检索结果-内蒙古大学图书馆

Improved marker coordinate recognition algorithm incorporating temporal continuity of deformation

OPTICS AND LASERS IN ENGINEERING 2021年 138卷 106379-106379页

作者： Zhu, Haibin Zhang, Xiaojuan Wang, Chao Ma, Shaopeng Inst Flexible Elect Technol THU Ctr Flexible Opt Measurement Technol Jiaxing 314006 Zhejiang Peoples R China China Railway Shanhaiguan Bridge Grp Co Ltd Qinhuangdao 066200 Hebei Peoples R China Beijing Inst Technol Sch Aerosp Engn Beijing 100081 Peoples R China Shanghai Jiao Tong Univ Sch Naval Architecture Ocean & Civil Engn Shanghai 200240 Peoples R China

Marker coordinate recognition (MCR) is widely used in fields such as medical character positioning, artificial intelligence control, and motion and deformation monitoring. registration algorithms are often applied to improve the accuracy of MCR. However, external conditions such as light and temperature induce a temporal variation in the grey level during image acquisition, thereby reducing measurement accuracy. To overcome this problem, a mechanical constraint is introduced into marker point image processing, and an algorithm that incorporates the temporal continuity of deformation is proposed. A detailed derivation of this algorithm is generated, and the algorithm's performance is systematically validated through numerical and experimental tests. The results show that the proposed method yields accurate measurements accuracy but with a slight increase in computational cost. The proposed method can be used to improve deformation measurement and position accuracy.

关键词： Marker coordinate recognition (MCR) Temporal continuity registration algorithm Measurement error

来源：评论

学校读者我要写书评

暂无评论

Recurrent spatial transformer network for high-accuracy image registration in moving PCB defect detection

引用

JOURNAL OF ENGINEERING-JOE 2020年第13期2020卷 438-443页

作者： Huang, Weibo Hua, Guoliang Yu, Zhaofu Liu, Hong Peking Univ Shenzhen Grad Sch Key Lab Machine Percept Shenzhen Guangdong Peoples R China Shenzhen Skyworth RGB Elect Co Ltd Shenzhen Guangdong Peoples R China

Defects detection is an extremely important part in the production of printed circuit board (PCB) to guarantee the quality and reliability. A widely used and researched method for this task is referential comparison method. However, this method gets poor performance on the situation that PCB moves on the conveyor, due to the lack of ability to register test images with referential images. Therefore, accurate image registration which estimates the affine transformation between the captured test images and the referential images becomes an urgent problem to be solved. In this study, a spatial transformer network is proposed. In particular, a recurrent image registration strategy is introduced to step-by-step register the images in a recurrent progress. Furthermore, a referential part is designed to help training the network. Besides, in order to simulate the real moving PCB images and train the proposed model, a factitious dataset is generated by applying random affine transformations to real PCB images. Experiments show that recurrent spatial transformer network can achieve pixel-level accurate image registration. The defects detection precision of referential comparison method has a great improvement by using the registration algorithm.

关键词： printed circuits automatic optical inspection object detection image registration affine transforms integrated circuit reliability transformers electronic engineering computing printed circuit board reliability referential comparison method referential images captured test images recurrent image registration strategy moving PCB images random affine transformations recurrent spatial transformer network pixel-level accurate image registration defects detection precision registration algorithm high-accuracy image registration PCB defect detection

来源：评论

学校读者我要写书评

暂无评论

Vehicle pose estimation algorithm for parking automated guided vehicle

引用

INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS 2019年第6期16卷

作者： Ning, Zhixiong Wang, Xin Wang, Jun Wen, Huafeng Harbin Inst Technol Shenzhen Sch Mech Engn & Automat Shenzhen 518055 Peoples R China Shenzhen Fine Automat Co Ltd Shenzhen Peoples R China

Parking automated guided vehicle is more and more widely used for efficient automatic parking and one of the tough challenges for parking automated guided vehicle is the problem of vehicle pose estimation. The traditional algorithms rely on the profile information of vehicle body and sensors are required to be mounted at the top of the vehicle. However, the sensors are always mounted at a lower place because the height of a parking automated guided vehicle is always beyond 0.2mm, where we can only get the vehicle wheel information and limited vehicle body information. In this article, a novel method is given based on the symmetry of wheel point clouds collected by 3-D lidar. Firstly, we combine cell-based method with support vector machine classifier to segment ground point clouds. Secondly, wheel point clouds are segmented from obstacle point clouds and their symmetry are corrected by iterative closest point algorithm. Then, we estimate the vehicle pose by the symmetry plane of wheel point clouds. Finally, we compare our method with registration method that combines sample consensus initial alignment algorithm and iterative closest point algorithm. The experiments have been carried out.

