浏览全部资源
扫码关注微信
广东工业大学 机电工程学院,广东 广州 510006
[ "刘跃生(1992-),男,广东揭阳人,博士研究生,2015年于广东技术师范大学获得学士学位,2019年于广东工业大学获得硕士学位,现为广东工业大学机电工程学院博士研究生,主要从事计算机视觉及机器人控制方面的研究。E-mail: 2249791454@qq.com" ]
[ "陈新度(1967-),男,湖南长沙人,教授,博士生导师,分别在1989年、1992年和1995年于华中理工大学获得学士学位、硕士学位和博士学位,现为广东工业大学的教授,主要研究方向为网络化制造、制造系统建模和仿真优化。E-mail:544394747@qq.com陈新度(1967-),男,湖南长沙人,教授,博士生导师,分别在1989年、1992年和1995年于华中理工大学获得学士学位、硕士学位和博士学位,现为广东工业大学的教授,主要研究方向为网络化制造、制造系统建模和仿真优化。E-mail:544394747@qq.com" ]
收稿日期:2021-03-23,
修回日期:2021-05-14,
纸质出版日期:2021-09-15
移动端阅览
刘跃生,陈新度,吴磊等.混合稀疏迭代最近点配准[J].光学精密工程,2021,29(09):2255-2267.
LIU Yue-sheng,CHEN Xin-du,WU Lei,et al.Sparse mixture iterative closest point registration[J].Optics and Precision Engineering,2021,29(09):2255-2267.
刘跃生,陈新度,吴磊等.混合稀疏迭代最近点配准[J].光学精密工程,2021,29(09):2255-2267. DOI: 10.37188/OPE.20212909.2255.
LIU Yue-sheng,CHEN Xin-du,WU Lei,et al.Sparse mixture iterative closest point registration[J].Optics and Precision Engineering,2021,29(09):2255-2267. DOI: 10.37188/OPE.20212909.2255.
为了避免离群值的影响,提出了混合稀疏迭代最近点(SM-ICP)方法,以实现点云精确配准。本文对稀疏表示、正则化求解和点云配准方法进行了研究。首先,利用混合正则项表示配准残差,构建混合稀疏配准函数。然后,结合交替乘子法(ADMM)构建了所提出函数的双循环优化框架。其中,混合正则项的平衡权重
<math id="M1"><mi>θ</mi></math>
http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=20936161&type=
http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=20936158&type=
1.52400005
2.37066650
可由Sigmoid函数求解;此外,还给出了ADMM优化框架内循环中对应损失函数的标量形式。最后,推导了该标量化损失函数在点云配准中的软阈值表达式。实验结果表明,所提出SM-ICP算法的配准精度优于所对比的算法。特别的,在重叠率约为50%的斯坦福兔子配准实验中,SM-ICP算法的截断配准误差为2.04×10
-4
,较Robust Trimmed-ICP(Tr-ICP)算法和ICP算法的配准误差减小了一个量级,且较稀疏ICP(S-ICP)算法减小了约三倍;在其它对象、场景类型的点云配准实验中,SM-ICP算法的配准精度同样较其它对比算法更优;在具有不同层级随机噪声点云的配准实验中,SM-ICP的截断配准误差为4.90×10
-
6
~1.33×10
-4
,同样较其它对比算法减小了一个量级或几倍;在发动机叶片配准实验中,本文方法成功实现了点云精确配准,而其它对比算法的配准结果中存在不同程度的点云错位情况。所提出的点云配准方法具有精确、鲁棒性和泛化性等优势。
The sparse mixture iterative closest point (SM-ICP) method is proposed for achieving accurate alignment of point-sets, while avoiding the influence of outliers. This study investigates sparse representation, non-convex optimization, and point-sets registration. First, the registered residuals are represented by mixed regularization to establish a sparse mixture formula. The alternating direction of multiplier method (ADMM) is then integrated to solve the proposed formula using a nested framework. Among the variables, the balance weight
θ
for mixed regularization can be calculated using a sigmoid function. The scalar version is also provided to represent the corresponding loss of function in the inner loop of ADMM. Finally, the soft threshold formula for the scalar version can be deduced in point-set registration. Experimental results indicate that the registration accuracy of the proposed SM-ICP method is better than the that of established algorithms investigated for comparison. This improved accuracy is especially striking in the registration experiment of the Stanford bunny dataset. With 50% overlap rate, the trimmed registration error of SM-ICP was 2.04×10
-
4
. Compared with other methods, our trimmed error was one order of magnitude lower than those of the robust Trimmed-ICP (robust Tr-ICP) and ICP algorithms. Moreover, it was approximately three times lower than the error obtained using the sparse ICP (S-ICP) algorithm. In the registration experiments for both other objects and for scene data, the registration accuracy of the SM-ICP method also performed better than comparable algorithms. In the registration experiment of point-sets with different levels of random noise, the trimmed registration error of SM-ICP was 4.90×10
-
6
~1.33×10
-
4
. This was several times to one order of magnitude lower than those of other algorithms. In the registration experiment for the engine blade, our method successfully achieved accurate registration of point-sets, but the results produced by comparable algorithms displayed different degrees of dislocation in their point-sets registration. In summary, the proposed SM-ICP algorithm displays advantages in accuracy, robustness, and generalization for point-set registration.
