Enhanced Arithmetic Optimization Algorithm for Improving the Accuracy of Monocular Vision Pose Measurement System in a Robotic Manipulator
IEEE Transactions on Instrumentation and Measurement · 2026 · 75 · 1010113-1010113
DOI: 10.1109/tim.2026.3746819 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Instrumentation and Measurement, 2026. Verfasst von Yaru Li und 5 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Gefördert von: Zhejiang Province Natural Science Foundation of China, Joint Fund of the National Natural Science Foundation of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
To address the issue of intrinsic parameter variations in the camera due to vibrations and other factors during its movement along with the robotic manipulator, an enhanced arithmetic optimization algorithm (EAOA) is proposed. First, an efficient perspective n-point (EPnP) algorithm is used to estimate the pose of an object. The image point coordinates obtained and the pose measurement results are utilized to minimize the reprojection error, which is used to establish the objective function. Second, based on the backpropagation algorithm, the negative gradients of each intrinsic parameter are taken as the optimization direction, and the size is restricted, enabling the online measurement of intrinsic parameters (IPS) to be achieved. Finally, the EAOA is used to further optimize the IPS, thereby improving the accuracy of the pose measurement system. The experimental results show that EAOA can perform online optimization of IPS based on the input information from each measurement. Compared with EPnP, the reprojection error of EAOA is improved by 60.58 %, the orientation error is improved by 32.32 %, and the position error is improved by 46.25 %, significantly enhancing the accuracy of the pose measurement system.
Förderung
- Zhejiang Province Natural Science Foundation of China
- Joint Fund of the National Natural Science Foundation of China
- National Natural Science Foundation of China
- Fundamental Research Funds for the Provincial Universities of Zhejiang
Zitieren
APA
Li, Y., Wang, Y., Luo, Z., Jiang, W., Cheng, Y., & Tang, Y. (2026). Enhanced Arithmetic Optimization Algorithm for Improving the Accuracy of Monocular Vision Pose Measurement System in a Robotic Manipulator. IEEE Transactions on Instrumentation and Measurement, 75, 1010113-1010113. https://doi.org/10.1109/tim.2026.3746819
Vancouver
Li Y, Wang Y, Luo Z, Jiang W, Cheng Y, Tang Y. Enhanced Arithmetic Optimization Algorithm for Improving the Accuracy of Monocular Vision Pose Measurement System in a Robotic Manipulator. IEEE Transactions on Instrumentation and Measurement. 2026;75:1010113-1010113. doi:10.1109/tim.2026.3746819
BibTeX
@article{Li2026,
author = {Li, Yaru and Wang, Yunmei and Luo, Zai and Jiang, Wensong and Cheng, Yinbao and Tang, Yingqi},
title = {Enhanced Arithmetic Optimization Algorithm for Improving the Accuracy of Monocular Vision Pose Measurement System in a Robotic Manipulator},
journal = {IEEE Transactions on Instrumentation and Measurement},
year = {2026},
volume = {75},
pages = {1010113--1010113},
doi = {10.1109/tim.2026.3746819}
}
EUVIMED