浏览全部资源
扫码关注微信
1.福州大学 物理与信息工程学院, 福建 福州 350116
2.泉州黎明职业大学 智能制造工程学院, 福建 泉州 362000
3.数字电视智能化技术国家地方联合工程研究中心, 福建 福州 350116
[ "郑思凡(1975-),男,福建仙游人,博士研究生,2008年于华侨大学获得硕士学位,现为黎明职业大学智能制造工程学院实验师,主要从事机器视觉故障诊断,经编机贾卡嵌入式系统与写花工艺图形软件开发。 E-mail: zhengsf@lmu.edu.cn" ]
[ "陈平平(1985-),福州大学物理与信息工程学院教授,博导,2012年于厦门大学获得博士学位,2013~2015香港中文大学博士后,2016~2017新加坡科技技术大学博士后,2019年广东省科技进步二等奖,主要研究方向为人工智能,计算机通信以及wifi通信。E-mail: ppchen.xm@gmail.com" ]
收稿日期:2020-08-20,
修回日期:2020-10-17,
纸质出版日期:2021-05-15
移动端阅览
郑思凡,陈平平,苏凯雄等.泛函回归代理及条件期望配准的机械摆动测量[J].光学精密工程,2021,29(05):1154-1168.
ZHENG Si-fan,CHEN Ping-ping,SU Kai-xiong,et al.Mechanical swing measurement based on functional regression surrogate and conditional expectation registration[J].Optics and Precision Engineering,2021,29(05):1154-1168.
郑思凡,陈平平,苏凯雄等.泛函回归代理及条件期望配准的机械摆动测量[J].光学精密工程,2021,29(05):1154-1168. DOI: 10.37188/OPE.20212905.1154.
ZHENG Si-fan,CHEN Ping-ping,SU Kai-xiong,et al.Mechanical swing measurement based on functional regression surrogate and conditional expectation registration[J].Optics and Precision Engineering,2021,29(05):1154-1168. DOI: 10.37188/OPE.20212905.1154.
在机械摆动的运动分割及视觉测量中,针对传统以块状轨迹群为单位的谱聚类运动分割因摆杆光流轨迹中断及线速度分布差异所导致的碎片化与过分割的局限性,提出一种以曲率为相似度度量的弧状轨迹群为单位的谱聚类分割算法,并结合点云配准完成转速图像测量。算法先用活动子集的稀疏高斯回归学习出弧状轨迹群的平均轨迹,将此平均轨迹作为稀疏子空间聚类的种子样本一次性完成运动分割,最后将非种子样本重新归入其被代理的种子样本聚类中以获得每帧最大稠密度的分割点云。在各帧点云基础上,通过条件期望点云配准算法求取帧间点云变换矩阵,并提取转动分量完成摆杆摆角测量。为证明有效性,结合客运车辆日次安全检测视觉自动化系统项目,以6种不同照度下5种车型的双摇杆刮水器总成为对象,比较了三种算法对摆角的测量精度。结果表明:本算法能完整学习出等长轨迹,且与人为标定角位移回归值误差均方值小于10%,同时运算量小于传统的交替方向乘子法(ADMM)单次迭代,可作为工业智能制造与自动控制系统中的机械视觉运动测量及机械视觉故障诊断方面应用。
The process of motion segmentation and measurement of mechanical swing based on traditional block shape optical flow trajectory group clustering exhibits limitations in terms of over-segmentation and fragmentation due to the partial occlusion, interruption, and uneven velocity distribution of the optical flow trajectory. To overcome these limitations, we herein propose an arc-shaped trajectory clustering algorithm that uses curvature as a similarity metric and combines it with point cloud registration to perform mechanical swing measurement. The algorithm first performs sparse Gaussian regression of the active subset to learn the average trajectory of the arc-shaped trajectory group. Subsequently, the average trajectory is used as the seed sample of the sparse subspace clustering to complete the motion segmentation at one time. Finally, the non-seed sample is reclassified into its surrogate seed sample cluster to obtain the point set of each frame. Through conditional expectation point cloud registration, the rotation component is extracted to complete the swing angle measurement. The proposed algorithm is used for a vehicle windshield wiper under the four-link wiper assembly model and six different environment illuminances, as part of a visual automation system project targeting the daily safety inspection of passenger station vehicles, and compared with other algorithms. The experimental results show that the proposed algorithm can fully learn the blocked trajectory, and the mean square error with an artificially calibrated value is less than 10%. Furthermore, the computational complexity is only equivalent to that in the case of a single iteration of the alternating direction method of multipliers (ADMMs), Therefore, the proposed algorithm can be used for mechanical vision motion measurement in industrial intelligent manufacturing and automatic control systems.