王宾 , 刘林 , 侯榆青 , 等 . 应用改进迭代最近点方法的三维心脏点云配准 [J]. 光学 精密工程 , 2020 , 28 ( 2 ): 474 - 484 .
WANG B , LIU L , HOU Y Q , et al . Three-dimensional cardiac point cloud registration by improved iterative closest point method [J]. Opt. Precision Eng. , 2020 , 28 ( 2 ): 474 - 484 . (in Chinese)
ZHEN X , SENG J C Y , SOMANI N . Adaptive Automatic Robot Tool Path Generation Based on Point Cloud Projection Algorithm [C]. 2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) , 2019 . doi: 10.1109/etfa.2019.8869301 http://dx.doi.org/10.1109/etfa.2019.8869301
王锐 , 王世峰 , 常锴 , 等 . 单线激光雷达与GNSS/INS的空间重构技术的研究 [J]. 光学 精密工程 , 2020 , 28 ( 4 ): 851 - 858 .
WANG R , WANG S F , CHANG K , et al . Space reconstruction using single-line LIDAR and GNSS/INS fused data [J]. Opt. Precision Eng. , 2020 , 28 ( 2 ): 851 - 858 . (in Chinese)
杨稳 , 周明全 , 耿国华 , 等 . 层次优化的颅骨点云配准 [J]. 光学 精密工程 , 2019 , 27 ( 12 ): 237 - 246 . doi: 10.3788/ope.20192712.2730 http://dx.doi.org/10.3788/ope.20192712.2730
YANG W , ZHOU M Q , GENG G H , et al . Hierarchical optimization of skull point cloud registration [J]. Opt. Precision Eng. , 2019 , 27 ( 12 ): 237 - 246 . doi: 10.3788/ope.20192712.2730 http://dx.doi.org/10.3788/ope.20192712.2730
BESL P J , MCKAY N D . A method for registration of 3-D shapes [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2002 , 14 ( 2 ): 239 - 256 .
BOUAZIZ S , TAGLIASACCHI A , PAULY M . Sparse iterative closest point [C]. Eleventh Eurographics/acmsiggraph Symposium on Geometry Processing , 2013 . doi: 10.1111/cgf.12178 http://dx.doi.org/10.1111/cgf.12178
CHETVERIKOV D , SVIRKO D , STEPANOV D , et al . The trimmed iterative closest point algorithm [J], 2002 , 16 ( 3 ): 545 - 548 . doi: 10.1109/icpr.2002.1047997 http://dx.doi.org/10.1109/icpr.2002.1047997
CHETVERIKOV D , STEPANOV D , KRSEK P . Robust euclidean alignment of 3D point sets: the trimmed iterative closest point algorithm [J]. Image & Vision Computing , 2005 , 23 ( 3 ): 299 - 309 . doi: 10.1016/j.imavis.2004.05.007 http://dx.doi.org/10.1016/j.imavis.2004.05.007
李宁 , 赵永强 , 潘泉 . 时空自适应的分焦平面偏振视频PCA去噪 [J]. 红外与激光工程 , 2019 , 48 ( 10 ): 270 - 276 . doi: 10.3788/irla201948.1026001 http://dx.doi.org/10.3788/irla201948.1026001
LI N , ZHAO Y Q , PAN Q . PCA-based spatial-temporal adaptive denoising of DoFp video for microgrid polarimeters [J]. Infrared and Laser Engineering , 2019 , 48 ( 10 ): 270 - 276 . doi: 10.3788/irla201948.1026001 http://dx.doi.org/10.3788/irla201948.1026001
陈华伟 , 袁小翠 , 吴禄慎 , 等 . 基于曲率突变分析的点云特征线自动提取 [J]. 光学 精密工程 , 2019 , 027 ( 005 ): 1218 - 1228 . doi: 10.3788/ope.20192705.1218 http://dx.doi.org/10.3788/ope.20192705.1218
CHEN H W , YUAN X C , WU L C , et al . Automatic point cloud feature-line extraction algorithm based on curvature-mutation analysis [J] . Opt. Precision Eng. , 2019 , 27 ( 5 ): 1218 - 1228 . doi: 10.3788/ope.20192705.1218 http://dx.doi.org/10.3788/ope.20192705.1218
