检索结果-南通市图书馆

A Simple Deep Learning Network for Classification of 3D Mobile LiDAR Point Clouds

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Geodesy and Geoinformation Science 2021年第3期4卷 49-59页

作者： Yanjun WANG Shaochun LI Mengjie WANG Yunhao LIN Hunan Provincial Key Laboratory of Geo-Information Engineering in Surveying Mapping and Remote SensingHunan University of Science and TechnologyXiangtan 411201China National-local Joint Engineering Laboratory of Geo-spatial Information Technology Hunan University of Science and TechnologyXiangtan 411201China School of Resource Environment and Safety Engineering Hunan University of Science and TechnologyXiangtan 411201China

Automatic and accurate classification is a fundamental problem to the analysis and modeling of LiDAR(Light Detection and Ranging)***,convolutional neural network(ConvNet or CNN)has achieved remarkable performance in image recognition and computer *** significant efforts have also been made to develop various deep networks for satellite image scene classification,it still needs to further investigate suitable deep learning network frameworks for 3D dense mobile laser scanning(MLS)*** this paper,we present a simple deep CNN for multiple object classification based on multi-scale context *** the pointwise classification,we first extracted the neighboring points within spatial context and transformed them into a three-channel image for each ***,the classification task can be treated as the image recognition using *** proposed CNN architecture adopted common convolution,maximum pooling and rectified linear unit(ReLU)layers,which combined multiple deeper network *** being trained and tested on approximately seven million labeled MLS points,the deep CNN model can classify accurately into nine *** with the widely used ResNet algorithm,this model performs better precision and recall rates,and less processing time,which indicated the significant potential of deep-learning-based methods in MLS data classification.

关键词： deep learning convolutional neural network(CNN) mobile laser scanning(MLS) LiDAR data classification point-to-image transformation

MF~2ResU-Net:a multi-feature fusion deep learning architecture for retinal blood vessel segmentation

在线全文

学校读者我要写书评

暂无评论

Digital Chinese Medicine 2022年第4期5卷 406-418页

作者： CUI Zhenchao SONG Shujie QI Jing School of Cyber Security and Computer Hebei UniversityBaodingHebei 071002China Machine vision Engineering Research Center Hebei UniversityBaodingHebei 071002China

Objective For computer-aided Chinese medical diagnosis and aiming at the problem of insufficient segmentation,a novel multi-level method based on the multi-scale fusion residual neural network(MF2ResU-Net)model is *** To obtain refined features of retinal blood vessels,three cascade connected UNet networks are *** deal with the problem of difference between the parts of encoder and decoder,in MF2ResU-Net,shortcut connections are used to combine the encoder and decoder layers in the *** refine the feature of segmentation,atrous spatial pyramid pooling(ASPP)is embedded to achieve multi-scale features for the final segmentation *** The MF2ResU-Net was superior to the existing methods on the criteria of sensitivity(Sen),specificity(Spe),accuracy(ACC),and area under curve(AUC),the values of which are 0.8013 and 0.8102,0.9842 and 0.9809,0.9700 and 0.9776,and 0.9797 and 0.9837,respectively for DRIVE and CHASE *** results of experiments demonstrated the effectiveness and robustness of the model in the segmentation of complex curvature and small blood *** Based on residual connections and multi-feature fusion,the proposed method can obtain accurate segmentation of retinal blood vessels by refining the segmentation features,which can provide another diagnosis method for computer-aided Chinese medical diagnosis.