于海莲 , 滕强 , 李正伟 . 基于干涉原理的机床摆动式回转轴位置精度测量 [J]. 机床与液压 , 2019 , 47 ( 14 ): 167 - 172 .
YU H L , TENG Q , LI ZH W . Measurement method for non-orthogonal rotary axes positioning error of machine tool based on laser interferometry [J]. Machine Tool& Hydraulics , 2019 , 47 ( 14 ): 167 - 172 . (in Chinese)
杨明 , 余菲 , 王继鹏 . 摆动喷管摆角测量系统设计 [J]. 自动化技术与应用 , 2018 , 37 ( 5 ): 145 - 148 .
YANG M , YU F , WANG J P . Design of a swing angle measurement system of nozzle [J]. Techniques of Automation & Applications , 2018 , 37 ( 5 ): 145 - 148 . (in Chinese)
谢为金 , 王惠民 , 张诗清 , 等 . 一种利用角度传感器测量吊钩摆动角的方法 [J]. 建筑机械 , 2013 ,( 17 ): 71 - 74 .
XIE W J , WANG H M , ZHANG SH Q , et al . A method of using the angle sensor for measuring hook swing angle [J]. Construction Machinery , 2013 ,( 17 ): 71 - 74 . (in Chinese)
吴斌 , 王航 , 康杰虎 . 小型精密谐波转台角度定位精度标定与补偿 [J]. 光学 精密工程 , 2019 , 27 ( 10 ): 2207 - 2214 .
WU B , WANG H , KANG J H . Calibration and compensation of small precision harmonic turntable [J]. Opt. Precision Eng. , 2019 , 27 ( 10 ): 2207 - 2214 . (in Chinese)
64Mp ultra-high resolution image sensor with Tetracell technology [OL]. available:https://www.samsung.com , March 3, 2020 .
郭学梅 , 刘阳 , 何醇 , 等 . 基于MIAS3D系统的驾驶动作三维运动参数测量 [J]. 数字技术与应用 , 2010 ( 9 ): 158 - 160 .
GUO X M , L Y , H CH , et al . Measurement of three- dimensional motion parameters of driving action based on mias3d system [J]. Digital Technology Application , 2010 , 2010 ( 9 ): 158 - 160 (in Chinese)
尹芳 , 吴云 . 空间非合作旋转目标的模型重建与位姿优化 [J]. 光学 精密工程 , 2019 , 27 ( 8 ): 1854 - 1862 .
YIN F , WU Y . Model reconstruction and pose optimization of non-cooperative rotating space target [J]. Opt. Precision Eng. , 2019 , 27 ( 8 ): 1854 - 1862 . (in Chinese)
HE M , ZHU C , Huang Q , et al . A review of monocular visual odometry [J]. The Visual Computer , 2020 , 36 ( 5 ): 1053 - 1065 .
LI Y , USHIKU Y , HARADA T . Pose graph optimization for unsupervised monocular visual odometry [C]. 2019 International Conference on Robotics and Automation (ICRA) , Montreal, QC, Canada , 2019 , pp. 5439 - 5445
CHEN W L , HOU R B , ALLAM M . Optimization of position and pose estimation by using Epipolar line segmentation optimization BA algorithm [C]. Proceedings of the 2019 4th International Conference on Robotics , Control and Automation (ICRCA 2019). New York, NY, USA , 21 - 26 .
