检索结果-南通市图书馆

Automatic detection of breast lesions in automated 3D breast ultrasound with cross-organ transfer learning

虚拟现实与智能硬件（中英文） 2024年第3期6卷 239-251页

作者： Lingyun BAO Zhengrui HUANG Zehui LIN Yue SUN Hui CHEN You LI Zhang LI Xiaochen YUAN Lin XU Tao TAN Affiliated Hangzhou First People's Hospital School of MedicineWestlake UniversityHangzhou 330100China Faculty of Applied Sciences Macao Polytechnic UniversityMacao 999078China Pathology Department Changsha First HospitalChangsha 410073China Radiology Department Changsha First HospitalChangsha 410073China College of Aerospace Science and Engineering National University of Defense TechnologyChangsha 410073China hunan Provincial key laboratory of image measurement and vision navigation Changsha 410073China School of Information Science and Technology Shanghaitech UniversityShanghai 201210China

Background Deep convolutional neural networks have garnered considerable attention in numerous machine learning applications,particularly in visual recognition tasks such as image and video *** is a growing interest in applying this technology to diverse applications in medical image *** three dimensional Breast Ultrasound is a vital tool for detecting breast cancer,and computer-assisted diagnosis software,developed based on deep learning,can effectively assist radiologists in ***,the network model is prone to overfitting during training,owing to challenges such as insufficient training *** study attempts to solve the problem caused by small datasets and improve model detection *** We propose a breast cancer detection framework based on deep learning(a transfer learning method based on cross-organ cancer detection)and a contrastive learning method based on breast imaging reporting and data systems(BI-RADS).Results When using cross organ transfer learning and BIRADS based contrastive learning,the average sensitivity of the model increased by a maximum of 16.05%.Conclusion Our experiments have demonstrated that the parameters and experiences of cross-organ cancer detection can be mutually referenced,and contrastive learning method based on BI-RADS can improve the detection performance of the model.

关键词： Breast ultrasound Automated 3D breast ultrasound Breast cancers Deep learning Transfer learning Convolutional neural networks Computer-aided diagnosis Cross organ learning

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Pose optimization based on integral of the distance between line segments

引用

Science China Technological Sciences 2016年第1期59卷 135-148页

作者： ZHANG YueQiang LI Xin LIU HaiBo SHANG Yang YU QiFeng College of Aerospace Science and Engineering National University of Defense Technology hunan Provincial key laboratory of image measurement and vision navigation

In this paper, new solutions for the problem of pose estimation from correspondences between 3D model lines and 2D image lines are proposed. Traditional line-based pose estimation methods rely on the assumption that the noises(perpendicular to the line) for the two endpoints are statistically independent. However, these two noises are in fact negatively correlated when the image line segment is fitted using the least-squares technique. Therefore, we design a new error function expressed by the average integral of the distance between line segments. Three least-squares techniques that optimize both the rotation and translation simultaneously are proposed in which the new error function is exploited. In addition, Lie group formalism is utilized to describe the pose parameters, and then, the optimization problem can be solved by means of a simple iterative least squares method. To enhance the robustness to outliers existing in the match data, an M-estimation method is developed to convert the pose optimization problem into an iterative reweighted least squares problem. The proposed methods are validated through experiments using both synthetic and real-world data. The experimental results show that the proposed methods yield a clearly higher precision than the traditional methods.

关键词： machine vision perspective-n-line problem line distance function pose optimization M-estimation

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Multiple rotation averaging using only the relative rotation angle

引用

Science China(Technological Sciences) 2023年第10期66卷 2978-2985页

作者： LI Bin SHANG Yang GUAN BangLei LIANG ShunKun SUN XiaoLiang YU QiFeng College of Aerospace Science and Engineering National University of Defense TechnologyChangsha 410073China hunan Provincial key laboratory of image measurement and vision navigation Changsha 410073China

In this work,we propose multiple rotation averaging using only the relative rotation angle,which is a straightforward camera pose optimization *** use the axis-angle representation to parameterize the rotation and use only relative rotation angles to constrain absolute rotations instead of complete relative *** used with an inertial measurement unit(IMU),our method can obviate the need to estimate and maintain extrinsic parameters between the camera and *** advantage makes our method immune to extrinsic parameters and *** performed extensive evaluations on both synthetic data and publicly available real datasets,which showed that our method was comparable with the state-of-the-art method and achieved a significant gain in accuracy for the visual measurement when applied to the case in which the camera and IMU are tightly fixed.