关键词： Medical image processing Atrous space pyramid pooling(ASPP) Residual neural network Multi-level model Retinal vessels segmentation

Video Polyp Segmentation: A Deep Learning Perspective

在线全文

学校读者我要写书评

暂无评论

Machine Intelligence Research 2022年第6期19卷 531-549页

作者： Ge-Peng Ji Guobao Xiao Yu-Cheng Chou Deng-Ping Fan Kai Zhao Geng Chen Luc Van Gool Research School of Engineering Australian National UniversityCanberra 2601Australia College of Computer and Control Engineering Minjiang UniversityFuzhou 350108China Department of Computer Science Johns Hopkins UniversityBaltimore 21218USA Computer vision Laboratory ETH ZürichZürich 8092Switzerland Department of Radiological Sciences University of CaliforniaLos Angeles 90095USA School of Computer Science and Engineering Northwestern Polytechnical UniversityXi′an 710072China

We present the first comprehensive video polyp segmentation(VPS)study in the deep learning *** the years,developments in VPS are not moving forward with ease due to the lack of a large-scale dataset with fine-grained segmentation *** address this issue,we first introduce a high-quality frame-by-frame annotated VPS dataset,named SUN-SEG,which contains 158690colonoscopy video frames from the well-known *** provide additional annotation covering diverse types,i.e.,attribute,object mask,boundary,scribble,and ***,we design a simple but efficient baseline,named PNS+,which consists of a global encoder,a local encoder,and normalized self-attention(NS)*** global and local encoders receive an anchor frame and multiple successive frames to extract long-term and short-term spatial-temporal representations,which are then progressively refined by two NS *** experiments show that PNS+achieves the best performance and real-time inference speed(170 fps),making it a promising solution for the VPS ***,we extensively evaluate 13 representative polyp/object segmentation models on our SUN-SEG dataset and provide attribute-based ***,we discuss several open issues and suggest possible research directions for the VPS *** project and dataset are publicly available at https://***/GewelsJI/VPS.

关键词： Video polyp segmentation(VPS) dataset self-attention colonoscopy abdomen

Attention Based Multi-Patched 3D-CNNs with Hybrid Fusion Architecture for Reducing False Positives during Lung Nodule Detection

在线全文

学校读者我要写书评

暂无评论

Journal of Computer and Communications 2021年第4期9卷 1-26页

作者： Vamsi Krishna Vipparla Premith Kumar Chilukuri Giri Babu Kande Emerging Technologies Department Mahindra & Mahindra IT Mumbai Maharashtra India Computer vision Division Supervue AI Visakhapatnam Andhra Pradesh India Department of Electronics & Communication Engineering Vasireddy Venkatadri Institute of Technology Nambur Andhra Pradesh India

In lung nodules there is a huge variation in structural properties like Shape, Surface Texture. Even the spatial properties vary, where they can be found attached to lung walls, blood vessels in complex non-homogenous lung structures. Moreover, the nodules are of small size at their early stage of development. This poses a serious challenge to develop a Computer aided diagnosis (CAD) system with better false positive reduction. Hence, to reduce the false positives per scan and to deal with the challenges mentioned, this paper proposes a set of three diverse 3D Attention based CNN architectures (3D ACNN) whose predictions on given low dose Volumetric Computed Tomography (CT) scans are fused to achieve more effective and reliable results. Attention mechanism is employed to selectively concentrate/weigh more on nodule specific features and less weight age over other irrelevant features. By using this attention based mechanism in CNN unlike traditional methods there was a significant gain in the classification performance. Contextual dependencies are also taken into account by giving three patches of different sizes surrounding the nodule as input to the ACNN architectures. The system is trained and validated using a publicly available LUNA16 dataset in a 10 fold cross validation approach where a competition performance metric (CPM) score of 0.931 is achieved. The experimental results demonstrate that either a single patch or a single architecture in a one-to-one fashion that is adopted in earlier methods cannot achieve a better performance and signifies the necessity of fusing different multi patched architectures. Though the proposed system is mainly designed for pulmonary nodule detection it can be easily extended to classification tasks of any other 3D medical diagnostic computed tomography images where there is a huge variation and uncertainty in classification.

