检索结果-南通市图书馆

A new kernel method for hyperspectral image feature extraction

在线全文

学校读者我要写书评

暂无评论

Geo-Spatial Information Science 2017年第4期20卷 309-318页

作者： Bin Zhao lianru gao Wenzhi Liao Bing Zhang Key Laboratory of Digital Earth Science Institute of Remote Sensing and Digital Earth Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Ringgold Standard Institution Beijing China Department of Telecommunications and Information Processing Ghent University Ghent Belgium

Hyperspectral image provides abundant spectral information for remote discrimination of subtle differences in ground ***,the increasing spectral dimensions,as well as the information redundancy,make the analysis and interpretation of hyperspectral images a *** extraction is a very important step for hyperspectral image *** extraction methods aim at reducing the dimension of data,while preserving as much information as ***,nonlinear feature extraction methods (*** minimum noise fraction (KMNF) transformation) have been reported to benefit many applications of hyperspectral remote sensing,due to their good preservation of high-order structures of the original ***,conventional KMNF or its extensions have some limitations on noise fraction estimation during the feature extraction,and this leads to poor performances for *** paper proposes a novel nonlinear feature extraction method for hyperspectral *** of estimating noise fraction by the nearest neighborhood information (within a sliding window),the proposed method explores the use of image *** approach benefits both noise fraction estimation and information preservation,and enables a significant improvement for *** results on two real hyperspectral images demonstrate the efficiency of the proposed *** to conventional KMNF,the improvements of the method on two hyperspectral image classification are 8 and 11％.This nonlinear feature extraction method can be also applied to other disciplines where high-dimensional data analysis is required.

关键词： Hyperspectral image dimensionality reduction feature extraction image segmentation kernel method

A maximum noise fraction transform with improved noise estimation for hyperspectral images

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

Science in China(Series F) 2009年第9期52卷 1578-1587页

作者： LIU Xiang ZHANG Bing gao lianru CHEN DongMei Institute of Remote Sensing Applications Chinese Academy of Sciences Beijing 100101 China Center for Earth Observation and Diqital Earth Chinese Academy of Sciences Beijing 100190 China Queen's University Kingston ON K7L 3N6 Canada

Feature extraction is often performed to reduce spectral dimension of hyperspectral images before image classification. The maximum noise fraction （MNF） transform is one of the most commonly used spectral feature extraction methods. The spectral features in several bands of hyperspectral images are submerged by the noise. The MNF transform is advantageous over the principle component （PC） transform because it takes the noise information in the spatial domain into consideration. However, the experiments described in this paper demonstrate that classification accuracy is greatly influenced by the MNF transform when the ground objects are mixed together. The underlying mechanism of it is revealed and analyzed by mathematical theory. In order to improve the performance of classification after feature extraction when ground objects are mixed in hyperspectral images, a new MNF transform, with an improved method of estimating hyperspectral image noise covariance matrix （NCM）, is presented. This improved MNF transform is applied to both the simulated data and real data. The results show that compared with the classical MNF transform, this new method enhanced the ability of feature extraction and increased classification accuracy.

关键词： principal component transform maximum noise fraction transform hyperspectral image noise estimation

Frequency‐to‐spectrum mapping GAN for semisupervised hyperspectral anomaly detection

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1258-1273页

作者： Degang Wang lianru gao Ying Qu Xu Sun Wenzhi Liao Key Laboratory of Computational Optical Imaging Technology Aerospace Information Research InstituteChinese Academy of SciencesBeijingChina College of Resources and Environment University of Chinese Academy of SciencesBeijingChina Faculty of Geographical Science Beijing Normal UniversityBeijingChina Flanders Make LommelBelgium Ghent University GhentBelgium

Most unsupervised or semisupervised hyperspectral anomaly detection(HAD)methods train background reconstruction models in the original spectral ***,due to the noise and spatial resolution limitations,there may be a lack of discrimination between backgrounds and *** makes it easy for the autoencoder to capture the lowlevel features shared between the two,thereby increasing the difficulty of separating anomalies from the backgrounds,which runs counter to the purpose of *** this end,the authors map the original spectrums to the fractional Fourier domain(FrFD)and reformulate it as a mapping task in which restoration errors are employed to distinguish background and *** study proposes a novel frequency‐to‐spectrum mapping generative adversarial network for ***,the depth separable features of backgrounds and anomalies are enhanced in the *** to the semisupervised approach,FTSGAN needs to learn the embedded features of the backgrounds,thus mapping and restoring them from the FrFD to the original spectral *** strategy effectively prevents the model from focussing on the numerical equivalence of input and output,and restricts the ability of FTSGAN to restore *** comparison and analysis of the experiments verify that the proposed method is competitive.

