基于迭代最近点的三维点云配准改进算法研究
Research on Improved 3D Point Cloud Registration Algorithm Based on Iterative Nearest Point
DOI: 10.12677/CSA.2022.124105, PDF,    科研立项经费支持
作者: 王海萍：台州科技职业学院，浙江 台州
关键词: 三维点云；迭代最近点；配准；3D扫描；飞行时间技术；3D Point Cloud； Iterative Closest Point； Registration； 3D Scanning； Time-of-Flight Technology
摘要: 本文研究了一种适用于旋转盘3D扫描系统的三维点云快速准确配准的算法问题，利用飞行时间技术提高原始三维点云数据采集精度，减少源头数据误差引入，通过辅助的参照物多图扫描获取旋转轴信息及其转换矩阵，为目标物体的三维点云粗配准提供较好的初始信息，继而实现高精度、快速的目标物体的点云精配准，为高精度的增材制造过程提供算法支撑。
Abstract: This paper studies an improved iterative closest point (ICP) algorithm of fast and accurate registration of 3D point cloud for the rotating disk 3D scanning system. The author first adopts the time-of-flight technology to improve the acquisition accuracy of original 3D point cloud data sampling, reducing the introduction of source data errors. Then, she uses an auxiliary reference object to scan multiple images, and obtain the rotation axis information and its transformation matrix, in order to provide better initial information for the rough registration of the 3D point cloud of the target object. Finally, the high-precision and fast point cloud registration of the target object is achievable, which makes a high-precision additive manufacturing process available.
文章引用：王海萍. 基于迭代最近点的三维点云配准改进算法研究[J]. 计算机科学与应用, 2022, 12(4): 1023-1030. https://doi.org/10.12677/CSA.2022.124105

参考文献

[1] 张衡, 杨可. 增材制造的现状与应用综述[J]. 包装工程, 2021, 42(16): 9-15.
[2] 郭照灿, 张德海, 何文斌, 杨光露, 李军恒, 付亮. 金属多材料增材制造研究现状与展望[J]. 精密成形工程, 2022(2): 129-137.
[3] 童晶. 基于深度相机的三维物体与人体扫描重建[D]: [博士学位论文]. 杭州: 浙江大学, 2012.
[4] Yang, H. and Carlone, L. (2019) A Polynomial-Time Solution for Robust Registration with Extreme Outlier Rates. Robotics: Science and System, Breisgau, 22-26 June 2019, 1-10. [Google Scholar] [CrossRef] 
[5] Le, H.M., Do, T.-T., Hoang, T. and Cheung, N.-M. (2019) SDRSAC: Semi-Definite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, 15-20 June 2019, 124-133. [Google Scholar] [CrossRef] 
[6] Pomerleau, F., Colas, F., Siegwart, R., et al. (2015) A Review of Point Cloud Registration Algorithms for Mobile Robotics. Foundations and Trends in Robotics, 4, 1-104. [Google Scholar] [CrossRef] 
[7] Cheng, L., Chen, S., Liu, X.Q., Xu, H., Wu, Y., Li, M.C. and Chen, Y.M. (2018) Registration of Laser Scanning Point Clouds: A Review. Sensors, 18, 1641. [Google Scholar] [CrossRef] [PubMed]
[8] Zeng, A., Song, S.R., Nießner, M., Fisher, M., Xiao, J.X. and Funkhouser, T. (2017) 3dmatch: Learning Local Geometric Descriptors from RGB-D Reconstructions. Proceedings of the IEEE Con-ference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 1802-1811. [Google Scholar] [CrossRef] 
[9] Deng, H.W., Birdal, T. and Ilic, S. (2018) Ppfnet: Global Context Aware Local Features for Robust 3D Point Matching. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 195-205. [Google Scholar] [CrossRef] 
[10] Gojcic, Z., Zhou, C.F., Wegner, J.D. and Wieser, A. (2019) The Perfect Match: 3D Point Cloud Matching with Smoothed Densities. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, 15-20 June 2019, 5545-5554. [Google Scholar] [CrossRef] 
[11] Peng, F.R., Wu, Q., Fan, L.X., Zhang, J., You, Y., Lu, J.F. and Yang, J.-Y. (2014) Street View Cross-Sourced Point Cloud Matching and Registration. 2014 IEEE International Con-ference on Image Processing (ICIP), Paris, 27-30 October 2014, 2026-2030. [Google Scholar] [CrossRef] 
[12] Huang, X.S., Zhang, J., Fan, L.X., Wu, Q. and Yuan, C. (2017) A Systematic Approach for Cross-Source Point Cloud Registration by Preserving Macro and Micro Structures. IEEE Transactions on Image Processing, 26, 3261-3276. [Google Scholar] [CrossRef] 
[13] Huang, X.S., Mei, G.F. and Zhang, J. (2020) Feature-Metric Reg-istration: A Fast Semi-Supervised Approach for Robust Point Cloud Registration without Correspondences. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, 14-19 June 2020, 11366-11374. [Google Scholar] [CrossRef] 
[14] Huang, X.S., Zhang, J., Wu, Q., Fan, L.X. and Yuan, C. (2016) A Coarse-to-Fine Algorithm for Registration in 3D Street-View Cross-Source Point Clouds. 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Gold Coast, 30 November-2 December 2016, 1-6. [Google Scholar] [CrossRef] 
[15] Huang, X.S., Zhang, J., Wu, Q., Fan, L.X. and Yuan, C. (2017) A Coarse-to-Fine Algorithm for Matching and Registration in 3D Crosssource Point Clouds. IEEE Transactions on Circuits and Systems for Video Technology, 28, 2965-2977. [Google Scholar] [CrossRef] 
[16] Huang, X.S., Fan, L.X., Wu, Q., Zhang, J. and Yuan, C. (2019) Fast Registration for Cross-Source Point Clouds by Using Weak Regional Affinity and Pixel-Wise Refinement. IEEE International Conference on Multimedia and Expo (ICME), Shanghai, 8-12 July 2019, 1552-1557. [Google Scholar] [CrossRef]