检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Wu, Weiwen Yu, Haijun Chen, Peijun Luo, Fulin Liu, Fenglin Wang, Qian Zhu, Yining Zhang, Yanbo Feng, Jian Yu, Hengyong Key Lab of Optoelectronic Technology and Systems Ministry of Education Chongqing University Chongqing400044 China State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430079 China Department of Electrical and Computer Engineering University of Massachusetts Lowell LowellMA01854 United States School of Mathematical Sciences Capital Normal University Beijing100048 China Beijing Higher Institution Engineering Research Center of Testing and Imaging Beijing100048 China PingAn Technology US Research Lab Palo AltoCA94306 United States

The potential huge advantage of spectral computed tomography (CT) is its capability to provide accuracy material identification and quantitative tissue information. This can benefit clinical applications, such as brain angiography, early tumor recognition, etc. To achieve more accurate material components with higher material image quality, we develop a dictionary learning based image-domain material decomposition (DLIMD) for spectral CT in this paper. First, we reconstruct spectral CT image from projections and calculate material coefficients matrix by selecting uniform regions of basis materials from image reconstruction results. Second, we employ the direct inversion (DI) method to obtain initial material decomposition results, and a set of image patches are extracted from the mode-1 unfolding of normalized material image tensor to train a united dictionary by the K-SVD technique. Third, the trained dictionary is employed to explore the similarities from decomposed material images by constructing the DLIMD model. Fourth, more constraints (i.e., volume conservation and the bounds of each pixel within material maps) are further integrated into the model to improve the accuracy of material decomposition. Finally, both physical phantom and preclinical experiments are employed to evaluate the performance of the proposed DLIMD in material decomposition accuracy, material image edge preservation and feature recovery. Copyright © 2019, The Authors. All rights reserved.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Person Re-identification by Integrating Static Texture and Shape Cues 12th

Person Re-identification by Integrating Static Texture and S...

引用

12th Chinese Conference on Biometric Recognition, CCBR 2017

作者： Madongo, Canaan Tinotenda Huang, Di Chen, Jiaxin Laboratory of Intelligent Recognition and Image Processing School of Computer Science and Engineering Beihang University Beijing100191 China Department of Electrical and Computer Engineering New York University Abu Dhabi Abu Dhabi United Arab Emirates

ISBN: (纸本)9783319699226

Person Re-Identification (Re-ID) is a challenging task with wide ranging applications in various fields. This paper presents a novel hand-crafted method for this issue, enhancing the state of the art ones in literature in two aspects. In contrast to most current studies that analyze texture features, we propose a discriminative and compact shape feature by applying Procrustes shape analysis. It not only retains shape distinctiveness of an individual sample, but also alleviates cross-view impacts. Furthermore, we combine the shape feature with some current popular texture features, namely LOMO and mid-level filters, so that the advantages of multiple clues can be jointly used. A score level fusion strategy is finally adopted to optimally integrate their credits. Evaluated on two public benchmarks, i.e. VIPeR and CUHK03, the proposed method achieves very competitive results, indicating its effectiveness in person Re-ID. © 2017, Springer International Publishing AG.

关键词： computers

来源：评论

学校读者我要写书评

暂无评论

A Semantic Feature Extraction Method For Hyperspectral image Classification Based On Hashing Learning

A Semantic Feature Extraction Method For Hyperspectral Image...

引用

Workshop on Hyperspectral image and Signal processing: Evolution in remote sensing, WHISPERS

作者： Meng Zhao Chunyan Yu Meiping Song Chein-I Chang Center for Hyperspectral Imaging in Remote Sensing (CHIRS) Dalian Maritime University Dalian China State Key Laboratory of Integrated Services Networks Xidian University Xian China Department of Computer Science and Electrical Engineering University of Maryland Baltimore MD USA

ISBN: (纸本)9781728115825

Aiming at extraction the semantic feature of hyperspectral image, a semantic feature extraction method based on supervised hashing learning is proposed in the paper. Firstly, a set of hash functions are defined based on hyperspectral target subspace constraint which take into account the locality and discriminability between classes. Secondly, a semantic subspace is obtained through discriminative learning algorithm by the label information of hyperspectral image. Finally, the sparse binary hash codes are obtained by eigenvector mapping which represents the semantic features of targets. In the method, hashing learning uses the similarity binary codes to express the similarity of the original hyperspectral spatial data, and it uses both spectral features and spatial neighborhood features, which leads to strong distinguishing ability on a certain class of hyperspectral image. The experimental on real hyperspectral images classification results show that the fusion of the extracted semantic features with the original hyperspectral features can effectively improve the classification accuracy.