关键词： deep learning generative adversarial network hyperspectral image neural network semisupervised learning

Performance releaser with smart anchor learning for arbitrary‐oriented object detection

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

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1213-1225页

作者： Tianwei W.Zhang Xiaoyu Y.Dong Xu Sun lianru R.gao Ying Qu Bing Zhang Ke Zheng Key Laboratory of Computational Optical Imaging Technology Aerospace Information Research InstituteChinese Academy of SciencesBeijingChina University of Chinese Academy of Sciences BeijingChina Department of Complexity Science and Engineering The University of TokyoTokyoJapan University of Tennessee KnoxvilleTennesseeUSA Key Laboratry of Digital Earth Science Aerospace Information Research InstituteChinese Academy of SciencesBeijingChina College of Geography and Environment Liaocheng UniversityLiaochengChina

Arbitrary‐oriented object detection is widely used in aerial image applications because of its efficient object ***,the use of oriented bounding box aggravates the imbalance between positive and negative samples when using one‐stage object detectors,which seriously decreases the detection *** believe that it is the anchor learning strategy(ALS)used by such detectors that needs to take the *** this study,three perspectives on ALS design were summarised and ALS—Performance Releaser with Smart Anchor Learning(PRSAL)was *** Releaser with Smart Anchor Learning is a dynamic ALS that utilises anchor classification ability as an equivalent indicator to anchor box regression ability,this allows anchors with high detection potential to be filtered out in a more reasonable *** the same time,PRSAL focuses more on anchor potential and it is able to automatically select a number of positive samples that far exceed that of other methods by activating anchors that previously had a low spatial overlap,thereby releasing the detection *** validate the PRSAL using three remote sensing datasets—HRSC2016,DOTA and UCAS‐AOD as well as one scene text dataset—ICDAR *** experimental results show that the proposed method gives substantially better results than existing models.

关键词： anchor learning strategy deep learning object detection remote sensing

Two-level parallel independent component analysis endmember extraction algorithms

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

遥感学报 2011年第6期15卷 1202-1214页

作者： LUOWenfei gaolianru SchoolofGeographicalScience SouthChinaNormalUniversityGuangdongGuangzhou510631China； CenterforEarthObservationandDigitalEarth ChineseAcademyoJ’SciencesBeijing100190China

在多对称处理器集群体系结构下进行独立成分分析并行算法研究,在共享内存模型一级并行算法基础上,通过同步、异步迭代两种方式并行计算固定点函数,分别提出具有两级并行特性的二级同步、二级异步并行端元提取算法,并结合两者的优势,进... 详细信息

在多对称处理器集群体系结构下进行独立成分分析并行算法研究,在共享内存模型一级并行算法基础上,通过同步、异步迭代两种方式并行计算固定点函数,分别提出具有两级并行特性的二级同步、二级异步并行端元提取算法,并结合两者的优势,进一步提出二级分组并行算法。实验评价表明,二级同步、分组并行算法在保持原算法精度的同时,大大提高了原算法的效率,体现出良好的并行计算性能,而二级异步并行算法可在节点数较少的情况下适用。

关键词：遥感技术应用理论图像处理

基于模糊C-均值聚类和萤火虫算法的高光谱图像波段选择

在线全文

学校读者我要写书评

暂无评论

激光与光电子学进展 2023年第12期60卷 166-176页

作者：张周孙旭刘荣高连如东华理工大学测绘工程学院江西南昌330013 中国科学院空天信息创新研究院计算光学成像技术重点实验室北京100094

传统基于聚类的波段选择方法多属于硬聚类,在对波段进行划分时不够精确。针对该问题,提出一种基于模糊C-均值聚类(FCM)的无监督波段选择方法,通过引入萤火虫算法(FA)得到FCM-FA,利用FA的全局搜索特性,修正FCM在特定情况下获得局部最优... 详细信息

传统基于聚类的波段选择方法多属于硬聚类,在对波段进行划分时不够精确。针对该问题,提出一种基于模糊C-均值聚类(FCM)的无监督波段选择方法,通过引入萤火虫算法(FA)得到FCM-FA,利用FA的全局搜索特性,修正FCM在特定情况下获得局部最优解的问题。在两个公开高光谱数据集上进行分类实验,结果表明:在136组实验中,所提FCM-FA所选波段在55.9%的情况下能够达到使用全波段的分类精度;在77.9%情况下能够达到最优分类精度;FA的引入有效地提升了FCM的效果,总体精度最大提高了3.12个百分点,Kappa最大提高了4.26个百分点。经验证,FCMFA能够在大幅减少数据量的同时保留原数据的主要信息,可进一步进行推广和研究。