关键词： multiple rotation averaging pose optimization relative rotation angle IMU

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Hull deformation measurement for spacecraft TT&C ship by Photogrammetry

引用

Science China(Technological Sciences) 2015年第8期58卷 1339-1347页

作者： LIU HaiBo SUN Cong ZHANG YueQiang LIU XinMing LIU JinBo ZHANG XiaoHu YU QiFeng College of Aerospace Science and Engineering National University of Defense Technology hunan Provincial key laboratory of image measurement and vision navigation China Satellite Maritime Tracking and Control Department

When voyaging,ships are subject to inevitable hull deformations caused by the changes in the environmental temperature and external *** are a crucial source of errors when measuring data using a spacecraft tracking,telemetry,and control(TT&C) ship.A prototype system based on photogrammetry was developed for the real-time measurement of a spacecraft TT&C ship's hull *** system has high accuracy,a simple structure,and convenient maintenance,and requires few changes to the ship's *** improve its performance,an estimation approach is proposed for hull deformation *** the proposed approach,the central positions of cross spots in successive frames can be predicted based on the prediction of the camera's attitude,and their extract locations can be found by defining a series of small windows around each predictive ***,the optimal estimate of the camera's attitude is updated by the designed extended Kalman filter using the extracted cross spots and their corresponding local coordinates,with which the hull deformation angles can be *** verify the proposed measurement approach,its performance was tested during the normal sailing,floating,and rocking on the sea of a spacecraft TT&C *** experimental testing results demonstrated that the proposed approach performs well in terms of accuracy and *** can satisfy the hull deformation measurement requirement for a spacecraft TT&C ship in real time.

关键词： photogrammetry ship deformation spacecraft TT&C ship EKF

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Non-contact optical dynamic measurements at different ranges:a review

引用

Acta Mechanica Sinica 2021年第4期37卷 537-553,I0001页

作者： Yu Fu Yang Shang Wenxin Hu Bin Li Qifeng Yu Shenzhen key laboratory of Intelligent Optical measurement and Detection Shenzhen UniversityShenzhen 518060China hunan Provincial key laboratory of image measurement and vision navigation College of Aerospace Science and EngineeringNational University of Defense TechnologyChangsha 410073China

Optical dynamic measurements are widely used for non-contact vibration,continuous deformation,or moving *** measurement techniques were developed for different deformation *** paper reviews three types of technique for different measurement ranges:interferometric techniques for deformation or vibration(nanometer to submillimeter amplitude)whose measurement accuracies rely on phase extraction of interferometric signal;imaging based techniques for deformation or vibration(micrometer to centimeter amplitude)with the aid of moire,structured light,and man-made speckles,whose sensitivities is from 1/100 to 1/10 pixel;and videometrics for large deformation or movement detection(greater than centimeter amplitude).Many research groups have improved measurement capabilities for these three techniques to meet particular industrial application requirements.

关键词： Vibration measurement Laser interferometry Digital image correlation High-speed imaging Videometrics

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Precise monocular vision-based pose measurement system for lunar surface sampling manipulator

引用

Science China(Technological Sciences) 2019年第10期62卷 1783-1794页

作者： WANG Gang SHI ZhongChen SHANG Yang SUN XiaoLiang ZHANG WenLong YU QiFeng College of Aerospace Science and Engineering National University of Defense TechnologyChangsha410073China hunan Provincial key laboratory of image measurement and vision navigation Changsha410073China

Space manipulator has been playing an increasingly important role in space exploration due to its flexibility and versatility. This paper is to design a vision-based pose measurement system for a four-degree-of-freedom(4-DOF) lunar surface sampling manipulator relying on a monitoring camera and several fiducial markers. The system first employs double plateaus histogram equalization for the markers to improve the robustness to varying noise and illumination. The markers are then accurately extracted in sub-pixel based on template matching and curved surface fitting. Finally, given the camera parameters and 3D reference points, the pose of the manipulator end-effector is solved from the 3D-to-2D point correspondences by combining a plane-based pose estimation method with rigid-body transformation. Experiment results show that the system achieves highprecision positioning and orientation performance. The measurement error is within 3 mm in position, and 0.2° in orientation,meeting the requirements for space manipulator operations.

