检索结果-南通市图书馆

feature matching via Topology-Aware Graph Interaction Model

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 113-130页

作者： Yifan Lu Jiayi Ma Xiaoguang Mei Jun Huang Xiao-Ping Zhang the Electronic Information School Wuhan UniversityWuhan 430072China IEEE Tsinghua Berkeley Shenzhen Institute Shenzhen 518071China the Department of Electrical Computer and Biomedical EngineeringToronto Metropolitan UniversityToronto ON M5B 2K3Canada

feature matching plays a key role in computer vision. However, due to the limitations of the descriptors, the putative matches are inevitably contaminated by massive outliers.This paper attempts to tackle the outlier filtering problem from two aspects. First, a robust and efficient graph interaction model,is proposed, with the assumption that matches are correlated with each other rather than independently distributed. To this end, we construct a graph based on the local relationships of matches and formulate the outlier filtering task as a binary labeling energy minimization problem, where the pairwise term encodes the interaction between matches. We further show that this formulation can be solved globally by graph cut algorithm. Our new formulation always improves the performance of previous localitybased method without noticeable deterioration in processing time,adding a few milliseconds. Second, to construct a better graph structure, a robust and geometrically meaningful topology-aware relationship is developed to capture the topology relationship between matches. The two components in sum lead to topology interaction matching(TIM), an effective and efficient method for outlier filtering. Extensive experiments on several large and diverse datasets for multiple vision tasks including general feature matching, as well as relative pose estimation, homography and fundamental matrix estimation, loop-closure detection, and multi-modal image matching, demonstrate that our TIM is more competitive than current state-of-the-art methods, in terms of generality, efficiency, and effectiveness. The source code is publicly available at http://***/YifanLu2000/TIM.

关键词： feature matching graph cut outlier filtering topology preserving

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

GeoGlue: feature matching with self-supervised geometric priors for high-resolution UAV images

引用

International Journal of Digital Earth 2023年第1期16卷 1246-1275页

作者： Weijia Bei Xiangtao Fan Hongdeng Jian Xiaoping Du Dongmei Yan Key Laboratory of Digital Earth Science Aerospace Information Research InstituteChinese Academy of SciencesBeijingPeople’s Republic of China International Research Center of Big Data for Sustainable Development Goals BeijingPeople’s Republic of China College of Resources and Environment University of Chinese Academy of SciencesBeijingPeople’s Republic of China

We present GeoGlue,a novel method using high-resolution UAV imagery for accurate feature matching,which is normally challenging due to the complicated scenes.Current feature detection methods are performed without guidance of geometric priors(e.g.,geometric lines),lacking enough attention given to salient geometric features which are indispensable for accurate matching due to their stable existence across views.In this work,geometric lines arefirstly detected by a CNN-based geometry detector(GD)which is pre-trained in a self-supervised manner through automatically generated images.Then,geometric lines are naturally vectorized based on GD and thus non-significant features can be disregarded as judged by their disordered geometric morphology.A graph attention network(GAT)is utilized forfinal feature matching,spanning across the image pair with geometric priors informed by GD.Comprehensive experiments show that GeoGlue outperforms other state-of-the-art methods in feature-matching accuracy and performance stability,achieving pose estimation with maximum rotation and translation errors under 1%in challenging scenes from benchmark datasets,Tanks&Temples and ETH3D.This study also proposes thefirst self-supervised deep-learning model for curved line detection,generating geometric priors for matching so that more attention is put on prominent features and improving the visual effect of 3D reconstruction.

关键词： feature matching geometric priors self-supervised learning graph attention network 3D reconstruction digital earth

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

Illumination-robust and Anti-blur feature Descriptors for Image matching in Abdomen Reconstruction

引用

International Journal of Automation and computing 2014年第5期11卷 469-479页

作者： Huan Liu Ying Xiao Wei-Dong Tang Yan-Hui Zhou College of Electronic and Information Engineering Jinggangshan University College of Mechanical and Electronic Engineering Jinggangshan University

This paper puts forward a method for abdomen panorama reconstruction based on a stereo vision system. For the purpose of recovering the abdomen completely and accurately under the condition of actual photographing with illumination variance and blur noise, some innovative combined feature descriptors are presented on the basis of Hu-moment invariants. Furthermore, considering the study on the abdomen surface reconstruction, a circle template which is divided into 6 sectors is designed. It is noted that a descriptor merely using gray intensity is not able to provide sufficient information for feature description. Consequently, the sector entropy which denotes the structure characteristics is drawn into the feature descriptor. By means of the combined effect of the gray intensity and the sector entropy, the similarity measurement is conducted for the final abdomen reconstruction. The experimental results reveal that the proposed method can acquire a high precision of abdomen reconstruction similar to the 3D scanner. This stereo vision system has wide practicability in the field of clothing.

