1.中国海洋大学 工程学院,山东 青岛 266100
[ "迟书凯(1980-),男,山东烟台人,博士,高级工程师,2002年于青岛海洋大学获得学士学位,2007年于中国海洋大学获得硕士学位,2017年于中国海洋大学获得博士学位,现为中国海洋大学自动化教学实验中心主任,主要从事水下机器视觉、智能仪器仪表、水下无人系统方面的研究。E-mail:chishukai@ouc.edu.cn" ]
[ "高 翔(1989-),男,山东临沂人,博士,讲师,2012年于中国海洋大学获得学士学位,2015年于中国海洋大学获得硕士学位,2019年于中国科学院大学获得博士学位,现为中国海洋大学工程学院讲师,主要从事三维计算机视觉、基于图像的大规模场景三维重建等方面的研究。E-mail:xgao@ouc.edu.cn" ]
[ "解则晓(1968-),男,山东临沂人,博士,教授,博士生导师,1991年于青岛大学获得学士学位,1997年于大连理工大学获得硕士学位,2000年于天津大学获得博士学位,2000年至2002年从事博士后科研工作,现为中国海洋大学自动化及测控系教授,主要从事机器视觉与视觉测量、逆向工程、水下三维探测技术方面的研究。E-mail:xiezexiao@ouc.edu.cn" ]
扫 描 看 全 文
迟书凯, 叶旋, 高翔, 等. 基于编码标记点的高精度运动估计[J]. 光学精密工程, 2021,29(7):1720-1730.
Shu-kai CHI, Xuan YE, Xiang GAO, et al. Coded marker-based high-accuracy motion estimation[J]. Optics and Precision Engineering, 2021,29(7):1720-1730.
迟书凯, 叶旋, 高翔, 等. 基于编码标记点的高精度运动估计[J]. 光学精密工程, 2021,29(7):1720-1730. DOI: 10.37188/OPE.20212907.1720.
Shu-kai CHI, Xuan YE, Xiang GAO, et al. Coded marker-based high-accuracy motion estimation[J]. Optics and Precision Engineering, 2021,29(7):1720-1730. DOI: 10.37188/OPE.20212907.1720.
为实现前景运动的精确估计,本文提出了一种基于编码标记点的高精度运动估计方法。该方法在测量环境内的前背景中粘贴环状编码标记点,并在每次前景运动后采集若干图像,通过同时估计所有相机位姿以及背景固定标记点、前景运动标记点的空间坐标,获取前景运动六自由度参数(旋转、平移)。为实现上述目标,本文提出了包括基于随机抽样一致性的编码标记点识别与提取,图聚类的编码标记点与相机分组,增量式从运动恢复结构的背景点与相机位姿初始化,图优化的前景点与前景运动初始化以及广义光束平差的全局优化等在内的一套高精度运动估计流程。实验结果表明,本文提出的前景运动估计方法精度在0.3 mm左右,可以满足高精度前景运动估计的需求。
In order to achieve accurate foreground motion estimation, a coded marker-based high-accuracy motion estimation method is proposed in this paper. First, several circular coded markers are pasted on the foreground and background of the measurement environment. Then, several images are captured after each foreground motion. Finally, based on the captured images, all the camera poses and the spatial coordinates of the fixed markers on the background and the moving markers on the foreground are estimated simultaneously to obtain the 6 Degrees of Freedom (DoF) parameters (rotation and translation) of foreground motion. To this end, a high-accuracy motion estimation pipeline is proposed in this paper, which includes RANdom SAmple Consensus (RANSAC)-based coded marker detection and recognition, graph clustering-based coded marker and camera partitioning, incremental Structure from Motion (SfM)-based background marker and camera initialization, graph optimization-based foreground marker and foreground motion initialization, and generalized Bundle Adjustment (BA)-based global optimization. The experimental results show that the accuracy of the proposed foreground motion estimation method is approximately 0.3 mm, which is satisfactory for high-accuracy foreground motion estimation.
高精度运动估计编码标记点基于图聚类的分组基于广义光束平差的全局优化
High-accuracy motion estimationcoded markergraph clustering-based partitioninggeneralized BA-based global optimization
SULTANAL M, MAHMOOD A, JAVED S, et al. Unsupervised deep context prediction for background estimation and foreground segmentation[J]. Machine Vision Applications, 2019, 30: 375–395.
王向军, 张继龙, 阴雷. 光流法运动估计在FPGA上的实现与性能分析[J]. 光学 精密工程, 2019, 27(1): 211-220.