关键词： vision-based pose measurement pose estimation lunar surface sampling sub-pixel corner detection Chang’e 5

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

vision navigation for aircrafts based on 3D reconstruction from real-time image sequences

引用

Science China(Technological Sciences) 2015年第7期58卷 1196-1208页

作者： ZHU ZunShang SU Ang LIU HaiBo SHANG Yang YU QiFeng College of Aerospace Science and Engineering National University of Defense Technology hunan key laboratory of Videometrics and vision navigation

In this paper,we propose a novel vision navigation method based on three-dimensional(3D)reconstruction from real-time image *** adapts 3D reconstruction and terrain matching to establish the correspondence between image points and3D space points and the terrain reference(by using a digital elevation map(DEM)).An adaptive weighted orthogonal iterative pose estimation method is employed to calculate the position and attitude angle of the *** and real experiments show that the proposed method is capable of providing accurate navigation parameters for a long-endurance flight without using a global positioning system or an inertial navigation system(INS).Moreover,it can be combined with an INS to achieve an improved navigation result.

关键词： vision navigation 3D reconstruction terrain matching pose estimation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

New method for camera pose estimation based on line correspondence

引用

Science China(Technological Sciences) 2013年第11期56卷 2787-2797页

作者： LIU JinBo ZHANG XiaoHu LIU HaiBo YUAN Yun ZHU ZhaoKun YU QiFeng College of Aerospace Science and Engineering National University of Defense Technology hunan key laboratory of Videometrics and vision navigation

The key technology of the measuring method of pose shaking of unstable platform based on CCD lies in the camera pose estimation. A new method for camera pose estimation based on line correspondence is put forward in this paper. First, two appro- priate lines are selected in the space to establish a local coordinate system, the remaining lines form three-line sets with these two lines respectively and then the angle depth of the lines of the local coordinate system can be obtained by using the linearity of interpretation plane; then the invariance of included angle between spatial coordinate system and camera coordinate system during rigid transformation is used to establish a constraint equation set of angle depth of three lines similar to traditional P3P, and the corresponding angle depth of the third line in the set can be obtained linearly by variable substitution; finally, the rota- tion matrix can be expressed with quaternion and the pose parameters of camera in the space can be calculated by singular value decomposition （SVD）. The static experiment and dynamic experiment verify the accuracy and stability of the algorithm and that the camera pose shocking is within 1~ and the 3a error is superior to 0.3＇. The method in this paper can be directly used in the micro-vibration measurement of experimental platform and robot navigation and other fields and is of important theoretical significance and engineering application prospect.

关键词： unstable platform measurement of pose shaking line correspondence angle depth quaternion

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Correction method for non-landing measuring of vehicle-mounted theodolite based on static datum conversion

引用

Science China(Technological Sciences) 2013年第9期56卷 2268-2277页

During the non-landing measuring of vehicle mounted theodolite, especially under high-speed tracking measurement, the misalignment of theodolite's center of mass and spindle etc. will cause high-frequency vibration of theodolite platform, increase the observation error of targets and even unbelievable results. In this paper, a correction method of non-landing measuring of theodolite based on static datum conversion is presented, which can effectively improve the observation accuracy of theodolite. The CCD camera is fixed to the theodolite platform to calculate the gesture shaking quantity of theodolite platform in geodetic coordinate system through the real time imaging of static datum. The observation results of theodolite are corrected by using such shaking quantity. The experiment shows that the correction accuracy exceeds 10 s of arc. The intrinsic parameter calibration technology of camera based on stellar angular distance and absolute conic put forward in this paper can prevent the estimated error of extrinsic parameters influencing the intrinsic parameter calibration and improve the intrinsic parameter calibration accuracy; the static datum conversion technology can reduce the influence of installation error of camera and theodolite platform on gesture measuring of the platform. The simulation experiment shows that when the shaking range of the platform is less than 30 min of arc, the influence of the three-axis installation error of camera within 3deg on the accuracy of correction results is less than 8 s of arc. The method in this paper can be extended to and used in the field of gesture shaking measuring and micro-structure deformation of various unstable platforms, therefore it is of important theoretical research significance and has wide engineering application prospect.