关键词： Stereo vision system illumination-robust and anti-blur combined invariant sector entropy circle template feature matching 3D reconstruction

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

Learning to focus: cascaded feature matching network for few-shot image recognition

引用

Science China(Information Sciences) 2021年第9期64卷 90-102页

作者： Mengting CHEN Xinggang WANG Heng LUO Yifeng GENG Wenyu LIU School of Electronic Information and Communications Huazhong University of Science and Technology

Generally, deep networks learn to recognize a category of objects by training on a large number of annotated images accurately. However, a meta-learning problem known as a low-shot image recognition task occurs when a few images with annotations are available for learning a recognition model for a single category. Consequently, the objects in testing/query and training/support image datasets are likely to vary in terms of size, location, style, and so on. In this paper, we propose a method, cascaded feature matching network(CFMN), to solve this problem. We train the meta-learner to learn a more fine-grained and adaptive deep distance metric using feature matching block, which aligns associated features together and naturally ignores non-discriminative features. By applying the proposed feature matching block in different layers of the network, multi-scale information among the compared images is incorporated into the final cascaded matching feature, which boosts the recognition performance and generalizes better by learning on relationships. Moreover, the experiments for few-shot learning(FSL) using two standard datasets:miniImageNet and Omniglot, confirm the effectiveness of our proposed method. Besides, the multi-label fewshot task is first studied on a new data split of the COCO dataset, which further shows the superiority of the proposed feature matching network when performing the FSL in complex images.

关键词： few-shot learning image recognition feature matching self-attention

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

A fast, accurate and dense feature matching algorithm for aerial images

引用

Journal of Systems Engineering and Electronics 2020年第6期31卷 1128-1139页

作者： LI Ying GONG Guanghong SUN Lin School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China

Three-dimensional(3D)reconstruction based on aerial images has broad prospects,and feature matching is an important step of it.However,for high-resolution aerial images,there are usually problems such as long time,mismatching and sparse feature pairs using traditional algorithms.Therefore,an algorithm is proposed to realize fast,accurate and dense feature matching.The algorithm consists of four steps.Firstly,we achieve a balance between the feature matching time and the number of matching pairs by appropriately reducing the image resolution.Secondly,to realize further screening of the mismatches,a feature screening algorithm based on similarity judgment or local optimization is proposed.Thirdly,to make the algorithm more widely applicable,we combine the results of different algorithms to get dense results.Finally,all matching feature pairs in the low-resolution images are restored to the original images.Comparisons between the original algorithms and our algorithm show that the proposed algorithm can effectively reduce the matching time,screen out the mismatches,and improve the number of matches.

关键词： feature matching feature screening feature fusion aerial image three-dimensional(3D)reconstruction

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

Absence Importance and Its Application to feature Detection and matching

引用

International Journal of Automation and computing 2016年第5期13卷 480-490页

作者： Zhi-Heng Wang Qin-Feng Song Hong-Min Liu Zhan-Qiang Huo School of Computer Science and Technique Henan Polytechnic University

feature detection and matching play important roles in many fields of computer vision, such as image understanding, feature recognition, 3D-reconstruction, video analysis, etc. Extracting features is usually the first step for feature detection or matching, and the gradient feature is one of the most used selections. In this paper, a new image feature-absence importance （AI） feature, which can directly characterize the local structure information, is proposed. Greatly different from the most existing features, the proposed absence importance feature is mainly based on the consideration that the absence of the important pixel will have a great effect on the local structure. Two absence importance features, mean absence importance （MAI） and standard deviation absence importance （SDAI）, are defined and used subsequently to construct new algorithms for feature detection and matching. Experiments demonstrate that the proposed absence importance features can be used as an important complement of the gradient feature and applied successfully to the fields of feature detection and matching.

关键词： Absence importance （AI） feature detection feature matching mean absence importance （MAI） standard deviation absence importance （SDAI）.