关键词： Feature extraction Hyperspectral imaging Semantics Support vector machines Hash functions Integrated circuits

来源：评论

学校读者我要写书评

暂无评论

A Geometric Approach to Second-Order Consensus of Heterogeneous Networked Systems

引用

IEEE Transactions on Cybernetics 2018年 2018 Jan 9页

作者： Su, Housheng Ye, Yanyan Chen, Xia He, Haibo School of Automation Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan 430074 China. China China Department of Electrical Computer and Biomedical Engineering University of Rhode Island Kingston RI 02881 USA. United States

This paper investigates second-order consensus of networked systems with heterogeneous intrinsic nonlinear dynamics via a geometrical method, in which the nonlinear dynamics are governed by both velocity and position. First, two necessary conditions are deduced for the existence of consensus solutions by analyzing the inherent nonlinear dynamics of isolated nodes. Then a closed invariant set is constructed via geometrical methods. The nonempty of the set implies the existence of consensus solution. Assuming that the primary and the second dimension about the above invariant set are the same linear subspace, the system can be divided into two simple subsystems through a linear transformation. In addition, some sufficient conditions are proposed for reaching the global consensus based on matrix theory and Lyapunov method. Finally, numerical simulation results are provided to illustrate the validity of theoretical analysis. IEEE

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

R3-Net: A deep network for multi-oriented vehicle detection in aerial images and videos

arXiv

引用

arXiv 2018年

作者： Li, Qingpeng Mou, Lichao Xu, Qizhi Zhang, Yun Zhu, Xiao Xiang State Key Laboratory of Virtual Reality Technology and Systems Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing100191 China Remote Sensing Technology Institute German Aerospace Center Wessling82234 Germany Signal Processing in Earth Observation Technical University of Munich Munich80333 Germany Canada Research Chair Laboratory in Advanced Geomatics Image Processing Department of Geodesy and Geomatics Engineering University of New Brunswick FrederictonNBE3B 5A3 Canada

Vehicle detection is a significant and challenging task in aerial remote sensing applications. Most existing methods detect vehicles with regular rectangle boxes and fail to offer the orientation of vehicles. However, the orientation information is crucial for several practical applications, such as the trajectory and motion estimation of vehicles. In this paper, we propose a novel deep network, called rotatable region-based residual network (R3-Net), to detect multi-oriented vehicles in aerial images and videos. More specially, R3-Net is utilized to generate rotatable rectangular target boxes in a half coordinate system. First, we use a rotatable region proposal network (R-RPN) to generate rotatable region of interests (R-RoIs) from feature maps produced by a deep convolutional neural network. Here, a proposed batch averaging rotatable anchor (BAR anchor) strategy is applied to initialize the shape of vehicle candidates. Next, we propose a rotatable detection network (R-DN) for the final classification and regression of the R-RoIs. In RDN, a novel rotatable position sensitive pooling (R-PS pooling) is designed to keep the position and orientation information simultaneously while downsampling the feature maps of RRoIs. In our model, R-RPN and R-DN can be trained jointly. We test our network on two open vehicle detection image datasets, namely DLR 3K Munich Dataset and VEDAI Dataset, demonstrating the high precision and robustness of our method. In addition, further experiments on aerial videos show the good generalization capability of the proposed method and its potential for vehicle tracking in aerial videos. The demo video is available at https://***/xCYD-tYudN0. Copyright © 2018, The Authors. All rights reserved.

关键词： remote sensing

来源：评论

学校读者我要写书评

暂无评论

An adaptable deep learning model for ionospheric pattern analysis on spaceborne interferometric SAR systems

An adaptable deep learning model for ionospheric pattern ana...

引用

AIAA Space and Astronautics Forum and Exposition, 2018

作者： Massinas, Basil A. Doulamis, Anastasios Doulamis, Nikolaos Voulodimos, Athanasios Frangos, Panayiotis Paradissis, Demitris Zografou Athens15780 Greece Dionysos Satellite Observatory National Technical University of Athens 9 Heroon Polytechniou St. Zografou Athens15780 Greece Department of Surveying Engineering National Technical University of Athens 9 Heroon Polytechniou Str Zografou Athens15780 Greece Department of Informatics and Computer Engineering University of West Attica Egaleo Athens12243 Greece School of Electrical and Computer Engineering National Technical University of Athens Greece Department of Surveying Engineering Dionysos Satellite Observatory National Technical University of Athens 9 Heroon Polytechniou Str. Zografou Athens15780 Greece Radar Systems & Remote Sensing Laboratory National Technical University of Athens 9 Heroon Polytechniou Str. Zografou Athens15780 Greece