关键词： vehicle-mounted theodolite non-landing Measuring error correction static datum conversion decoupling calibration

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Study of the response of 10B-doped MCP to wide-energy range neutrons from eV to MeV

引用

Nuclear Science and Techniques 2024年第8期35卷 132-141页

作者： Qiang Li Li‑Jiao Wang Xiang‑Biao Qiu Jing‑Wen Li Wei Xu Tao Li Ze‑Bin Lin Chang‑Jun Ning Yong‑Hao Chen Rui‑Rui Fan Kang Sun Jing‑Yu Tang Rong Zhang Han‑Tao Jing Bo Mei Qi An Hao‑Fan Bai Jiang‑Bo Bai Jie Bao Ping Cao Qi‑Ping Chen Zhen Chen Zeng‑Qi Cui An‑Chuan Fan Chang‑Qing Feng Fan‑Zhen Feng Ke‑Qing Gao Min‑Hao Gu Chang‑Cai Han Zi‑Jie Han Guo‑Zhu He Yong‑Cheng He Yang Hong Yi‑Wei Hu Han‑Xiong Huang Wei‑Hua Jia Hao‑Yu Jiang Wei Jiang Zhi‑Jie Jiang Zheng‑Yao Jin Ling Kang Bo Li Chao Li Gong Li Jia‑Wen Li Xiao Li Yang Li Jie Liu Rong Liu Shu‑Bin Liu Guang‑Yuan Luan Bin‑Bin Qi Jie Ren Zhi‑Zhou Ren Xi‑Chao Ruan Zhao‑Hui Song Zhi‑Xin Tan Sheng‑Da Tang Peng‑Cheng Wang Zhao‑Hui Wang Zhong‑Wei Wen Xiao‑Guang Wu Xuan Wu Li‑Kun Xie Yi‑Wei Yang Han Yi Yong‑Ji Yu Guo‑Hui Zhang Lin‑Hao Zhang Mo‑Han Zhang Qi‑Wei Zhang Xian‑Peng Zhang Yu‑Liang Zhang Yue Zhang Zhi‑Yong Zhang Mao‑Yuan Zhao Lu‑Ping Zhou Zhi‑Hao Zhou Ke‑Jun Zhu Institute of High Energy Physics Chinese Academy of Sciences(CAS)Beijing 100049China Spallation Neutron Source Science Center Dongguan 523803China State key laboratory of Particle Detection and Electronics Institute of High Energy PhysicsChinese Academy of SciencesBeijing 100049China Dongguan Songshan Lake Future School Dongguan 523808China North Night vision Science&Technology(Nanjing)Research Institute Co.Ltd. Nanjing 211106China Sino‑French Institute of Nuclear Engineering and Technology Sun Yat-sen UniversityZhuhai 519082China School of Nuclear Science and Technology University of Science and Technology of ChinaHefei 230027China State key laboratory of Particle Detection and Electronics University of Science and Technology of ChinaHefei 230026China Department of Modern Physics University of Science and Technology of ChinaHefei 230026China State key laboratory of Nuclear Physics and Technology School of PhysicsPeking UniversityBeijing 100871China Institute of Nuclear Physics and Chemistry China Academy of Engineering PhysicsMianyang 621900China key laboratory of Nuclear Data China Institute of Atomic EnergyBeijing 102413China USTC Archaeometry Lab University of Science and Technology of ChinaHefei 230026China Northwest Institute of Nuclear Technology Xi’an 710024China University of Chinese Academy of Sciences Beijing 100049China

Neutron-sensitive microchannel plates(nMCPs)have applications in neutron detection,including energy spectrum measurements,neutron-induced cross sections,and neutron imaging.10B-doped MCPs(B-MCPs)have attracted significant attention owing to their potential for exhibiting a high neutron detection efficiency over a large neutron energy *** spatial and temporal resolutions are useful for neutron energy-resolved ***,their practical applications still face many technical *** this study,a B-MCP with 10 mol%10B was tested for its response to wide-energy neutrons from eV to MeV at the Back-n white neutron source at the China Spallation Neutron *** neutron detection efficiency was calibrated at 1 eV,which is approximately 300 times that of an ordinary MCP and indicates the success of 10 B *** factors that caused the reduction in the detection efficiency were simulated and *** neutron energy spectrum obtained using B-MCP was compared with that obtained by other measurement methods,and showed very good consistency for neutron energies below tens of *** response is more complicated at higher neutron energy,at which point the elastic and nonelastic reactions of all nuclides of B-MCP gradually become *** is beneficial for the detection of neutrons,as it compensates for the detection efficiency of B-MCP for high-energy neutrons.

关键词： Neutron radiation image 10B-doped MCP Neutron response Wide-energy range neutrons

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：