Monocular vision measurement system based on EPNP algorithm

Zhang Huijuan; Xiong Zhi; Lao Dabao; Zhou Weihu

doi:10.3788/IRLA201948.0517005

The method of pose measurement using computer vision is widely used in modern control, navigation, tracking and other fields. A monocular visual pose measurement method was studied and designd based on P4P rectangular distribution of planar target and EPNP algorithm in this paper. Firstly, a single camera was used to obtain the plane target image. After the image processing, the pixel coordinates of the four feature points were obtained, and the EPNP algorithm was used to perform the attitude calculation. Secondly, the simulation analysis of pose error measurement provides theoretical guidance and basis for improving attitude measurement accuracy. Finally, a coordinate system registration method combined with a high-precision two-dimensional turntable was proposed. The method was used to verify the accuracy of the three-direction attitude angles. The experimental results show that the rotation angle around the x and y axes is[-6, 6], the pose measurement error is less than 0.1 to meet the measurement application requirements.

Monocular vision measurement system based on EPNP algorithm

1. School of Mechanical Engineering,Hubei University of Technology,Wuhan 430068,China;

2. Institute of Optics,Chinese Academy of Sciences,Beijing 100094,China

Received Date: 2018-12-09

Rev Recd Date: 2019-01-01

Publish Date: 2019-05-25

Key words:

computer vision /
pose /
EPNP /
plane target

Abstract: The method of pose measurement using computer vision is widely used in modern control, navigation, tracking and other fields. A monocular visual pose measurement method was studied and designd based on P4P rectangular distribution of planar target and EPNP algorithm in this paper. Firstly, a single camera was used to obtain the plane target image. After the image processing, the pixel coordinates of the four feature points were obtained, and the EPNP algorithm was used to perform the attitude calculation. Secondly, the simulation analysis of pose error measurement provides theoretical guidance and basis for improving attitude measurement accuracy. Finally, a coordinate system registration method combined with a high-precision two-dimensional turntable was proposed. The method was used to verify the accuracy of the three-direction attitude angles. The experimental results show that the rotation angle around the x and y axes is[-6, 6], the pose measurement error is less than 0.1 to meet the measurement application requirements.

HTML

Reference (14)

[1]	Yu Chang'an. Study on position and attitude tracking technology of single camera vision based on cooperate aim[D]. Harbin:Harbin Institute of Technology, 2010. (in Chinese)于长安.基于合作目标的单目视觉位姿跟踪技术研究[D].哈尔滨:哈尔滨工业大学, 2010.
[2]	Wang Peng, Sun Changku, Zhang Zimiao. Linear pose estimation with a monocular vision system[J]. Chinese Journal of Scientific Instrument, 2011, 32(5):1126-1131. (in Chinese)王鹏, 孙长库, 张子淼.单目视觉位姿测量的线性求解[J].仪器仪表学报, 2011, 32(5):1126-1131.
[3]	Stephen A Kyle. Roll angle in 6DOF tracking[J]. Journal of the CMSC, 2008, 6(5):1-10.
[4]	Wang Tianyu, Dong Wenbo, Wang Zhenyu. Position and orientation measurement system based on monocular vision and fixed target[J]. Infrared and Laser Engineering, 2017, 46(4):0427003. (in Chinese)王天宇, 董文博, 王震宇. 基于单目视觉和固定靶标的位姿测量系统[J]. 红外与激光工程, 2017, 46(4):0427003.
[5]	Rawia Frikha. Camera pose estimation for augmented reality in a small indoor dynamicscene[J]. Journal of Electronic Imaging, 2017, 26(5):24-30.
[6]	Xi Zhihong, Li Shuang, Zeng Jiqin, et al. Research on an imp-roved algorit-hm for solving PnP problem[J]. Applied Science and Technology, 2018, 45(4):56-60. (in Chinese)席志红, 李爽, 曾继琴, 等. 一种改进的PnP问题求解算法研究[J]. 应用科技, 2018, 45(4):56-60.
[7]	Chen Peidong. A thesis submitted in partial fulfillment of the requirements for the degree of master of engineering[D]. Wuhan:Huazhong University of Science Technology, 2014. (in Chinese)陈沛东. 盾构姿态测量系统的关键技术[D]. 武汉:华中科技大学, 2014.
[8]	Gao Yang. Research on 6-DOF measurement in large-scale precision engineering[D]. Tianjin:Tianjin University, 2016.(in Chinese)高扬. 面向大型精密工程的六自由度测量技术研究[D]. 天津:天津大学. 2016.
[9]	He Feiyan, Lin Jiarui, Gao Yang, et al. Optimized pose measurement system combining monocular vision with inclinometer sensor[J]. Acta Optica Sinica Journal of Optics, 2016, 36(12):1-8. (in Chinese)何斐彦, 林嘉睿, 高扬, 等. 单目视觉与倾角仪组合优化的位姿测量系统[J]. 光学学报, 2016, 36(12):1-8.
[10]	Lepetit V, Moreno-Noguer F, Fua P. Epnp:an accurate O(n) solution to the pnp problem[J]. International Journal of Computer Vision, 2009, 81(2):155-166.
[11]	Li Shujie, Liu Xiaoping. An accurate and fast algorithm for camera pose estimate on[J]. Journal of Image and Graphics, 2014, 19(1):20-27. (in Chinese)李书杰, 刘小平. 摄像机位姿的高精度快速求解[J]. 中国图像图形学报, 2014, 19(1):20-27.
[12]	Wu Jun, Bai Gang, Zhang Caixia. Experimental comparison and analysis of EPNP and POSIT algorithm in head pose estimation[J].Journal of North China University of Technology, 2017, 29(2):19-27. (in Chinese)武君, 白刚, 张彩霞. EPNP和POSIT算法在头部姿态估计上的实验比较与分析[J]. 北方工业大学学报, 2017, 29(2):19-27.
[13]	Deng Fei, Wu Yousi. Position and pose estimation of spherical panoramic image with improved EPnP algorithm[J].Acta Geodaetica et Cartographica Sinica, 2016, 45(6):677-684. (in Chinese)邓非, 吴幼丝. 球形全景影像位姿估计的改进EPnP算法[J]. 测绘学报, 2016, 45(6):677-684.
[14]	Yang Sen. Weighted linear methods for the camera pose estimation[J]. Journal of Software, 2011, 22(10):2476-2487. (in Chinese)杨森. 摄像机位姿的加权线性算法[J]. 软件学报, 2011, 22(10):2476-2487.

Monocular vision measurement system based on EPNP algorithm

doi: 10.3788/IRLA201948.0517005

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views