Pose estimation of camera based on weighted accelerated orthogonal iterative algorithm

被引：0

作者：

Xiong Z. ^{[1
,2
]}

Xu H. ^{[1
,2
]}

Zhang L. ^{[3
]}

Guo Z. ^{[1
,2
]}

Wu C. ^{[1
,2
]}

Feng W. ^{[1
,2
]}

Zhai Z. ^{[1
,2
]}

Zhou W. ^{[1
,4
]}

Dong D. ^{[4
]}

机构：

[1] School of Mechanical Engineering, Hubei University of Technology, Wuhan

[2] Hubei Key Lab of Manufacture Quality Engineering, Wuhan

[3] Haining Institute of Integrated Circuits and Advanced Manufacturing, Haining

[4] Institute of Microelectronics, Chinese Academy of Sciences, Beijing

来源：

Hongwai yu Jiguang Gongcheng/Infrared and Laser Engineering | 2022年 / 51卷 / 10期

关键词：

adaptive weights; machine vision; pose estimation; weighted orthogonal iterative;

D O I：

10.3788/IRLA20220030

中图分类号：

学科分类号：

摘要：

Pose estimation in monocular vision is a key problem in three-dimensional measurement, which is widely used in machine vision, precision measurement and so on. This problem can be solved by n-point perspective (PnP) algorithm. Orthogonal iterative algorithm (OI), as the representative of PnP algorithm, has been widely used in practice because of its high precision. In order to further improve the robustness and computational efficiency of OI algorithm, a weighted accelerated orthogonal iterative algorithm (WAOI) is proposed in this paper. Firstly, the weighted orthogonal iterative algorithm is deduced according to the classical orthogonal iterative algorithm. The weighted collinearity error function is constructed and the weight is updated by using the object point reprojection error to achieve the purpose of iteratively optimizing the pose estimation results. Secondly on this basis, through adaptive weights, the calculation of translation vector and objective function in each iteration is integrated to reduce the amount of calculation in the iterative process, so as to accelerate the algorithm. The experimental results show that when there are two rough points in the 12 reference points, the reprojection accuracy of the reference point of WAOI is 0.64 pixel, the operation time is 8.02 ms, the accuracy is high and the running speed is fast, so it has strong engineering practical value. © 2022 Chinese Society of Astronautics. All rights reserved.

引用

共 22 条

[1]

Wang Ping, Zhou Xuefeng, An Aimin, Et al., Robust and linear solving method for Perspective-n-Point problem, Chinese Journal of Scientific Instrument, 41, 9, pp. 271-280, (2020)

[2]

Liu Jinbo, Guo Pengyu, Li Xin, Et al., Evaluation strategy for camera pose estimation algorithm based on point correspondences, Acta Optica Sinica, 36, 5, (2016)

[3]

Wang Jiabao, Zhang Shirong, Zhou Qingya, Vision based real-time 3D displacement measurement using weighted iterative EPnP algorithm, Chinese Journal of Scientific Instrument, 41, 2, pp. 166-175, (2020)

[4]

Abdel-aziz Y I, Karara H M, Hauck M., Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry, Photo-grammetric Engineering & Remote Sensing, 81, 2, pp. 103-107, (2015)

[5]

Zhang Huijuan, Xiong Zhi, Lao Dabao, Et al., Monocular vision measurement system based on EPNP algorithm, Infrared and Laser Engineering, 48, 5, (2019)

[6]

Li S, Xu C, Xie M., A robust O(n) solution to the perspective-n-point problem, IEEE Transactions on Pattern Analysis and Machine Intelligence, 34, 7, pp. 1444-1450, (2012)

[7]

Zheng Y, Kuang Y, Sugimoto S, Et al., Revisiting the PNP problem: A fast, general and optimal solution, IEEE International Conference on Computer Vision, pp. 2344-2351, (2013)

[8]

Wang P, Xu G, Cheng Y, Et al., A simple, robust and fast method for the perspective-n-point problem, Pattern Recognition Letters, 108, 6, pp. 31-37, (2018)

[9]

Lao Dabao, Zhang Huijuan, Xiong Zhi, Et al., Automatic measurement method of attitude based on monocular vision, Acta Photoica Sinica, 48, 3, (2019)

[10]

Lu C P, Hager G D, Mjolsness E., Fast and globally convergent pose estimation from video images, IEEE Transactions on Pattern Analysis and Machine Intelligence, 22, 6, pp. 610-622, (2000)

← 1 2 3 →