关键词： 3D-CNN Attention Gated Networks Lung Nodules Medical Imaging X-Ray Computed Tomography

A Practical Approach to Constructing a Geological Knowledge Graph:A Case Study of Mineral Exploration Data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Earth Science 2023年第5期34卷 1374-1389页

作者： Qinjun Qiu Bin Wang Kai Ma Hairong Lü Liufeng Tao Zhong Xie Collaborative Innovation Center of Geo-Information Technology for Smart Central Plains Zhengzhou 450046China Key Laboratory of Spatiotemporal Perception and Intelligent Processing Ministry of Natural ResourcesZhengzhou 450046China Key Laboratory of Geological Survey and Evaluation of Ministry of Education China University of GeosciencesWuhan 430074China Hubei Key Laboratory of Intelligent vision Based Monitoring for Hydroelectric Engineering China Three Gorges UniversityYichang 443002China College of Computer and Information Technology China Three Gorges UniversityYichang 443002China Department of Automation Tsinghua UniversityBeijing 100084China

Open data initiatives have promoted governmental agencies and scientific organizations to publish data online for *** of geoscience focuses on processing georeferenced quantitative data(e.g.,rock parameters,geochemical tests,geophysical surveys and satellite imagery)for discovering new *** knowledge is the cognitive result of human knowledge of the spatial distribution,evolution and interaction patterns of geological objects or *** graphs(KGs)can formalize unstructured knowledge into structured form and have been used in supporting decision-making *** this paper,we propose a novel framework that can extract the geological knowledge graph(GKG)from public reports relating to a modelling *** on the analysis of basic questions answered by geology,we summarize and abstract geological knowledge elements and then explore a geological knowledge representation model with three levels of“geological conceptsgeological entities-geological relations”to describe semantic units of geological knowledge and their logic ***,based on the characteristics of mineral resource reports,the geological knowledge representation model oriented to“object relationships”and the hierarchical geological knowledge representation model oriented to“process relationships”are proposed with reference to the commonly used geological knowledge graph *** research in this paper can provide some implications for the formalization and structured representation of geological knowledge graphs.

关键词： mineral resource report geological knowledge knowledge graph ontology hierarchical knowledge representation model

Hawk‐eye‐inspired perception algorithm of stereo vision for obtaining orchard 3D point cloud navigation map

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3期8卷 987-1001页

作者： Zichao Zhang Jian Chen Xinyu Xu Cunjia Liu Yu Han College of Engineering China Agricultural UniversityBeijingChina Jiangsu Province and Education Ministry Co‐sponsored Synergistic Innovation Center of Modern Agricultural Equipment Jiangsu UniversityZhenjiangChina Key Laboratory of spatial‐temporal Big Data Analysis and Application of Natural Resources in Megacities MNRShanghaiChina Department of Aeronautical and Automotive Engineering Loughborough UniversityLoughboroughLeicestershireUK College of Water Resources and Civil Engineering China Agricultural UniversityBeijingChina State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijingChina Key Laboratory of Urban Land Resources Monitoring and Simulation Ministry of Natural ResourcesShenzhenChina

The binocular stereo vision is the lowest cost sensor for obtaining 3D *** the weakness of long‐distance measurement and stability,the improvement of accuracy and stability of stereo vision is urgently required for application of precision *** address the challenges of stereo vision long‐distance measurement and stable perception without hardware upgrade,inspired by hawk eyes,higher resolution perception and the adaptive HDR(High Dynamic Range)were introduced in this *** the function from physiological structure of‘deep fovea’and‘shallow fovea’of hawk eye,the higher resolution reconstruction method in this paper was aimed at ac-curacy *** by adjustment of pupils,the adaptive HDR method was proposed for high dynamic range optimisation and stable *** various light conditions,compared with default stereo vision,the accuracy of proposed algorithm was improved by 28.0%evaluated by error ratio,and the stability was improved by 26.56%by disparity *** fixed distance measurement,the maximum improvement was 78.6%by standard *** on the hawk‐eye‐inspired perception algorithm,the point cloud of orchard was improved both in quality and *** hawk‐eye‐inspired perception algorithm contributed great advance in binocular 3D point cloud recon-struction in orchard navigation map.

