重庆理工大学 机械工程学院,重庆 400054
[ "余永维(1973-),男,重庆长寿人,博士,教授,1997年于武汉理工大学获得学士学位,2005年于重庆大学获得硕士学位,2014年于四川大学获得博士学位,主要从事机器视觉及智能控制等方面的研究。E-mail: weiyy@cqut.edu.cn" ]
[ "杜柳青(1975-),女,重庆长寿人,博士,教授,1996年于四川工业学院获得学士学位,2003年于重庆大学获得硕士学位,2016年于四川大学获得博士学位,主要从事微弱信号检测及先进制造技术等方面的研究。E-mail: lqdu@cqut.edu.cn" ]
收稿:2025-05-30,
修回:2025-07-10,
纸质出版:2025-10-10
移动端阅览
余永维,方荣,杜柳青等.三维点云的邻域分布快速配准[J].光学精密工程,2025,33(19):3106-3120.
YU Yongwei,FANG Rong,DU Liuqing,et al.Rapid registration for neighborhood distribution of 3D point cloud[J].Optics and Precision Engineering,2025,33(19):3106-3120.
余永维,方荣,杜柳青等.三维点云的邻域分布快速配准[J].光学精密工程,2025,33(19):3106-3120. DOI: 10.37188/OPE.20253319.3106. CSTR: 32169.14.OPE.20253319.3106.
YU Yongwei,FANG Rong,DU Liuqing,et al.Rapid registration for neighborhood distribution of 3D point cloud[J].Optics and Precision Engineering,2025,33(19):3106-3120. DOI: 10.37188/OPE.20253319.3106. CSTR: 32169.14.OPE.20253319.3106.
针对基于传统点云特征的粗-精两步配准算法存在高维特征计算复杂耗时、稠密点云配准速度慢等问题,提出一种三维点云的邻域分布快速配准方法。首先,定义邻域点的三种深层次几何特征,提出低维度多尺度邻域分布特征描述,以大幅降低特征计算复杂度,同时提高特征描述的区分度,实现点云局部特性的高效表征。然后,提出基于邻域分布特征的快速粗配准方法,根据点云整体起伏程度与邻域分布方向提取特征点,依据邻域分布特征描述建立特征点初步匹配的条件,并改进点对间欧氏距离约束条件以剔除错误匹配点对,实现高效准确粗配准。最后,为解决稠密点云配准速度慢问题,提出通过
k
维树及体素化网格法改进迭代最近点(Iterative Closest Point,ICP)算法,并采用二次精配准策略修正降采样引起的配准误差,进一步提高精配准的准确性和效率。斯坦福模型实验和实际工业零件点云配准实验均表明,本文方法相较基于现有传统特征描述的配准方法而言,配准精度提升了22%以上,耗时降低了43%以上,证明本方法能够快速有效配准不同视角物体表面点云,具有较好的稳定性和适用性。
A fast point-cloud registration method based on neighborhood distribution features is proposed to address the high computational cost of traditional high-dimensional feature extraction and the slow performance of dense registration algorithms that rely on coarse-fine two-step feature matching. First, three deep geometric features of neighboring points are defined, and a low-dimensional, multi-scale neighborhood distribution descriptor is introduced to substantially reduce feature-computation complexity while enhancing descriptor discriminability for efficient characterization of local point-cloud properties. Second, a rapid coarse-registration scheme is developed using the neighborhood distribution descriptor: feature points are selected according to the global undulation degree and neighborhood distribution direction; initial correspondences are established based on the neighborhood distribution descriptor; and Euclidean-distance constraints between point pairs are strengthened to remove incorrect matches, enabling efficient and accurate coarse alignment. Finally, to accelerate dense registration, the iterative closest point (ICP) algorithm is improved using a k-dimensional tree and voxel-grid downsampling, and a quadratic fine-registration strategy is employed to correct downsampling-induced errors, thereby further improving fine-registration accuracy and efficiency. Experiments on Stanford models and industrial part point clouds demonstrate that, compared with conventional feature-descriptor-based methods, the proposed approach increases registration accuracy by over 22% and reduces computation time by more than 43%, confirming its effectiveness, robustness, and practical applicability for rapid registration of object-surface point clouds acquired from different viewpoints.