关键词：遥感波段选择高光谱图像模糊C-均值聚类萤火虫算法

冠状动脉造影正常患者血清内皮素-1与TIMI-FC的关系

在线全文

学校读者我要写书评

暂无评论

临床心血管病杂志 2007年第2期23卷 91-93页

作者：卢少平杨晔高连如中国人民解放军海军总医院心内科北京100037

目的:探讨静息心电图呈ST-T改变而冠状动脉造影正常、心电图运动负荷试验阳性和阴性者的血流TIMI-FC值改变和与静息时的内皮素-1(ET-1)浓度的关系。方法:41例有静息时心电图ST-T改变,选择性冠状动脉造影检查结果阴性患者,根据负荷心电... 详细信息

目的:探讨静息心电图呈ST-T改变而冠状动脉造影正常、心电图运动负荷试验阳性和阴性者的血流TIMI-FC值改变和与静息时的内皮素-1(ET-1)浓度的关系。方法:41例有静息时心电图ST-T改变,选择性冠状动脉造影检查结果阴性患者,根据负荷心电图结果将其分为:心电图运动负荷试验阳性组(阳性组,18例)和心电图运动负荷试验阴性组(阴性组,23例)。20例静息心电图正常、负荷心电图阴性的健康志愿者为对照组。采用酶联免疫吸附法(ELISA)测定ET-1浓度,以Judkins法进行多方位冠状动脉造影,测量TIMI-FC。结果:①阳性组ET-1浓度和TIMI-FC值较阴性组和对照组均增高(均P0.05);②ET-1水平和最大的TIMI-FC值呈正相关,ET-1水平与△TIMI-FC值也呈正相关,且相关性更大。结论:在静息心电图ST-T改变而冠状动脉造影正常者中,心电图运动负荷试验阳性的患者存在内皮功能异常。△TIMI-FC在评价冠状动脉内皮功能异常的严重程度上有一定价值。

关键词：冠状动脉造影心电描记术内皮素-1 血流速度

在线全文

学校读者我要写书评

暂无评论

高分五号高光谱图像自编码网络非线性解混

遥感学报 2020年第4期24卷 388-400页

作者：韩竹高连如张兵孙旭李庆亭中国科学院空天信息创新研究院数字地球重点实验室北京100094 中国科学院大学北京100049

针对高光谱非线性混合模型中的共线性问题,提出了一种非监督的增强型非线性自编码网络方法 ENAE(Enhanced Nonlinear Autoencoder)。通过结合自编码网络在挖掘数据内在结构、提取特征方面的优势,引入端元正则项减弱端元间的共线性效应,... 详细信息

针对高光谱非线性混合模型中的共线性问题,提出了一种非监督的增强型非线性自编码网络方法 ENAE(Enhanced Nonlinear Autoencoder)。通过结合自编码网络在挖掘数据内在结构、提取特征方面的优势,引入端元正则项减弱端元间的共线性效应,从而提高高光谱混合像元分解精度。ENAE方法的实现步骤主要包括两部分:一是网络结构初始化,二是非线性分解。网络结构初始化是确定编码器的节点数以及端元和丰度的初值;非线性分解则主要是实现损失函数的最小化。通过模拟数据、城市区域真实数据和高分五号卫星高光谱数据的实验,得到了相较于传统非线性分解方法更高的精度,证明了ENAE方法的鲁棒性。

关键词：高光谱遥感高分五号卫星自编码网络混合像元非线性分解

“生物药”——Wharton's jelly源间充质干细胞

在线全文

学校读者我要写书评

暂无评论

转化医学杂志 2016年第4期5卷 193-197页

作者：高连如海军总医院心脏中心北京100048

干细胞治疗代表生物冶疗进入到了一个崭新的时代。间充质干细胞是存在于胚胎或成体组织中来源于中胚层具有多向分化潜能的干细胞。由于成体间充质干细胞的质量与数量自身缺陷,使之应用受到了很大限制。Wharton's jelly组织,是起始于胚... 详细信息

干细胞治疗代表生物冶疗进入到了一个崭新的时代。间充质干细胞是存在于胚胎或成体组织中来源于中胚层具有多向分化潜能的干细胞。由于成体间充质干细胞的质量与数量自身缺陷,使之应用受到了很大限制。Wharton's jelly组织,是起始于胚胎发育第13天的胚外中胚层组织。使用基因微阵列分析及功能分析,首次发现Wharton's jelly源间充质干细胞(Wharton's jelly derived mesenchymal stem cells,WJMSCs)高表达胚胎早期干性基因及心肌细胞分化早期特异转录因子,可分化心肌细胞等多种细胞。进而,应用临床级WJMSCs经冠状动脉移植治疗ST抬高型急性心肌梗死患者的随机双盲临床试验,首次证明WJMSCs可明显改善心肌活力及心脏功能。因此,WJMSCs具有极其重要益处;无伦理涉及,有强的分化潜能,无致瘤性;加之,WJMSCs可作为产品,在任何时候病情需要时立即应用。为此,WJMSCs作为真正意义上的干细胞族,将最有希望成为具有应用前景的于细胞生物药。

关键词：间充质干细胞 Wharton's jelly源间充质干细胞生物药物