Abstract
The six-dimensional (6D) pose estimation of metal parts is a key technology for robotic grasping in intelligent manufacturing. However, current methods matching edge or geometric features suffer from unstable feature extraction results, which result in low robustness and unsatisfactory accuracy. In this paper, we propose a 6D pose estimation method based on semantic-level line matching. The proposed method uses a line detection network to replace the low-level feature extraction methods and fetch semantic-level line features. After filtered by a segmentation network, the features are utilized to generate object-level line descriptors for representing metal parts. The 2D-3D correspondences are achieved by matching descriptors in a sparse template set. Finally, 6D pose estimation of metal parts is completed by solving the PnP problem. Experimental results show that the proposed method achieves higher accuracy compared with existing methods on the Mono-6D dataset.
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
Du, G., Wang, K., Lian, S., Zhao, K.: Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: A review. Artif. Intell. Rev. 54(3), 1677–1734 (2021). https://doi.org/10.1007/s10462-020-09888-5
Zhang, H., Cao, Q.: Detect in RGB, optimize in edge: Accurate 6D pose estimation for texture-less industrial parts. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 3486–3492. IEEE (2019). https://doi.org/10.1109/ICRA.2019.8794330
Zhang, X., Jiang, Z., Zhang, H.: Real-time 6d pose estimation from a single RGB image. Image Vis. Comput. 89, 1–11 (2019). https://doi.org/10.1016/j.imavis.2019.06.013
Chan, J., Addison Lee, J., Kemao, Q.: BORDER: an oriented rectangles approach to texture-less object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2855–2863 (2016). https://doi.org/10.1109/CVPR.2016.312
Tombari, F., Franchi, A., Di Stefano, L.: BOLD features to detect texture-less objects. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1265–1272. IEEE, Sydney, Australia (2013). https://doi.org/10.1109/ICCV.2013.160
Liu, M.Y., Tuzel, O., Veeraraghavan, A., Taguchi, Y., Marks, T.K., Chellappa, R.: Fast object localization and pose estimation in heavy clutter for robotic bin picking. Int. J. Robot. Res. 31(8), 951–973 (2012). https://doi.org/10.1177/0278364911436018
Imperoli, M., Pretto, A.: D\(^{2}\)CO: fast and robust registration of 3D textureless objects using the directional chamfer distance. In: Nalpantidis, L., Krüger, V., Eklundh, J.-O., Gasteratos, A. (eds.) ICVS 2015. LNCS, vol. 9163, pp. 316–328. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-20904-3_29
Wang, Y., Wang, X., Chen, Y.: Multi-surface hydraulic valve block technique hole plug inspection from monocular image. Meas. Sci. Technol. 32(11), 115016 (2021). https://doi.org/10.1088/1361-6501/ac1460
He, Z., Wuxi, F., Zhao, X., Zhang, S., Tan, J.: 6D pose measurement of metal parts based on virtual geometric feature point matching. Meas. Sci. Technol. 32(12), 125210 (2021). https://doi.org/10.1088/1361-6501/ac2a85
He, Z., Jiang, Z., Zhao, X., Zhang, S., Wu, C.: Sparse template-based 6-d pose estimation of metal parts using a monocular camera. IEEE Trans. Industr. Electron. 67(1), 390–401 (2019). https://doi.org/10.1109/TIE.2019.2897539
Yang, X., Li, K., Fan, X., Zhang, H., Cao, H.: A multi-stage 6D object pose estimation method of texture-less objects based on sparse line features. In: 2022 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), pp. 0221–0225 (2022). https://doi.org/10.1109/IEEM55944.2022.9989794
Zhou, Y., Qi, H., Ma, Y.: End-to-end wireframe parsing. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 962–971 (2019). https://doi.org/10.1109/ICCV.2019.00105
Von Gioi, R., Jakubowicz, J., Morel, J.M., Randall, G.: LSD: a fast line segment detector with a false detection control. IEEE Trans. Pattern Anal. Mach. Intell. 32(4), 722–732 (2008). https://doi.org/10.1109/TPAMI.2008.300
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Ulrich, M., Wiedemann, C., Steger, C.: Combining scale-space and similarity-based aspect graphs for fast 3d object recognition. IEEE Trans. Pattern Anal. Mach. Intell. 34(10), 1902–1914 (2012). https://doi.org/10.1109/TPAMI.2011.266
Konishi, Y., Hanzawa, Y., Kawade, M., Hashimoto, M.: Fast 6D pose estimation from a monocular image using hierarchical pose trees. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 398–413. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_24
Hinterstoisser, S., et al.: Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7724, pp. 548–562. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-37331-2_42
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, Z., Wu, Z., Pu, B., Tang, J., Wang, X. (2023). 6D Pose Estimation Method of Metal Parts for Robotic Grasping Based on Semantic-Level Line Matching. In: Yang, H., et al. Intelligent Robotics and Applications. ICIRA 2023. Lecture Notes in Computer Science(), vol 14273. Springer, Singapore. https://doi.org/10.1007/978-981-99-6498-7_1
Download citation
DOI: https://doi.org/10.1007/978-981-99-6498-7_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6497-0
Online ISBN: 978-981-99-6498-7
eBook Packages: Computer ScienceComputer Science (R0)