ISBN: (数字)9781624105753

ISBN: (纸本)9781624105753

The study of ionospheric phenomena trigger great interest but also present significant research challenges along a vast range of scientific and technological applications. The optimal estimation of the ionospheric disturbances behavior is critical in many Space and Earth science applications, including efficient Spaceborne Synthetic Aperture Radar (SAR) signal processing through accurate noise modeling and removal, continuous monitoring of land and sea surface and geodynamics SAR Interferometry (InSAR) purposes. Several empirical models have been put in place for approximating the behavior of the ionosphere, leveraging for example statistical factors based on autocorrelation/autocovariance metrics for related signal analysis. Furthermore, different machine learning algorithms have been proposed for approximating the unknown dynamics of the ionospheric disturbances and detecting patterns therein;non-linear autoregressive models, echo state networks and ensemble classifiers are some examples. More recently, the advent of deep learning has unleashed new great possibilities in the field of pattern analysis, and has been successfully applied to a vast range of data types, including data originating from radar sources. The strength of deep learning lies in that it allows computational models of multiple processing layers to learn and represent data with multiple levels of abstraction mimicking the ways the brain perceives and understands multimodal information, thus implicitly capturing intricate structures of large-scale data. Convolutional Neural Networks (CNNs) are among the most popular and effective deep learning schemes proposed. In this paper, we introduce a novel variation of the aforementioned CNN architecture. We aim to combine the powerful representational capabilities of an autoregressive CNN, while also enhancing the model with a dynamic weight adaptation technique in the feedforward neural network of the final layer of the CNN. This adaptation allows for hig

关键词： Ionosphere

来源：评论

学校读者我要写书评

暂无评论

Deep learning enabled fast optical characterization of two-dimensional materials

arXiv

引用

arXiv 2019年

作者： Han, Bingnan Lin, Yuxuan Yang, Yafang Mao, Nannan Li, Wenyue Wang, Haozhe Fatemi, Valla Zhou, Lin Wang, Joel I-Jan Ma, Qiong Cao, Yuan Rodan-Legrain, Daniel Bie, Ya-Qing Navarro-Moratalla, Efrén Klein, Dahlia MacNeill, David Wu, Sanfeng Leong, Wei Sun Kitadai, Hikari Ling, Xi Jarillo-Herrero, Pablo Palacios, Tomás Yin, Jihao Kong, Jing Image Processing Center School of Astronautics Beihang University Beijing100191 China Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States Department of Physics Massachusetts Institute of Technology CambridgeMA02139 United States Department of Chemistry Boston University BostonMA02215 United States Research Laboratory of Electronics Massachusetts Institute of Technology CambridgeMA02139 United States Instituto de Ciencia Molecular Universidad de Valencia c/Catedrático José Beltrán 2 Paterna46980 Spain Division of Materials Science and Engineering Boston University BostonMA02215 United States

Characterization of nanomaterial morphologies with advanced microscopy and/or spectroscopy tools plays an indispensable role in nanoscience and nanotechnology research 1 2, 3, 4, 5, as rich information about the chemical compositions, crystallography, other physical and chemical properties, as well as the growth mechanism can be extracted from morphology analysis. However, the interpretation of imaging data heavily relies on the "intuition" of experienced researchers. As a result, many of the deep graphical features are often unused because of difficulties in processing the data and finding the correlations. Such difficulties can be well addressed by deep learning 6 7, 8, 9. In this work, we use the optical characterization of two-dimensional (2D) materials as a case study, and demonstrate a neural network based algorithm for the material and thickness identification of exfoliated 2D materials with high prediction accuracy and real-time processing capability. Further analysis shows that the trained network can be used to predict physical properties of the materials. Finally, a transfer learning technique is applied to adapt the pretrained network to more optical characterization applications such as identifying layer numbers of chemically synthesized graphene domains. Copyright © 2019, The Authors. All rights reserved.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Dimensionality reduction of hyperspectral imagery based on spatial-spectral manifold learning

arXiv

引用

arXiv 2018年

作者： Huang, Hong Shi, Guangyao He, Haibo Duan, Yule Luo, Fulin Key Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China Chongqing University Chongqing400044 China Department of Electrical Computer and Biomedical Engineering University of Rhode Island KingstonRI02881 United States State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430079 China