关键词： Parking AGV vehicle pose estimation 3-D point clouds ground segmentation registration algorithm

来源：评论

学校读者我要写书评

暂无评论

Method for coregistration of optical measurements of breast tissue with histopathology: the importance of accounting for tissue deformations

引用

JOURNAL OF BIOMEDICAL OPTICS 2019年第7期24卷 75002-75002页

作者： de Boer, Lisanne L. Kho, Esther Nijkamp, Jasper Van de Vijver, Koen K. Sterenborg, Henricus J. C. M. ter Beek, Leon C. Ruers, Theo J. M. Netherlands Canc Inst Dept Surg Amsterdam Netherlands Netherlands Canc Inst Dept Pathol Amsterdam Netherlands Ghent Univ Hosp Dept Pathol Ghent Belgium Univ Amsterdam Dept Biomed Engn & Phys Med Ctr Amsterdam Netherlands Netherlands Canc Inst Dept Med Phys Amsterdam Netherlands Univ Twente Fac Sci & Technol Enschede Netherlands

For the validation of optical diagnostic technologies, experimental results need to be benchmarked against the gold standard. Currently, the gold standard for tissue characterization is assessment of hematoxylin and eosin (H&E)-stained sections by a pathologist. When processing tissue into H&E sections, the shape of the tissue deforms with respect to the initial shape when it was optically measured. We demonstrate the importance of accounting for these tissue deformations when correlating optical measurement with routinely acquired histopathology. We propose a method to register the tissue in the H&E sections to the optical measurements, which corrects for these tissue deformations. We compare the registered H&E sections to H&E sections that were registered with an algorithm that does not account for tissue deformations by evaluating both the shape and the composition of the tissue and using microcomputer tomography data as an independent measure. The proposed method, which did account for tissue deformations, was more accurate than the method that did not account for tissue deformations. These results emphasize the need for a registration method that accounts for tissue deformations, such as the method presented in this study, which can aid in validating optical techniques for clinical use. (C) The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License.

关键词： gold standard histopathology diffuse reflectance registration algorithm optical techniques validation

来源：评论

学校读者我要写书评

暂无评论

An Improved Low-Noise Processing Methodology Combined with PCL for Industry Inspection Based on Laser Line Scanner

引用

SENSORS 2019年第15期19卷 3398-3398页

作者： Li, Jianxiong Zhou, Qian Li, Xinghui Chen, Ruiming Ni, Kai Tsinghua Univ Grad Sch Shenzhen Shenzhen 518055 Peoples R China Tsinghua Univ Tsinghua Shenzhen Int Grad Sch Shenzhen 518055 Peoples R China

This paper introduces a three-dimensional (3D) point cloud data obtained method based on a laser line scanner and data processing technology via a PCL open project. This paper also provides a systematical analysis of the error types of laser line scanner and common error reducing solutions and calibration of the laser line scanner. The laser line scanner is combined with a precision motorized stage to obtain the 3D information of a measurand, and the format of point cloud data is converted via the set of x, y, and z coordinates. The original signal is processed according to the noise signal types of the raw point cloud data. This paper introduced a denoise process step by step combining various segmentation methods and a more optimized three-dimensional data model is obtained. A novel method for industry inspection based on the numerous point cloud for the dimensions evaluation via feature extraction and the deviation of complex surface between scanned point cloud and designed point cloud via registration algorithm is proposed. Measurement results demonstrate the good performance of the proposed methods. An obtained point cloud precision of +/- 10 mu m is achieved, and the precision of dimension evaluation is less than +/- 40 mu m. The results shown in the research demonstrated that the proposed method allows a higher precision and relative efficiency in measurement of dimensions and deviation of complex surfaces in industrial inspection.

关键词： 3D reconstruction laser line scanner industry inspection registration algorithm

来源：评论

学校读者我要写书评

暂无评论

Motion-corrected en face optical coherence tomography angiography imaging based on the modified Lissajous scanning pattern 27

Motion-corrected <i>en face</i> optical coherence tomography...

引用

27th Conference on Opthalmic Technologies

作者： Chen, Yiwei Hong, Young-Joo Makita, Shuichi Yasuno, Yoshiaki Univ Tsukuba Computat Opt Grp 1-1-1 Tennodai Tsukuba Ibaraki 3058571 Japan

ISBN: (数字)9781510605329

ISBN: (纸本)9781510605312;9781510605329

A motion-corrected en face optical coherence tomography angiography (OCT-A) imaging method is presented in this paper. This method was designed to correct eye motion artifacts in en face OCT-A images automatically using a software. A modified Lissajous scanning pattern, which is compatible with OCT-A, was adopted as the scanning protocol for the optical coherence tomography (OCT) machine to obtain the OCT-A data. The OCT-A data was then processed using motion correction algorithm that was tailored for the modified Lissajous scanning pattern to correct the eye motion artifacts in the en face plane. The OCT-A slab between the inner limiting membrane and outer plexiform layer was segmented to provide an enhanced motion-corrected en face OCT-A image of the inner retinal flow. The comparison of the en face OCT-A images with and without motion correction show that our motion correction algorithm corrected the eye motion artifacts effectively. A motion-corrected en face OCT-A image of target layer is presented to confirm our method.

