Abstract
The movement of workers in intelligent assisted assembly scenarios can cause model shaking, as well as issues such as obstruction, severe tilting, and scale changes of landmarks, which can lead to failed tracking of landmarks. Based on this, a high-precision and fast detection and tracking method is proposed. Firstly, the framework of the marker detection and tracking algorithm was established, and its working principle and process were explained; Secondly, coordinates are provided for subsequent algorithms through marker detection calculations; Then, the pyramid optical flow algorithm in the visual odometer is added to process the coordinates, and a tracking effect is added to the landmark coordinates to combat the problems caused by worker movement; Finally, when using the processed coordinates for pose solving, a nonlinear optimization matrix that combines the two-step degree method and Gaussian Newton method is added to enhance the algorithm’s anti-interference ability. The simulation experiment results show that the marker detection and tracking algorithm runs quickly, with guaranteed tracking accuracy and efficiency. It can effectively solve related problems such as image jitter, occlusion, and scale changes, and effectively reduce the impact of lighting. The design has achieved the expected results.
This Work Was Supported By the Shanghai Science and Technology Commission Science and Technology Plan Project: 21010501000
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Nistér, D., Naroditsky, O., Bergen, J.: Visual odometry. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2004. CVPR 2004. IEEE, 1, I-I (2004)
Davison, A.J., Reid, I.D., Molton, N.D., et al.: MonoSLAM: real-time single camera SLAM. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 1052–1067 (2007)
Kitt, B.M., Rehder, J., Chambers, A.D., et al.: Monocular visual odometry using a planar road model to solve scale ambiguity. two thousand and eleven
Chien, H.J., Chuang, C.C., Chen, C.Y., et al.: When to use what feature? SIFT,SURF,ORB,or A-KAZE features for monocular visual odometry. In: 2016 International Conference on Image and Vision Computing New Zealand (IVCNZ). IEEE, pp. 1–6 (2016)
Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Trans. Rob. 31(5), 1147–1163 (2015)
Mur-Artal, R., Tardós, J.D.: Orb-slam2: an open-source slam system for monocular, stereo, and rgb-d cameras. IEEE Trans. Rob. 33(5), 1255–1262 (2017)
Naixin, Q., Xiaogang, Y., Xiaofeng, L., et al.: A visual mileage calculation method based on ORB fFeatures and LK optical flow. J. Instrum. 39(12), 216–227 (2018)
Jianjun, T., Bo, Y., Junhao, G.: Exploration and Practice of AR Intelligent guidance technology for aircraft assembly operations. Aviation Manufact. Technol. 62(8), 22–27 (2019)
WESTERFIELD G,MITROVIC A,BILLINGHURST M.: Intelligent Augmented Reality Training for Motherboard Assembly. Int. J. Artif. Intell. Educ. 25, 57–172 (2015)
Ran, L.: Research on pose estimation andstate detection methods for matrix components in AR assisted assembly [D]. Shanghai Jiao Tong University, Shanghai (2018)
Sun, J., Song, F., Ji, L.:https://ieeexplore.ieee.org/document/10046501/ “ VINS-Mask: A ROI-mask Feature Tracker for Monocular Visual-inertial System[J]. HYPERLINK “ ROI-mask Feature Tracker for Monocular Visual-inertial System[J].2022 International Conference on Automation, Robotics and Computer Engineering (ICARCE).IEEE,2022:1–3
Harris, C.G., Stephens, M.J.: A combined corner and edge detector. Alvey vision conference (1988)
Jiu, Y., Yangping, W., Jianwu, P., et al.: Improving the AR system long-term tracking registration method for TLD and ORB. Comput. Eng. Appl. 57(7), 181 (2021)
Cvi š i ć I, Ć esi ć J,Markovi ć I,et al.: SOFT-SLAM: computationally efficient stereo visual simultaneous localization and mapping for autonomous unmanned aerial vehicles. J. Field Robot. 35(4), 578–595 (2018)
Persson, M., Piccini, T., Felsberg, M., et al.: Robust stereo visual odometry from monocular techniques. In: 2015 IEEE Intelligent Vehicles Symposium (IV). IEEE, 2015 686–691 (2015)
Zhang, L., Curless, B., Seitz, S.M.: Rapid shape acquisition using color structured light and multi-pass dynamic programming. In: International Symposium on 3D Data Processing Visualization and Transmission Proceedings, pp. 24–36 (2002)
Hsieh C K,Lai S H,Chen Y C,2D expression-invariant face recognition with constrained optical flow [C]∥2009 IEEE International Conference on Multimedia and Expo,June 28-July 3 2009,New York,NY,USA,New York: IEEE Press,2009;1058–1061
Ping, H., Zhen, C., Huan, W.: Binocular visual odometer based on circular feature matching. J. Opt. 41(15), 3–4 (2021)
Wang, J.: Research on monocular vision odometer based on improved feature method [D]. China University of Mining and Technology (2021)
Yuren, H., Tiejun, L., Dong, Y.: Overview of three bit tracking and registration technology in augmented reality. Comput. Eng. Appl. 55(21), 28–29 (2019)
Tao, W., Ling, H.: Gracker: a graph-based planar object tracker. IEEE Trans Pattern Anal. Mach. Intell. 40(6), 1494–1501 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Wang, S., Li, M. (2024). Design of Image Based Optical Flow Tracking and Positioning System in Intelligent Assembly. In: Li, J., Zhang, B., Ying, Y. (eds) 6GN for Future Wireless Networks. 6GN 2023. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 554. Springer, Cham. https://doi.org/10.1007/978-3-031-53404-1_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-53404-1_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53403-4
Online ISBN: 978-3-031-53404-1
eBook Packages: Computer ScienceComputer Science (R0)