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

Individual Identification of Dairy Cows Based on Deep feature Extrac-tion and matching

引用

Journal of Northeast Agricultural University(English Edition) 2022年第3期29卷 85-96页

作者： Shen Wei-zheng Sun Jia Liang Chen Shi Wei Guo Jin-yan Zhang Zhe Zhang Yong-gen College of Electrical Engineering and Information Northeast Agricultural UniversityHarbin 150030China Heilongjiang Agricultural Technology Extension Station Harbin 150030China College of Animal Sciences and Technology Northeast Agricultural UniversityHarbin 150030China

Individual identification of dairy cows is the prerequisite for automatic analysis and intelligent perception of dairy cows'behavior.At present,individual identification of dairy cows based on deep convolutional neural network had the disadvantages in prolonged training at the additions of new cows samples.Therefore,a cow individual identification framework was proposed based on deep feature extraction and matching,and the individual identification of dairy cows based on this framework could avoid repeated training.Firstly,the trained convolutional neural network model was used as the feature extractor;secondly,the feature extraction was used to extract features and stored the features into the template feature library to complete the enrollment;finally,the identifies of dairy cows were identified.Based on this framework,when new cows joined the herd,enrollment could be completed quickly.In order to evaluate the application performance of this method in closed-set and open-set individual identification of dairy cows,back images of 524 cows were collected,among which the back images of 150 cows were selected as the training data to train feature extractor.The data of the remaining 374 cows were used to generate the template data set and the data to be identified.The experiment results showed that in the closed-set individual identification of dairy cows,the highest identification accuracy of top-1 was 99.73%,the highest identification accuracy from top-2 to top-5 was 100%,and the identification time of a single cow was 0.601 s,this method was verified to be effective.In the open-set individual identification of dairy cows,the recall was 90.38%,and the accuracy was 89.46%.When false accept rate(FAR)=0.05,true accept rate(TAR)=84.07%,this method was verified that the application had certain research value in open-set individual identification of dairy cows,which provided a certain idea for the application of individual identification in the field of intelligent animal husbandry.

关键词： cow individual identification convolutional neural networks deep feature extraction feature matching

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

Transfer Learning Based on Joint feature matching and Adversarial Networks

引用

Journal of Shanghai Jiaotong university(Science) 2019年第6期24卷 699-705页

作者：钟昊文王超庹红娅胡健乔凌峰敬忠良 School of Aeronautics and Astronautics Shanghai Jiao Tong University

Domain adaptation and adversarial networks are two main approaches for transfer learning.Domain adaptation methods match the mean values of source and target domains,which requires a very large batch size during training.However,adversarial networks are usually unstable when training.In this paper,we propose a joint method of feature matching and adversarial networks to reduce domain discrepancy and mine domaininvariant features from the local and global aspects.At the same time,our method improves the stability of training.Moreover,the method is embedded into a unified convolutional neural network that can be easily optimized by gradient descent.Experimental results show that our joint method can yield the state-of-the-art results on three common public datasets.

关键词： transfer learning adversarial networks feature matching domain-invariant features

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

Trifocal Tensor Based feature matching Algorithm

引用

Journal of Beijing Institute of Technology 2020年第4期29卷 484-488页

作者： Mingwei Shao Pan Wang School of Information and Control Engineering Qingdao University of TechnologyQingdao 266000ShandongChina

feature matching is of significance in the field of computer vision.In this paper,a trifocal tensor based feature matching algorithm is proposed for three views,including a trinocular vision system.Initial matching point-pairs can be determined according to generic matching algorithms,on which an initial trifocal tensor of three views can be confirmed.Then the initial matching point-pairs should be re-selected.Meanwhile,the trifocal tensor will be recomputed.Iteratively,the optimized trifocal tensor can be obtained.Compatible fundamental matrix of every two views can be determined.Furthermore,in the trinocular vision sensor,the trifocal tensor can be calculated based on the intrinsic parameter matrix of each camera.With the strict constraint provided by the trifocal tensor,feature matching results will be optimized.Experiments show that our proposed algorithm has the characteristics of feasibility and precision.

关键词： optics trifocal tensor feature matching

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

A New Algorithm for feature matching in Reverse Engineering

引用

Tsinghua Science and Technology 2009年第S1期14卷 43-46页

作者：朱根松周天瑞周捷 College of Mechanical and Electrical Engineering Nanchang University College of Application and Science Jiangxi University of Science and Technology

feature recognition and surface reconstruction from point clouds are difficulties in reverse engineering. A new surface reconstruction algorithm for slicing point cloud was presented. The contours of slice were extracted. Then, the intersection of two adjacent curve segments in the contour was obtained and curves feature was extracted. Finally, adjacent section contours were matched directly with Fourier-Mellin curve matching method for feature extraction. An example of 3-D model reconstruction shows the reliability and application of the algorithm.

关键词： reverse engineering slice curve reconstruction feature recognition feature matching

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：