XIA J Y , LI B W , XU ZH Q , et al . Point cloud registration method based on improved TLBO for landing gear components measurement [J]. Symmetry , 2024 , 16 ( 11 ): 1506 . doi: 10.3390/sym16111506 http://dx.doi.org/10.3390/sym16111506
AIJAZI A K , CHECCHIN P . Non-repetitive scanning LiDAR sensor for robust 3D point cloud registration in localization and mapping applications [J]. Sensors , 2024 , 24 ( 2 ): 378 . doi: 10.3390/s24020378 http://dx.doi.org/10.3390/s24020378
WANG Y , ZHOU P B , GENG G H , et al . Enhancing point cloud registration with transformer: cultural heritage protection of the Terracotta Warriors [J]. Heritage Science , 2024 , 12 : 314 . doi: 10.1186/s40494-024-01425-9 http://dx.doi.org/10.1186/s40494-024-01425-9
姚敏 , 赵增浩 , 赵敏 , 等 . 复杂结构件内部缺陷检测 [J]. 仪器仪表学报 , 2020 , 41 ( 10 ): 213 - 220 .
YAO M , ZHAO Z H , ZHAO M , et al . Internal defect detection of complex structural parts [J]. Chinese Journal of Scientific Instrument , 2020 , 41 ( 10 ): 213 - 220 . (in Chinese)
GUO F , ZHENG W B , LIAN G F , et al . A point cloud registration method based on multiple-local-feature matching [J]. Optik , 2023 , 295 : 171511 . doi: 10.1016/j.ijleo.2023.171511 http://dx.doi.org/10.1016/j.ijleo.2023.171511
WEI K , DAI Y , REN B Y . Automatic identification and autonomous sorting of cylindrical parts in cluttered scene based on monocular vision 3D reconstruction [J]. Sensor Review , 2019 , 39 ( 6 ): 763 - 775 . doi: 10.1108/sr-01-2019-0033 http://dx.doi.org/10.1108/sr-01-2019-0033
XU G X , PANG Y J , BAI ZH X , et al . A fast point clouds registration algorithm for laser scanners [J]. Applied Sciences , 2021 , 11 ( 8 ): 3426 . doi: 10.3390/app11083426 http://dx.doi.org/10.3390/app11083426
HUANG SH J , WU SH SH , CHEN L , et al . A 3D local feature description algorithm based on point distribution [J]. Computers and Electrical Engineering , 2024 , 118 : 109341 . doi: 10.1016/j.compeleceng.2024.109341 http://dx.doi.org/10.1016/j.compeleceng.2024.109341
ZHAO L D , XIANG ZH F , CHEN M L , et al . Establishment and extension of a fast descriptor for point cloud registration [J]. Remote Sensing , 2022 , 14 ( 17 ): 4346 . doi: 10.3390/rs14174346 http://dx.doi.org/10.3390/rs14174346
林森 , 张强 . 应用邻域点信息描述与匹配的点云配准 [J]. 光学 精密工程 , 2022 , 30 ( 8 ): 984 - 997 . doi: 10.37188/OPE.20223008.0984 http://dx.doi.org/10.37188/OPE.20223008.0984
LIN S , ZHANG Q . Point cloud registration using neighborhood point information description and matching [J]. Opt. Precision Eng. , 2022 , 30 ( 8 ): 984 - 997 . (in Chinese) . doi: 10.37188/OPE.20223008.0984 http://dx.doi.org/10.37188/OPE.20223008.0984
陈慧娴 , 吴一全 , 张耀 . 基于深度学习的三维点云分析方法研究进展 [J]. 仪器仪表学报 , 2023 , 44 ( 11 ): 130 - 158 .
CHEN H X , WU Y Q , ZHANG Y . Research progress of 3D point cloud analysis methods based on deep learning [J]. Chinese Journal of Scientific Instrument , 2023 , 44 ( 11 ): 130 - 158 . (in Chinese)
司垒 , 王忠宾 , 李嘉豪 , 等 . 基于图像和激光点云融合的智能采面煤岩识别 [J]. 振动 测试与诊断 , 2023 , 43 ( 2 ): 254 - 262, 407 .