GOJCIC Z , ZHOU C , WEGNER J D , et al . The Perfect Match: 3D point cloud matching with smoothed densities [C]. Computer Vision and Pattern Recognition , 2019 . doi: 10.1109/cvpr.2019.00569 http://dx.doi.org/10.1109/cvpr.2019.00569
AOKI Y , GOFORTH H , SRIVATSAN R A , et al . PointNetLK: Robust & Efficient Point Cloud Registration using PointNet [C]. Computer Vision and Pattern Recognition , 2019 . doi: 10.1109/cvpr.2019.00733 http://dx.doi.org/10.1109/cvpr.2019.00733
HUANG X , MEI G , ZHANG J . Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences [C]. Computer Vision and Pattern Recognition , 2020 . doi: 10.1109/cvpr42600.2020.01138 http://dx.doi.org/10.1109/cvpr42600.2020.01138
LI P , LI H Y , HUANG Y B , et al . Quasi-sparse response surface constructing accurately and robustly for efficient simulation based optimization [J]. Advances in Engineering Software , 2017 , 114 : 325 - 336 . doi: 10.1016/j.advengsoft.2017.07.014 http://dx.doi.org/10.1016/j.advengsoft.2017.07.014
LI P , HU S , LI H Y , et al . An improved quasi-sparse response surface model using the weighting method for low-dimensional simulation [J]. Applied Soft Computing , 2019 , 85 : 105883 . doi: 10.1016/j.asoc.2019.105883 http://dx.doi.org/10.1016/j.asoc.2019.105883
BOYD S , PARIKH N , CHU E , et al . Distributed optimization and statistical learning via the alternating direction method of multipliers [J]. Foundations & Trends® in Machine Learning , 2010 , 3 ( 1 ): 1 - 122 . doi: 10.1561/2200000016 http://dx.doi.org/10.1561/2200000016
LANGE K . The MM Algorithm [M]. 2013 . doi: 10.1007/978-1-4614-5838-8_8 http://dx.doi.org/10.1007/978-1-4614-5838-8_8
MARJANOVIC G , SOLO V . On Lq Optimization and Matrix Completion [J]. IEEE Transactions on Signal Processing , 2012 , 60 ( 11 ): 5714 - 5724 . doi: 10.1109/tsp.2012.2212015 http://dx.doi.org/10.1109/tsp.2012.2212015
AIGER D , MITRA N. J , COHEN-OR D . 4-points congruent sets for robust surface registration [J]. ACM TOG (SIG-GRAPH) , 2008 , 85 ( 3 ): 1 - 10 . doi: 10.1145/1360612.1360684 http://dx.doi.org/10.1145/1360612.1360684
NICOLAS M , NILOY , DROR A . SUPER 4PCS: Fast Global Point cloud Registration via Smart Indexing [J]. Computer Graphics Forum , 2014 , 33 ( 5 ): 205 - 215 . doi: 10.1111/cgf.12446 http://dx.doi.org/10.1111/cgf.12446
张临池 . 适应性移动最小二乘曲面的多视点云对齐方法 [D]. 华中科技大学 , 2012 . doi: 10.1016/j.proeng.2012.01.754 http://dx.doi.org/10.1016/j.proeng.2012.01.754
ZHANG L C . Adaptive Moving Least-Squares Surfaces For Multiple Point Clouds Registration [D]. Huazhong University of Science and Technology , 2012 . doi: 10.1016/j.proeng.2012.01.754 http://dx.doi.org/10.1016/j.proeng.2012.01.754
0
浏览量
511
下载量
10
CSCD
关联资源
相关文章
相关作者
相关机构