检索结果-南通市图书馆

Topological distance-constrained feature descriptor learning model for vessel matching in coronary angiographies

Virtual Reality & Intelligent Hardware 2021年第4期3卷 287-301页

作者： Xiaojiao SONG Jianjun ZHU Jingfan FAN Danni AI Jian YANG Beijing Engineering Research Center of Mixed Reality and Advanced Display School of Optics and PhotonicsBeijing Institute of TechnologyBeijing 100081China

Background feature matching technology is vital to establish the association between virtual and real objects in virtual reality and augmented reality ***,it provides them with the ability to match a dynamic *** image matching methods,of which most are deep learning-based,have been proposed over the past few ***,vessel fracture,stenosis,artifacts,high background noise,and uneven vessel gray-scale make vessel matching in coronary angiography extremely *** matching methods perform poorly in this *** In this study,a topological distance-constrained feature descriptor learning model is *** model regards the topology of the vasculature as the connection relationship of the *** topological distance combines the geodesic distance between the input patches and constrains the descriptor network by maximizing the feature difference between connected and unconnected patches to obtain more useful potential feature *** Matching patches of different sequences of angiographic images are generated for the *** matching accuracy and stability of the proposed method is superior to those of the existing *** The proposed method solves the problem of matching coronary angiographies by generating a topological distance-constrained feature descriptor.

关键词： Vessel matching Deep learning feature descriptor Coronary angiographies Geodesic distance Topological distance-constrained

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

Performance study of feature descriptors for human detection on depth map

引用

International Journal of Modeling, Simulation, and Scientific Computing 2014年第3期5卷 17-32页

作者： Pengfei Wang Shiwei Ma Yujie Shen School of Mechatronic Engineering&Automation Shanghai Key Laboratory of Power Station Automation Technology Shanghai University No.149Yanchang Rd.200072 ShanghaiP.R.China

Depth map contains the space information of objects and is almost free from the influence of light,and it attracts many research interests in the field of machine vision used for human ***,hunting a suitable image feature for human detection on depth map is rather *** this paper,we evaluate the performance of the typical features on depth map.A depth map dataset containing various indoor scenes with human is constructed by using Microsoft’s Kinect camera as a quantitative benchmark for the study of methods of human detection on depth *** depth map is smoothed with pixel filtering and context filtering so as to reduce particulate ***,the performance of five image features and a new feature is studied and compared for human detection on the dataset through theoretic analysis and simulation *** show that the new feature outperforms other descriptors.

关键词： Human detection depth map feature descriptor

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

Robust multi-sensor image matching based on normalized self-similarity region descriptor

引用

Chinese Journal of Aeronautics 2024年第1期37卷 271-286页

作者： Xuecong LIU Xichao TENG Jing LUO Zhang LI Qifeng YU Yijie BIAN College of Aerospace Science and Engineering National University of Defense TechnologyChangsha 410073China High-Tech Institute Qingzhou 262500China

Multi-modal image matching is crucial in aerospace applications because it can fully exploit the complementary and valuable information contained in the amount and diversity of remote sensing ***,it remains a challenging task due to significant non-linear radiometric,geometric differences,and noise across different *** improve the performance of heterologous image matching,this paper proposes a normalized self-similarity region descriptor to extract consistent structural *** first construct the pointwise self-similarity region descriptor based on the Euclidean distance between adjacent image blocks to reflect the structural properties of multi-modal ***,a linear normalization approach is used to form Modality Independent Region descriptor(MIRD),which can effectively distinguish structural features such as points,lines,corners,and flat between multi-modal *** further improve the matching accuracy,the included angle cosine similarity metric is adopted to exploit the directional vector information of multi-dimensional feature *** experimental results show that the proposed MIRD has better matching accuracy and robustness for various multi-modal image matching than the state-of-the-art *** can effectively extract consistent geometric structure features and suppress the influence of SAR speckle noise using non-local neighboring image blocks operation,effectively applied to various multi-modal image matching.