关键词： adaptive high dynamic range binocular stereo vision hawk‐eye‐inspired perception point cloud of orchard super‐resolution generative adversarial network

Optical imaging of post-embryonic zebrafish using multi orientation raster scan optoacoustic mesoscopy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Light(Science & Applications) 2016年第1期5卷 336-341页

作者： Murad Omar Johannes Rebling Kai Wicker Tobias Schmitt-Manderbach Mathias Schwarz Jérôme Gateau Hérnan López-Schier Timo Mappes Vasilis Ntziachristos Chair for Biological Imaging Technische Universität MünchenMünchen D-81675Germany Institute for Biological and Medical Imaging Helmholtz Zentrum MünchenNeuherberg D-85764Germany Carl Zeiss AG Corporate Research and TechnologyJena D-07745Germany ESPCI Paris PSL Research UniversityCNRSINSERMInstitut LangevinParis F-75005France Research Unit Sensory Biology and Organogenesis Helmholtz Zentrum MünchenNeuherberg D-85764Germany Carl Zeiss vision International GmbH Technology&InnovationAalen D-73430Germany

Whole-body optical imaging of post-embryonic stage model organisms is a challenging and long sought-after *** requires a combination of high-resolution performance and high-penetration ***(photoacoustic)mesoscopy holds great promise,as it penetrates deeper than optical and optoacoustic microscopy while providing high-spatial ***,optoacoustic mesoscopic techniques only offer partial visibility of oriented structures,such as blood vessels,due to a limited angular detection aperture or the use of ultrasound frequencies that yield insufficient *** introduce 3601 multi orientation(multi-projection)raster scan optoacoustic mesoscopy(MORSOM)based on detecting an ultra-wide frequency bandwidth(up to 160 MHz)and weighted deconvolution to synthetically enlarge the angular *** report unprecedented isotropic inplane resolution at the 9–17μm range and improved signal to noise ratio in phantoms and opaque 21-day-old *** find that MORSOM performance defines a new operational specification for optoacoustic mesoscopy of adult organisms,with possible applications in the developmental biology of adulthood and aging.

关键词： deconvolution development mesoscopy multiview optoacoustics photoacoustics

Comparison of ocular modulation transfer function determined by a ray-tracing aberrometer and a double-pass system in early cataract patients

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Medical Journal 2014年第19期127卷 3454-3458页

作者： Qiao Liya Wan Xiuhua Cai Xiaogu Balamurali Vasudevan Xiong Ying Tan Jiaxuan Guan Zheng David A Atchison Wang Ningli Beijing Tongren Eye Center Beijing Tongren Hospital CapitalMedical University Beijing Ophthalmology & Visual Science KeyLaboratory Capital Medical University Beijing 100730 China College of Optometry Midwestem University Glendale ArizonaUnited States School of Optometry & vision Science and Institute of Health&Biomedical Innovation Queensland University of TechnologyAustralia