WANG X J, ZHANG J L, YIN L. Implementation and performance analysis of optical flow motion estimation on FPGA[J]. Opt. Precision Eng., 2019, 27(1): 211-220. (in Chinese)
YU Y C, XIONG Y L, HUANG W L, et al. Deformable Siamese attention networks for visual object tracking[C]. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020: 6728-6737.
DANELLJAN M, GOOL L V, TIMOFTE R. Probabilistic regression for visual tracking[C]. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020: 7183-7192.
SONG C, SONG J R, HUANG Q X. HybridPose: 6D object pose estimation under hybrid representations[C]. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020: 431-440.
CHEN W, JIA X, CHANG H J, et al. G2L-Net: Global to local network for real-time 6D pose estimation with embedding vector features[C]. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020: 4233-4242.
LI Y, ZHANG T W, NAKAMURA Y, et al. SplitFusion: Simultaneous tracking and mapping for non-rigid scenes[C]. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020.
BOLYA D, ZHOU C, XIAO F Y. YOLACT: Real-time instance segmentation[C]. In International Conference on Computer Vision (ICCV), 2019: 9157-9166.
解则晓, 高翔, 朱瑞新. 环状编码标记点的高效提取与鲁棒识别算法[J]. 光电子·激光, 2015, 26(3): 559-566.
XIE Z X, GAO X, ZHU R X. Efficient extraction and robust recognition algorithm of circular coded target[J]. Journal of Optoelectronics·Laser, 2015, 26(3): 559-566. (in Chinese)
解则晓, 高翔, 崔健. 移动式三维测量用圆形标记点提取算法[J]. 中国激光, 2013, 40(12): 1208002.
XIE Z X, GAO X, CUI J. Extraction algorithm of circular targets used for mobile three-dimensional measurement [J]. Chinese Journal of Lasers, 2013, 40(12): 1208002. (in Chinese)
GHOSAL S, MEHROTRA R. Orthogonal moment operators for subpixel edge detection[J]. Pattern Recognition, 1993, 26(2): 295-306.
FISCHLER M A, BOLLES R C. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6): 381-395.
解则晓, 王晓敏. 平面标定靶标标记点的圆心提取[J]. 光学 精密工程, 2019, 27(2): 440-449.
XIE Z X, WANG X M. Extraction of the center of the mark point of the plane calibration target[J]. Opt. Precision Eng., 2019, 27(2): 440-449. (in Chinese)
WU Y H, WANG H R, TANG F L, et al. Efficient conic fitting with an analytical Polar-N-Direction geometric distance[J]. Pattern Recognition, 2019, 90: 415-423.
HARTLEY, R I. In defense of the eight-point algorithm[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(6): 580-593.
DHILLON I S, GUAN Y Q, KULIS B. Weighted graph cuts without eigenvectors: A multilevel approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(11): 1944-1957.
CUI Z P, TAN P. Global structure-from-motion by similarity averaging[C]. In International Conference on Computer Vision (ICCV), 2015: 864-872.
SCHÖNBERGER J L, FRAHM J M. Structure-from-motion revisited[C]. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 4104-4113.
Nistér D. An efficient solution to the five-point relative pose problem[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(6): 756-770.
HARTLEY R I, ZISSERMAN A. Multiple View Geometry in Computer Vision[M]. Cambridge: Cambridge University Press, 2004.
GAO X S, HOU X R, TANG J L, et al. Complete solution classification for the perspective-three-point problem[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(8): 930-943.
AGARWAL S, SNAVELY N, SEITZ S M, et al. Bundle adjustment in the large[C]. In European Conference on Computer Vision (ECCV), 2010: 29-42.
ARUN K S, HUANG T S, BLOSTEIN S D. Least-squares fitting of two 3-D point sets[J] IEEE Transactions on Pattern Analysis and Machine Intelligence, 1987, 9(5): 698-700.
CARLONE L, TRON R, DANIILIDIS K, et al. Initialization techniques for 3D SLAM: A survey on rotation estimation and its use in pose graph optimization[C]. In IEEE International Conference on Robotics and Automation (ICRA), 2015: 4597-4604.
GAO X, SHEN S H, ZHU L J, et al. Complete scene reconstruction by merging images and laser scans[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 30(10): 3688-3701.
PARK J, ZHOU Q, KOLTUN V. Colored point cloud registration revisited[C]. In IEEE International Conference on Computer Vision (ICCV), 2017: 143-152.
0
浏览量
88
下载量
2
CSCD
关联资源
相关文章
相关作者
相关机构