OCHS P , MALIK J , BROX T . Segmentation of moving objects by long term video analysis [J]. IEEE transactions on pattern analysis and machine intelligence , 2014 , 36 ( 6 ): 1187 - 1200 .
KEUPER M , ANDRES B , BROX T . Motion trajectory segmenta-tion via minimum cost multicuts [C]. Proceedings of the IEEE In-ternational Conference on Computer Vision. Santiago, Chile : IEEE , 2015 : 3271 - 3279 .
KEUPER M , TANG S , ANDRES B , et al . Motion segmentation & multiple object tracking by correlation co-clustering [J]. IEEE transactions on pattern analysis and machine intelligence , 2018 , 1 ( 1 ): 1 - 1 .
INGWER P , GASSEN F , POST S , et al . Practical usefulness of structure from motion (SfM) point clouds obtained from different consumer cameras [J]. Spie. International Society for Optics and Photonics , 2015 , 9411 ( 1 ): 1 - 11 .
TRON R , VIDAL R . A benchmark for the comparison of 3d motion segmentation algorithms .[C]. 2007 IEEE conference on computer vision and pattern recognition , Minneapolis , MN , USA : IEEE , 2007 .
ELHAMIFAR E , VIDAL R . Sparse subspace clustering: Algorithm, theory, and applications [J]. IEEE transactions on pattern analysis and machine intelligence , 2013 , 35 ( 11 ): 2765 - 2781 .
PIMENTEL-ALARCÓN D , BALZANO L , MARCIA R , et al . Group-sparse subspace clustering with missing data [C]. 2016 IEEE Statistical Signal Processing Workshop (SSP). Palma de Mallorca, Spain : IEEE , 2016 .
XU J , XU K , CHEN K , et al . Reweighted sparse subspace clustering [J]. Computer Vision and Image Understanding , 2015 , 138 : 25 - 37 .
YOU C , ROBINSON D , VIDAL R . Scalable sparse subspace clustering by orthogonal matching pursuit [C]. Proceedings of the IEEE conference on computer vision and pattern recognition . Las Vegas, NV, USA : IEEE , 2016 : 3918 - 3927 .
FRAGKIADAKI K , SHI J . Detection free tracking: Exploiting motion and topology for segmenting and tracking under entanglement [C]. CVPR 2011. Providence , RI , USA : IEEE , 2011 . 2073 - 2080 .
GRADY L . Random walks for image segmentation [J]. IEEE transactions on pattern analysis and machine intelligence , 2006 , 28 ( 11 ): 1768 - 1783 .
FRAGKIADAKI K , ARBELAEZ P , FELSEN P , et al . Learning to seg- ment moving objects in videos [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA : IEEE , 2015 . 4083 - 4090 .
RAVICHANDRAN A , WANG C , RAPTIS M , et al . Superfloxels: A mid-level representation for video sequences [C]. European Conference on Computer Vision . Springer , Berlin, Heidelberg , 2012 : 131 - 140 .
陈静 , 张静 . 改进高斯过程回归的高光谱空谱联合分类算法 [J]. 光学 精密工程 , 2019 , 27 ( 07 ): 1649 - 1660 .
CHEN J , ZHANG J . Spectral-spatial joint classification of hyperspectral image algorithm based on improved Gaussian process regression [J]. Opt. Precision Eng. , 2019 , 27 ( 7 ): 1649 - 1660 . (in Chinese) .
LIU H , ONG Y S , SHEN X , et al . When Gaussian process meets big data: a review of scalable GPs [J]. IEEE Transactions on Neural Networks and Learning Systems , 2020 , ( 99 ): 1 - 19 .
ZHU Y . An augmented ADMM algorithm with application to the generalized lasso problem [J]. Journal of Computational and Graphical Statistics , 2017 , 26 ( 1 ): 195 - 204 .
HORAUD R , FORBES F , YGUEL M , et al . Rigid and Articulated Point Registration with Expectation Conditional Maximization [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence , 2011 , 33 ( 3 ): 587 - 602 .
0
浏览量
264
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构