Optimization of Surround-View System Projection Parameters using Fiducial Markers
https://doi.org/10.17587/mau.23.97-103
Abstract
The paper is devoted to the problem of increasing quality of reproduction of the environment by mobile robot’s surround-view system, operating in the augmented reality mode. A variant of a surround-view system based on the cameras with over-lapping fields of view is being considered. A virtual model has been developed, it includes 3D-CAD models of a mobile robot and surrounding objects, as well as virtual models of cameras. The cross-platform integrated development environment "Unity" was chosen to implement the model. Methods for solving the problem of displaying the surrounding mobile robot space in the "third-person view" mode are determined. A mathematical criterion for assessing the quality of reproduction of the surrounding space is proposed. It is based on the comparison of points obtained from a virtual model with points obtained as a result of projection of images from virtual cameras. To obtain points, ArUco fiducial markers were used, providing an unambiguous comparison of points on the original and synthesized images. The dependence of the value of the objective function of the optimization problem on the projection parameters by the uniform search method are investigated. A method for automatic adaptation of projection parameters using fisheye lenses and stereo vision methods is proposed. Directions for further research are identified.
Supporting agencies: The reported study was funded by RFBR, project number 20-38-90094 "Study of methods for estimating distances to environmental objects using a surround-view system of mobile robots".
About the Authors
V. V. Varlashin
Peter the Grate St. Petersburg Politechnic University (SPbPU)
Russian Federation
Russian Federation
Graduate Student of the Department of Mechatronics and Robotics, Research Engineer of the SPbPU
St. Petersburg, 195251
A. V. Lopota
Peter the Grate St. Petersburg Politechnic University (SPbPU)
Russian Federation
Russian Federation
St. Petersburg, 195251
References
1. Shi Q., Li C., Wang C., Luo H., Huang Q., Fukuda T. Design and implementation of an omnidirectional vision system for robot perception, Mechatronics, 2017, vol. 41, pp. 58—66.
2. Kashyap V., Agrawal P., Akhbari F. Real-time, Quasi Immersive, High Definition Automotive 3D Surround View System, Int’l Conf. IP, Comp. Vision, and Pattern Recognition, 2017, pp. 10—16.
3. Lim S., Jun S., Jung I. Wrap-around View Equipped on Mobile Robot, World Academy of Science, Engineering and Technology, International Journal of Electrical, Computer, Energetic, Electronic and Communication Engineering, 2012, vol. 6, pp. 354—356.
4. Yang Z., Zhao Y., Hu X., Yin Y., Zhou L., Tao D. A flexible vehicle surround view camera system by central-around coordinate mapping model, Multimedia Tools and Applications, 2018, vol. 78, pp. 11983—12006.
5. Gao Y., Lin C., Zhao Y., Wang X., Wei S., Huang Q. 3-D Surround View for Advanced Driver Assistance Systems, IEEE Transactions on Intelligent Transportation Systems, 2018, vol. 19, pp. 320—328.
6. Official web site of Open Source Robotics Foundation, available at: www.turtlebot.com/ (accessed 01.10.2021).
7. Official web site of Unity Technologies, available at: www.unity.com/ (accessed 01.10.2021).
8. Official web site Epic Games, available at: www.unrealengine.com/ (accessed 01.10.2021).
9. Official web site of OpenCV team community, available at: www.opencv.org/ (accessed 01.10.2021).
10. Kuo T. Y., Wang Y. S., Cheng Y. J., Wan K. H. 3D Around View Monitoring System for automobiles, ICCE, IEEE, 2017, pp. 271—272.
11. Yeh Y. T., Peng C. K., Chen K. W., Chen Y. S., Hung Y. P. Driver Assistance System Providing an Intuitive Perspective View of Vehicle Surrounding, ACCV Workshops, Springer, 2014, pp. 403—417.
12. Sung K., Lee J., An J. Chang E. Development of Image Synthesis Algorithm with Multi-Camera, VTC Spring, IEEE, 2012, pp. 1—5.
13. Auysakul J., Xu H., Zhao W. Development of Hemi-Cylinder Plane for Panorama View in Around View Monitor Applications, 2016 International Conference on Computational Intelligence and Applications (ICCIA), 2016, pp. 26—30.
14. Varlashin V. V., Ershova M. A., Bunyakov V. A., Shmakov O. U. Real-Time Surround-View System for Mobile Robotic System, Mekhatronika, Avtomatizatsiya, Upravlenie, 2019, vol. 20(3), pp. 162—170 (in Russian).
15. Lowe D. G. Object recognition from local scale-invariant features, Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999, vol. 2, pp. 1150—1157.
16. Bay H., Tuytelaars Y., Van Gool L. SURF: Speeded up robust features, Computer Vision-ECCV, 2006, vol. 3951, pp. 404—417.
17. Rublee E., Rabaud, V., Konolige K., Bradski G. R. ORB: An efficient alternative to SIFT or SURF, 2011 International Conference on Computer Vision, 2011, pp. 2564—2571.
18. Garrido-Jurado S., Muñoz-Salinas R., Madrid-Cuevas F. J., Marín-Jiménez M. J. Automatic generation and detection of highly reliable fiducial markers under occlusion, Pattern Recognition, 2014, vol. 47, pp. 2280—2292.
Review
For citations:
Varlashin V.V., Lopota A.V. Optimization of Surround-View System Projection Parameters using Fiducial Markers. Mekhatronika, Avtomatizatsiya, Upravlenie. 2022;23(2):97-103. (In Russ.) https://doi.org/10.17587/mau.23.97-103
Views:
349
.png)
Email this article 