Structured Contour Primitives Extraction for Microscopic Images and Application on High Precision Pose Measurement
Fangbo Qin1,2; Fei Shen1,2; Dapeng Zhang1,2; Xilong Liu1,2; De Xu1,2
2017
发表期刊IEEE Transactions on Systems, Man, and Cybernetics: Systems
期号X页码:1-12
摘要This paper proposes a suite of methods to realize high precision pose measurement in three-dimensional (3D) Cartesian space based on a multi-camera microscopic vision system. Since it is inefficient to develop a specific image algorithm for each kind of object and the imaging condition might be unsatisfactory, we propose a method of contour primitives of interest extraction (CPIE), which allows flexible reconfiguration for novel object image and owns robustness under different imaging conditions. The object is detected in grayscale image based on a template of contour primitives. Edges are extracted according to derivatives along the normal vectors of these contour primitives. The positions and directional derivatives of these edges are used for feature extraction and autofocus, respectively. The point features and line features extracted from multi-view images are utilized to measure 3D vectors and orientations, respectively, based on image Jacobian matrices. Cameras’ linear motions are considered in the imaging model, so that the measurement range is expanded beyond the limitation of microscopes’ shallow depths of field. The affine epipolar constraint and focused planes intersection constraint between cameras are applied to improve the real time performances of image feature extraction and multi-camera autofocus, respectively. A series of experiments are conducted to verify the effectiveness of the proposed methods. The root mean square errors of pose measurement are evaluated as 3μm in position and 0.05° in orientation, while the measurement range is about 5000μm in position and 20° in orientation.
关键词Microscopic Vision Image Feature Extraction Pose Measurement Geometric Constraint Precision Assembly
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/19789
专题精密感知与控制研究中心_精密感知与控制
作者单位1.Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
2.School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing 101408, China.
推荐引用方式
GB/T 7714
Fangbo Qin,Fei Shen,Dapeng Zhang,et al. Structured Contour Primitives Extraction for Microscopic Images and Application on High Precision Pose Measurement[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems,2017(X):1-12.
APA Fangbo Qin,Fei Shen,Dapeng Zhang,Xilong Liu,&De Xu.(2017).Structured Contour Primitives Extraction for Microscopic Images and Application on High Precision Pose Measurement.IEEE Transactions on Systems, Man, and Cybernetics: Systems(X),1-12.
MLA Fangbo Qin,et al."Structured Contour Primitives Extraction for Microscopic Images and Application on High Precision Pose Measurement".IEEE Transactions on Systems, Man, and Cybernetics: Systems .X(2017):1-12.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
2017-Structured Cont(1563KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Fangbo Qin]的文章
[Fei Shen]的文章
[Dapeng Zhang]的文章
百度学术
百度学术中相似的文章
[Fangbo Qin]的文章
[Fei Shen]的文章
[Dapeng Zhang]的文章
必应学术
必应学术中相似的文章
[Fangbo Qin]的文章
[Fei Shen]的文章
[Dapeng Zhang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 2017-Structured Contour Primitives Extraction for Microscopic Images and Application on High Precision Pose Measurement.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。