Abstract
Target pose estimation is a key technology in the field of artificial intelligence. This paper focuses on the pose estimation method based on monocular vision. Firstly, a cooperative target composed of five circular patterns is designed to increase the measurement accuracy. To solve the shortcomings of traditional image processing algorithms, we add two constraints, area threshold and ellipse roundness, to achieve more accurate feature extraction and segmentation. Then, the least square method is used to fit ellipses, and an ellipse sorting method is designed. Combined with the established models, the pose estimation of the target can be realized via the PNP problem. A large number of experiments prove the effectiveness and feasibility of the proposed method. Experiments show that the mean error for the attitude angle and position are less than 0.4° and 0.5 mm respectively. In a word, this method has the advantages of simple process, reasonable cost and high precision, and can be applied to engineering practice.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Guo, Y., Zhao, D.: Optimization design of non-coplanar target for pose measurement with monocular vision system. Optik 131, 72–78 (2017)
Ma, Y., Zhao, R., Liu, E., Zhang, Z., Yan, K.: A novel autonomous aerial refueling drogue detection and pose estimation method based on monocular vision. Measurement 136, 132–142 (2019)
De Jongh, W.C., Jordaan, H.W., Van Daalen, C.E.: Experiment for pose estimation of uncooperative space debris using stereo vision. Acta Astronaut. 168, 164–173 (2020)
Yu, J., et al.: A discriminative deep model with feature fusion and temporal attention for human action recognition. IEEE Access 8, 43243–43255 (2020)
Xiong, J., Zhong, S.-d., Liu, Y., Tu, L.-f.: Automatic three-dimensional reconstruction based on four-view stereo vision using checkerboard pattern. J. Central South Univ. 24(5), 1063–1072 (2017)
Ma, Y., Li, Q., Xing, J., Huo, G., Liu, Y.: An intelligent object detection and measurement system based on trinocular vision. IEEE Trans. Circ. Syst. Video Technol. 30(3), 711–724 (2020)
Yin, Y., Altmann, B., Pape, C., Reithmeier, E.: Machine-vision-guided rotation axis alignment for an optomechanical derotator. Optics Lasers Eng. 121, 456–463 (2019)
Cui, J.-s., Huo, J., Yang, M., Wang, Y.-k.: Research on the rigid body posture measurement using monocular vision by coplanar feature points. Optik 126(24), 5423–5429 (2015)
Sharma, S., D׳Amico, S.: Comparative assessment of techniques for initial pose estimation using monocular vision. Acta Astronautica 123, 435–445 (2016)
Schlobohm, J., Pösch, A., Reithmeier, E., Rosenhahn, B.: Improving contour based pose estimation for fast 3D measurement of free form objects. Measurement 92, 79–82 (2016)
Zhang, S.N., Wang, B.S., Yuan, W.Q.: A method of determining the pose of planar target in vision detection system. Adv. Mater. Res. 659, 156–161 (2013)
Long, Q., Zhongdan, L.: Linear N-point camera pose determination. IEEE Trans. Pattern Analysis Mach. Intell. 21(8), 774–780 (1999)
Huang, B., Sun, Y., Zhu, Y., Xiong, Z., Liu, J.: Vision pose estimation from planar dual circles in a single image. Optik 127(10), 4275–4280 (2016)
Safaee-Rad, R., Tchoukanov, I., Smith, K.C., Benhabib, B.: Three-dimensional location estimation of circular features for machine vision. IEEE Trans. Robot. Autom. 8(5), 624–640 (1992)
Abid Hasan, S.M., Ko, K.: Depth edge detection by image-based smoothing and morphological operations. J. Comput. Des. Eng. 3(3), 191–197 (2016)
Arunkumar, P., Shantharajah, S.P., Geetha, M.: Improved canny detection algorithm for processing and segmenting text from the images. Cluster Comput. 22(3), 7015–7021 (2018). https://doi.org/10.1007/s10586-018-2056-8
Fitzgibbon, A., Pilu, M., Fisher, R.B.: Direct least square fitting of ellipses. IEEE Trans. Pattern Anal. Mach. Intell. 21(5), 476–480 (1999)
Liang, J., et al.: Robust ellipse fitting based on sparse combination of data points. IEEE Trans. Image Process. 22(6), 2207–2218 (2013)
Yu, J., Kulkarni, S.R., Poor, H.V.: Robust ellipse and spheroid fitting. Pattern Recogn. Lett. 33(5), 492–499 (2012)
Zhang, G., Jayas, D.S., White, N.D.G.: Separation of touching grain kernels in an image by ellipse fitting algorithm. Biosys. Eng. 92(2), 135–142 (2005)
Wu, W.-Y., Wang, M.-J.J.: Elliptical object detection by using its geometric properties. Pattern Recogn. 26(10), 1499–1509 (1993)
Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. Pattern Anal. Mach. Intell. 22(11), 1330–1334 (2000)
Choi, M., Oh, J.J., Choi, S.B.: Linearized recursive least squares methods for real-time identification of tire-road friction coefficient. IEEE Trans. Veh. Technol. 62(7), 2906–2918 (2013)
Ye, N., Yang, B., Zhou, H., Zhang, L.: A calibration trilogy of monocular-vision-based aircraft boresight system. Measurement 117, 133–143 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhou, Y., Gao, H., Sun, J., Jiang, Y. (2020). Pose Estimation for Planar Target Based on Monocular Visual Information. In: Qian, J., Liu, H., Cao, J., Zhou, D. (eds) Robotics and Rehabilitation Intelligence. ICRRI 2020. Communications in Computer and Information Science, vol 1335. Springer, Singapore. https://doi.org/10.1007/978-981-33-4929-2_8
Download citation
DOI: https://doi.org/10.1007/978-981-33-4929-2_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-4928-5
Online ISBN: 978-981-33-4929-2
eBook Packages: Computer ScienceComputer Science (R0)