SI L , WANG ZH B , LI J H , et al . Coal-rock recognition of intelligent mining face based on the fusion of image and laser point cloud [J]. Journal of Vibration , Measurement & Diagnosis, 2023 , 43 ( 2 ): 254 - 262, 407 . (in Chinese)
陈仲生 , 李潮林 , 左旺 , 等 . 双重下采样增强的点云改进配准算法研究 [J]. 汽车工程 , 2023 , 45 ( 4 ): 572 - 578 .
CHEN ZH SH , LI CH L , ZUO W , et al . Study on improved point cloud registration algorithm enhanced by double down-sampling [J]. Automotive Engineering , 2023 , 45 ( 4 ): 572 - 578 . (in Chinese)
郑源 , 高峰 , 范嘉博 , 等 . 基于配准与参数迭代优化的叶片面轮廓度评定方法研究 [J]. 计算机集成制造系统 , 2025 , 31 ( 7 ): 2456 - 2465 .
ZHENG Y , GAO F , FAN J B , et al . Evaluation method of blade surface profile based on registration and parameter iterative optimization [J]. Computer Integrated Manufacturing Systems , 2025 , 31 ( 7 ): 2456 - 2465 . (in Chinese)
李建微 , 占家旺 . 三维点云配准方法研究进展 [J]. 中国图象图形学报 , 2022 , 27 ( 2 ): 349 - 367 . doi: 10.11834/jig.210243 http://dx.doi.org/10.11834/jig.210243
LI J W , ZHAN J W . Review on 3D point cloud registration method [J]. Journal of Image and Graphics , 2022 , 27 ( 2 ): 349 - 367 . (in Chinese) . doi: 10.11834/jig.210243 http://dx.doi.org/10.11834/jig.210243
ZHAO F Q , HUANG H , HU W X . An optimized hierarchical point cloud registration algorithm [J]. Multimedia Systems , 2024 , 31 ( 1 ): 14 . doi: 10.1007/s00530-024-01563-x http://dx.doi.org/10.1007/s00530-024-01563-x
XIONG F G , DONG B , HUO W , et al . A local feature descriptor based on rotational volume for pairwise registration of point clouds [J]. IEEE Access , 2020 , 8 : 100120 - 100134 . doi: 10.1109/access.2020.2995369 http://dx.doi.org/10.1109/access.2020.2995369
YANG J Q , ZHANG Q , XIAO Y , et al . TOLDI: an effective and robust approach for 3D local shape description [J]. Pattern Recognition , 2017 , 65 : 175 - 187 . doi: 10.1016/j.patcog.2016.11.019 http://dx.doi.org/10.1016/j.patcog.2016.11.019
方斌 , 丁军峰 , 马杰 , 等 . 三维局部描述子综述 [J]. 华中科技大学学报(自然科学版) , 2022 , 50 ( 11 ): 1 - 15 .
FANG B , DING J F , MA J , et al . 3D local descriptors: a review [J]. Journal of Huazhong University of Science and Technology (Natural Science Edition) , 2022 , 50 ( 11 ): 1 - 15 . (in Chinese)
HUANG Y , DA F P . Registration algorithm for point cloud based on normalized cross-correlation [J]. IEEE Access , 2019 , 7 : 137136 - 137146 . doi: 10.1109/access.2019.2942127 http://dx.doi.org/10.1109/access.2019.2942127
韩宏琪 , 江自真 , 周俊 , 等 . 基于法向量夹角的果树点云配准与枝叶分割方法研究 [J]. 农业机械学报 , 2024 , 55 ( 9 ): 327 - 336 .
HAN H Q , JIANG Z ZH , ZHOU J , et al . Fruit tree point cloud registration based on normal vector angles and branch-leaf segmentation method [J]. Transactions of the Chinese Society for Agricultural Machinery , 2024 , 55 ( 9 ): 327 - 336 . (in Chinese)
0
浏览量
3
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