关键词： Remote sensing Multi-modal image matching Template matching feature descriptor Similarity metric Synthetic Aperture Radar(SAR)

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

Applying rotation-invariant star descriptor to deep-sky image registration

引用

Frontiers of Computer Science 2018年第5期12卷 1013-1025页

作者： Haiyang ZHOU Yunzhi YU College of Optical Science and Engineering Zhejiang University Hangzhou 310027 China Department of Computer Science University of Southern California Los Angeles CA 90089-0781 USA

Image registration is a critical process of many deep-sky image processing applications. Image registration methods include image stacking to reduce noise or achieve long exposure effects within a short exposure time, image stitching to extend the field of view, and atmospheric turbu- lence removal. The most widely used method for deep-sky image registration is the triangle- or polygon-based method, which is both memory and computation intensive. Deepsky image registration mainly focuses on translation and rotation caused by the vibration of imaging devices and the Earth＇s rotation, where rotation is the more difficult problem. For this problem, the best method is to find corresponding rotation-invariant features between different images. In this paper, we analyze the defects introduced by applying rotation-invariant feature descriptors to deep-sky image reg- istration and propose a novel descriptor. First, a dominant orientation is estimated from the geometrical relationships between a described star and two neighboring stable stars. An adaptive speeded-up robust features （SURF） descriptor is then constructed. During the construction of SURF, the local patch size adaptively changes based on the described star size. Finally, the proposed descriptor is formed by fusing star properties, geometrical relationships, and the adaptive SURF. Extensive experiments demonstrate that the proposed descriptor successfully addresses the gap resulting from applying the traditional feature-based method to deep-sky image registration and performs well compared to state-of-the-art descriptors.

关键词： image registration feature descriptor deep-skyimage rotation-invariant descriptor

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

A Multisource Contour Matching Method Considering the Similarity of Geometric features

引用

Journal of Geodesy and Geoinformation Science 2020年第3期3卷 76-87页

作者： Wenyue GUO Anzhu YU Qun SUN Shaomei LI Qing XU Bowei WEN Yuanfu LI Information Engineering University Zhengzhou 450052China

The existing multi-source contour matching studies have focused on the matching methods with consideration of topological relations and similarity measurement based on spatial Euclidean distance,while it is lack of taking the contour geometric features into account,which may lead to mismatching in map boundaries and areas with intensive contours or extreme terrain *** light of this,it is put forward that a matching strategy from coarse to precious based on the contour geometric *** proposed matching strategy can be described as ***,the point sequence is converted to feature sequence according to a feature descriptive function based on curvature and angle of normal *** the level of similarity among multi-source contours is calculated by using the longest common subsequence ***,the identical contours could be matched based on the above calculated *** the experiment for the proposed method,the reliability and efficiency of the matching method are verified using simulative datasets and real datasets *** has been proved that the proposed contour matching strategy has a high matching precision and good applicability.

关键词： multisource contour matching geometric feature similarity measurement longest common subsequence feature descriptor

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

Medical image registration based on Clifford algebra and three-dimensional SURF

Medical image registration based on Clifford algebra and thr...

引用

第32届中国过程控制会议(CPCC2021)

作者： Cheng Tianyu Gu Juping Hua Liang Zhou Bojun Zhao Fengshen Zhao Jiahao School of Automation Nanjing University of Science and Technology School of Electrical Engineering Nantong University

Multimodal medical image registration can provide doctors with more abundant focus information of patients,but there is a contradiction between registration accuracy and efficiency in clinical *** this paper,a 3 D SURF framework based on Hessian four-dimensional scale space is built,a feature descriptor based on geometric algebraic relative angle invariants is designed,which is more suitable for 3 D images,and a fast spatial optimization(GA-FSO) algorithm based on this descriptor is *** method achieves high precision registration and compensates the lack of immediacy in clinical ***,the registration experiment is carried out based on the brain multimodal images provided by RIRE open database,and the mean error is less than 3 mm,which verifies the effectiveness of this registration scheme and satisfies demand of clinical online *** the contrastive experiments for registration are carried out with clinical case data to verify the clinical practicability of the registration *** study provides theoretical basis and technical support for the clinical application of three-dimensional multimodal medical image registration.

关键词： medical image registration geometric algebra SURF algorithm feature descriptor fast space optimization

来源： cnki会议评论

在线全文

cnki会议

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

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

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：