplanar feature points, the object pose could be estimated. The whole process consists of both non-iterative step and iterative step. In the non-iterative step, the initial estimating of pose is obtained and then it is refined in the iterative step. Experiments results on pose estimation by the algorithm proposed and the other existing algorithms demonstrate the superiority of our algorithm.

Keywords:

pose estimation, incident-ray-based, two parallel planes, four coplanar feature points

Acknowledgements:

This research was supported by the National Natural Science Foundation of China (No. 51605332, No. 51905378). This research was supported by the Natural Science Foundation of Tianjin, No.19JCQNJC04200, No.18JCQNJC73100.

OCIS codes: 150.0150, 150.1135, 100.0100

References:

1. Wang X., Cao Y., Zhou K. Methods of monocular pose measurement based on planar objects // Optics and Precision Engineering. 2017. V. 25(1). P. 274–280.
2. Gao F., Chen N., Fan Y. et al. Visual pose estimation method for rotor UAVs autonomous landing // Electronics Optics & Control. 2017. № 2. P. 41–44.
3. Sun C., Xu Z., Wang D. Pose prediction method for moving helmet-mounted display and sight system // Journal of Electronic Measurement and Instrumentation. 2014. № 7. P. 724–729.
4. Lei J., Zeng L., Ye N. Research on industrial robot alignment technique with monocular vision // Optics and Precision Engineering. 2018. V. 26(3). P. 733–741.
5. Yang W., Lin J., Gao Y. et al. Pose measurement system of double shield universal compact // ACTA OPTICA SINICA. 2015. V. 35(11). P. 139–147.
6. Quan L., Lan Z. Linear n-point camera pose determination // IEEE Transactions on Pattern Analysis & Machine Intelligence. 1999. V. 21(8). P. 774–780.
7. Daniilidis K., Ansar A. Linear pose estimation from points or lines // IEEE Transactions on Pattern Analysis & Machine Intelligence. 2003. V. 25(5). V. 578–589.
8. Duan F., Wu F., Hu Z. Pose determination and plane measurement using a trapezium // Pattern Recognition Letters. 2008. V. 29(3). P. 223–31.
9. Lepetit V., Moreno-Noguer F., Fua P. EPnP: An accurate O (n) solution to the PnP problem // International Journal of Computer Vision. 2009. V. 81(2). P. 155–166.
10. Hu Z., Lei C., Wu F. A short note on P4P problem // ACTA AUTOMATICA SINICA. 2001. V. 27(6). P. 770–776.
11. Zhang Z. A flexible new technique for camera calibration // IEEE Transactions on Pattern Analysis & Machine Intelligence. 2000. V. 22(11). P. 1330–1334.
12. Zhang Z., Liu B., Jiang Y. A two-step pose estimation method based on four non-coplanar points // Optik – International Journal for Light and Electron Optics. 2015. V. 126(17). P. 1520–1526.
13. Zhang S., Ding Y., Hao K. et al. An efficient two-step solution for vision-based pose determination of a parallel manipulator // Robotics & Computer Integrated Manufacturing. 2012. V. 28(2). P. 182–189.
14. Chen P., Wang C. IEPnP：An iterative camera pose estimation algorithm based on EPnP // ACTA OPTICA SINICA. 2018. V. 38(4). P. 130–136.
15. Dementhon D., Davis L. Model-based object pose in 25 lines of code // International journal of computer vision. 1995. V. 15(1). P. 123–141.
16. Oberkampf D., DeMenthon D., Davis L. Iterative pose estimation using coplanar feature points // Computer Vision and Image Understanding. 1996. V. 63(3). P. 495–511.
17. Gramegna T., Venturino L., Cicirelli G. et al. Optimization of the POSIT algorithm for indoor autonomous navigation // Robotics & Autonomous Systems. 2004. V. 48(2). P. 145–162.
18. Sun C., Sun P., Wang P. An improvement of pose measurement method using global control points calibration // Plos One. 2015. V. 10(7). P. e0133905.
19. Zhang Z., Zhang S., Li Q. Robust and accurate vision-based pose estimation algorithm based on four coplanar feature points // Sensors. 2016. V. 16(12). P. 2173.

20. Zhu Z., Wang X., Liu Q., Zhang F. Camera calibration method based on optimal polarization angle // Optics and Lasers in Engineering. 2019. V. 112(1). P. 128–135.
21. Zhu Z., Wang S., Zhang H. et al. Camera projector system calibration method based on optimal polarization angle // Optical Engineering. 2020. V. 59(3). P. 035104.
22. Ye J., Yu J. Ray geometry in non-pinhole cameras: a survey // Visual Computer. 2014. V. 30(1). P. 93–112.
23. Miraldo P., Araujo H. Calibration of smooth camera models // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2013. V. 35(9). P. 2091–2103.
24. Miraldo P., Araujo H., Goncalves N. et al. Pose estimation for general cameras using lines // IEEE Transactions on Systems, Man, and Cybernetics. 2015. V. 45(10). P. 2156–2164.
25. Miraldo P., Araujo H. Pose estimation for non-central cameras using planes // Journal of Intelligent and Robotic Systems. 2015. V. 80(3). P. 595–608.
26. Gennery D. Generalized camera calibration including fish-eye lenses // International Journal of Computer Vision. 2006. V. 68(3). P. 239–266.
27. Michael D., Shree K. The raxel imaging model and ray-based calibration // International Journal of Computer Vision. 2005. V. 61(2). P. 119–137.
28. Sun P., Sun C., Li W. et al. A new pose estimation algorithm using a perspective-ray-based scaled orthographic projection with iteration // Plos One. 2015. V. 10(7). P. e0134029.
29. Sun C., Dong H., Zhang B. et al. An orthogonal iteration pose estimation algorithm based on an incident ray tracking model // Measurement Science and Technology. 2018. V. 29(9). P. 095402.
30. Guo X., Tang J., Li J., et al. Attitude measurement based on imaging ray tracking model and orthographic projection with iteration algorithm // ISA Transactions. 2019. V. 95. V. 379–391.