The graph embedding (GE) methods have been widely applied for dimensionality reduction of hyperspectral imagery (HSI). However, a major challenge of GE is how to choose proper neighbors for graph construction and explore the spatial information of HSI data. In this paper, we proposed an unsupervised dimensionality reduction algorithm termed spatial-spectral manifold reconstruction preserving embedding (SSMRPE) for HSI classification. At first, a weighted mean filter (WMF) is employed to preprocess the image, which aims to reduce the influence of background noise. According to the spatial consistency property of HSI, the SSMRPE method utilizes a new spatial-spectral combined distance (SSCD) to fuse the spatial structure and spectral information for selecting effective spatial-spectral neighbors of HSI pixels. Then, it explores the spatial relationship between each point and its neighbors to adjusts the reconstruction weights for improving the efficiency of manifold reconstruction. As a result, the proposed method can extract the discriminant features and subsequently improve the classification performance of HSI. The experimental results on PaviaU and Salinas hyperspectral datasets indicate that SSMRPE can achieve better classification accuracies in comparison with some state-of-the-art methods. Copyright © 2018, The Authors. All rights reserved.

关键词： remote sensing

来源：评论

学校读者我要写书评

暂无评论

Morphological geodesic active contour based automatic aorta segmentation in thoracic CT images

Morphological geodesic active contour based automatic aorta ...

引用

International Conference on computer Vision and image processing, CVIP 2016

作者： Dasgupta, Avijit Mukhopadhyay, Sudipta Mehre, Shrikant A. Bhattacharyya, Parthasarathi Computer Vision and Image Processing Laboratory Department of Electronics and Electrical Communication Engineering Indian Institute of Technology Kharagpur West Bengal721302 India Institute of Pulmocare & Research KolkataWest Bengal700156 India

ISBN: (纸本)9789811021060

Automatic aorta segmentation and quantification in thoracic computed tomography (CT) images is important for detection and prevention of aortic diseases. This paper proposes an automatic aorta segmentation algorithm in both contrast and non-contrast CT images of thorax. The proposed algorithm first detects the slice containing the carina region. Circular Hough Transform (CHT) is applied on the detected slice to localize ascending and descending aorta (circles with lowest variances) followed by a morphological geodesic active contour to segment the aorta from CT stack. The dice similarity coefficients (DSC) between the ground truth and the segmented output were found to be 0.8845 ± 0.0584 on LIDC-IDRI dataset. © Springer Science+Business Media Singapore 2017.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Efficient T2 mapping with Blip-up/down EPI and gSlider-SMS (T2-BUDA-gSlider)

arXiv

引用

arXiv 2019年

作者： Cao, Xiaozhi Liao, Congyu Zhang, Zijing Iyer, Siddharth Srinivasan Chen, Zhifeng Lo, Wei-Ching Liu, Huafeng Wang, Kang He, Hongjian Setsompop, Kawin Zhong, Jianhui Bilgic, Berkin Center for Brain Imaging Science and Technology Department of Biomedical Engineering Zhejiang University Zhejiang Hangzhou China Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital CharlestownMA United States Department of Radiology Harvard Medical School CharlestownMA United States State Key Laboratory of Modern Optical Instrumentation College of Optical Science and Engineering Zhejiang University Zhejiang Hangzhou China Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States School of Biomedical Engineering Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou China Siemens Medical Solutions BostonMA United States Department of Neurology The First Affiliated Hospital School of Medicine Zhejiang University Hangzhou China Harvard-MIT Department of Health Sciences and Technology CambridgeMA United States Department of Imaging Sciences University of Rochester NY United States

Purpose: To rapidly obtain high isotropic-resolution T2 maps with whole-brain coverage and high geometric fidelity. Methods: A T2 blip-up/down echo planar imaging (EPI) acquisition with generalized Slice-dithered enhanced resolution (T2-BUDA-gSlider) is proposed. A radiofrequency (RF)-encoded multi-slab spin-echo EPI acquisition with multiple echo times (TEs) was developed to obtain high SNR efficiency with reduced repetition time (TR). This was combined with an interleaved 2-shot EPI acquisition using blip-up/down phase encoding. An estimated field map was incorporated into the joint multi-shot EPI reconstruction with a structured low rank constraint to achieve distortion-free and robust reconstruction for each slab without navigation. A Bloch simulated subspace model was integrated into gSlider reconstruction and utilized for T2 quantification. Results: In vivo results demonstrated that the T2 values estimated by the proposed method were consistent with gold standard spin-echo acquisition. Compared to the reference 3D fast spin echo (FSE) images, distortion caused by off-resonance and eddy current effects were effectively mitigated. Conclusion: BUDA-gSlider SE-EPI acquisition and gSlider-subspace joint reconstruction enabled distortion-free whole-brain T2 mapping in 2 min at ~1 mm3 isotropic resolution, which could bring significant benefits to related clinical and neuroscience applications. Copyright © 2019, The Authors. All rights reserved.

关键词： Spin polarization

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：