Background The evaluation of retinal image quality in cataract eyes has gained importance and the clinical modulation transfer functions （MTF） can obtained by aberrometer and double pass （DP） system. This study aimed to compare MTF derived from a ray tracing aberrometer and a DP system in early cataractous and normal eyes. Methods There were 128 subjects with 61 control eyes and 67 eyes with early cataract defined according to the Lens Opacities Classification System II1. A laser ray-tracing wavefront aberrometer （iTrace） and a double pass （DP） system （OQAS） assessed ocular MTF for 6.0 mm pupil diameters following dilation. Areas under the MTF （AUMTF） and their correlations were analyzed. Stepwise multiple regression analysis assessed factors affecting the differences between iTrace- and OQAS-derived AUMTF for the early cataract group. Results For both early cataract and control groups, iTrace-derived MTFs were higher than OQAS-derived MTFs across a range of spatial frequencies （P 〈0.01）. No significant difference between the two groups occurred for iTrace-derived AUMTF, but the early cataract group had significantly smaller OQAS-derived AUMTF than did the control group （P 〈0.01）. AUMTF determined from both the techniques demonstrated significant correlations with nuclear opacities, higher-order aberrations （HOAs）, visual acuity, and contrast sensitivity functions, while the OQAS-derived AUMTF also demonstrated significant correlations with age and cortical opacity grade. The factors significantly affecting the difference between iTrace and OQAS AUMTF were root-mean-squared HOAs （standardized beta coefficient=-0.63, P 〈0.01） and age （standardized beta coefficient=0.26, P 〈0.01）. Conclusions MTFs determined from a iTrace and a DP system （OQAS） differ significantly in early cataractous and normal subjects. Correlations with visual performance were higher for the DP system. OQAS-derived MTF may be useful as an indicator of visual performance in early cataract eyes.

关键词： cataract contrast sensitivity function double-pass system modulation transfer function retinal image quality," wavefront aberration

Visual perception alterations in COVID-19:a preliminary study

在线全文

学校读者我要写书评

暂无评论

International Journal of Ophthalmology(English edition) 2023年第1期16卷 1-9页

作者： María Begoña Coco-Martín Luis Leal-Vega Irene Alcoceba-Herrero Ainhoa Molina-Martín Dolores de-Fez María JoséLuque Carlos Dueñas-Gutiérrez Juan Francisco Arenillas-Lara David PPiñero Group of Applied Clinical Neurosciences and Advanced Data Analysis Department of MedicineDermatology and ToxicologyUniversity of ValladolidValladolid 47005Spain Group of Optics and Visual Perception Department of OpticsPharmacology and AnatomyUniversity of AlicanteAlicante 03690Spain Department of Optics and Optometry and Vision SciencesUniversity of ValenciaValencia 46100Spain COVID-19 Unit Department of Internal MedicineUniversity Clinical Hospital of ValladolidValladolid 47003Spain Stroke Unit Department of NeurologyUniversity Clinical Hospital of ValladolidValladolid 47003Spain Clinical Optometry Unit Department of OphthalmologyVithas Medimar International HospitalAlicante 03016Spain

AIM:To compare the visual perception(color and chromatic-achromatic contrast vision)of a small cohort of COVID-19 patients at the time of infection and after 6mo with that of a healthy population matched for sex and ***:A total of 25 patients(9 females,16 males,mean age:54±10y)with COVID-19 hospitalized in the COVID-19 Unit of the University Clinical Hospital of Valladolid were recruited for this preliminary *** perception,as determined by monocular measurement of contrast sensitivity function(CSF)and color vision was assessed in each patient using the Optopad *** results obtained were then compared with those of a sample of 16 age-and sex-matched healthy controls(5 females,11 males,mean age:50±6y)in which the same measurement procedure was *** significant differences between groups were assessed using the Mann-Whitney U *** were repeated after a minimum follow-up period of 6mo and statistically significant differences between the two time points in each group were assessed using the Wilcoxon signed rank ***:Discrimination thresholds(color and chromatic-achromatic contrast vision)and their corresponding sensitivity,calculated as the inverse of the discrimination threshold,were *** of the data revealed higher contrast threshold results(i.e.,worse contrast sensitivity)in the COVID-19 group than in the control group for all spatial frequencies studied in the Optopad-CSF achromatic test and most of the spatial frequencies studied in the Optopad-CSF chromatic test for the red-green and blue-yellow *** addition,color threshold results in the COVID-19 group were also significantly higher(i.e.,worse color sensitivity)for almost all color mechanisms studied in the Optopad-Color *** 6mo,most of the differences found between the groups were maintained despite COVID-19 ***:The present results provide preliminary evidence that visual perception may be impaired in COVID-19

关键词： SARS-CoV-2 COVID-19 visual perception contrast sensitivity function color vision