关键词： Optical coherence tomography angiography eye motion motion correction Lissajous scan registration algorithm

来源：评论

学校读者我要写书评

暂无评论

registration technique for spatial curves based on multi-view reconstruction

引用

INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS IN TECHNOLOGY 2016年第2期53卷 142-148页

作者： Zhang, Tian Liu, Shao-Li Tang, Cheng-Tong Liu, Jian-Hua Beijing Inst Technol Sch Mech Engn 5 Zhongguancun South St Beijing 100081 Peoples R China

A registration algorithm for spatial curves based on multi-view reconstruction is presented. Firstly the local segments of a spatial curve are reconstructed and fitted into Non-Uniform Rational B-Spline (NURBS) curves from multiple viewpoints. The intermediary planar targets are used to unify the local reconstruction coordinate systems. After determination of overlapping curves and corresponding points, all the local reconstructed spatial curves are registered in high precision. A reconstruction experiment towards a tube's central line is carried out on the proposed multi-view reconstruction system. The experiment's results show that the registration error of the proposed algorithm for spatial curves is 0.0273 mm.

关键词： spatial curve multi-view reconstruction registration algorithm NURBS curve

来源：评论

学校读者我要写书评

暂无评论

Robust Relative Navigation by Integration of ICP and Adaptive Kalman Filter Using Laser Scanner and IMU

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2016年第4期21卷 2015-2026页

作者： Aghili, Farhad Su, Chun-Yi Canadian Space Agcy St Hubert PQ J3Y 8Y9 Canada Concordia Univ Dept Mech & Ind Engn Montreal PQ H3G 1M8 Canada

This paper presents a robust six-degree-of-freedom relative navigation by combining the iterative closet point (ICP) registration algorithm and a noise-adaptive Kalman filter in a closed-loop configuration together with measurements from a laser scanner and an inertial measurement unit (IMU). In this approach, the fine-alignment phase of the registration is integrated with the filter innovation step for estimation correction, while the filter estimate propagation provides the coarse alignment needed to find the corresponding points at the beginning of ICP iteration cycle. The convergence of the ICP point matching is monitored by a fault-detection logic, and the covariance associated with the ICP alignment error is estimated by a recursive algorithm. This ICP enhancement has proven to improve robustness and accuracy of the pose-tracking performance and to automatically recover correct alignment whenever the tracking is lost. The Kalman filter estimator is designed so as to identify the required parameters such as IMU biases and location of the spacecraft center of mass. The robustness and accuracy of the relative navigation algorithm is demonstrated through a hardware-in-the loop simulation setting, in which actual vision data for the relative navigation are generated by a laser range finder scanning a spacecraft mockup attached to a robotic motion simulator.

关键词： Adaptive data fusion inertial measurement unit (IMU) iterative closest point (ICP) algorithm Kalman filtering laser scanner pose estimation registration algorithm relative navigation 3-D vision systems

来源：评论

学校读者我要写书评

暂无评论

Eye motion corrected OCT imaging with Lissajous scan pattern 26

Eye motion corrected OCT imaging with Lissajous scan pattern

引用

26th Conference on Ophthalmic Technologies

作者： Hong, Young-Joo Chen, Yiwei Li, En Miura, Masahiro Makita, Shuichi Yasuno, Yoshiaki Univ Tsukuba Computat Opt Grp 1-1-1 Tennoudai Tsukuba Ibaraki 3058571 Japan Tokyo Med Univ Dept Ophthalmol 3-20-1 Chuo Ami Ibaraki 3000395 Japan Computat Opt & Ophthalmol Grp Tsukuba Ibaraki 3058571 Japan

ISBN: (纸本)9781628419276

Ophthalmic optical coherence tomography (OCT) is a powerful tool which provides high resolution three dimensional (3D) volumetric image of human retina. However, the measurement data of OCT suffer motion artifact due to the involuntary eye motion during data acquisition. To eliminate this motion artifact and provide the true shape of retinal image, an eye motion corrected OCT imaging method based on Lissajous scan pattern is proposed in this paper. In this approach, we adopted Lissajous scan pattern for 3D-OCT imaging and developed motion correction algorithm. To verify the effectiveness of this method, we compare our method with single raster scan method by the experimental results. The experimental results show that the eye motion can be corrected by our method effectively.

关键词： Optical coherence tomography eye motion motion correction Lissajous scan registration algorithm

来源：评论

学校读者我要写书评

暂无评论

Mit :: Lcs :: Tm :: Mit-Lcs-Tm-568

引用

2016年

Mit :: Lcs :: Tm :: Mit-Lcs-Tm-568 by published by

关键词： algorithm camera computer graphics global global coordinate global registration image images input images internal camera luminance values mit-lcs-tm-568 nodes objective function optimization pose pose estimates projective transformation reconstruction registration algorithm spherical

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：