检索结果-内蒙古大学图书馆

IEEE Transactions on Biometrics, Behavior, and Identity Science 2024年第1期7卷 1-2页

作者： Naser Damer Weihong Deng Jianjiang Feng Vishal M. Patel Ajita Rattani Mark Nixon Smart Living & Biometric Technologies Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China Department of Automation Tsinghua University Beijing China Department of Electrical and Computer Engineering Johns Hopkins University Baltimore MD USA Department of Computer Science and Engineering College of Engineering University of North Texas Denton TX USA

来源：评论

学校读者我要写书评

暂无评论

Synthetic image rendering solves annotation problem in deep learning nanoparticle segmentation

arXiv

引用

arXiv 2020年

作者： Mill, Leonid Wolff, David Gerrits, Nele Philipp, Patrick Kling, Lasse Vollnhals, Florian Ignatenko, Andrew Jaremenko, Christian Huang, Yixing de Castro, Olivier Audinot, Jean-Nicolas Nelissen, Inge Wirtz, Tom Maier, Andreas Christiansen, Silke Institute of Optics Information and Photonics Friedrich-Alexander-University Erlangen-Nuremberg Erlangen Germany Pattern Recognition Lab Friedrich-Alexander-University Erlangen-Nuremberg Erlangen Germany Health Unit Flemish Institute for Technological Research Mol Belgium Institut für Nanotechnologie und korrelative Mikroskopie Forchheim Germany Advanced Instrumentation for Ion Nano-Analytics Materials Research and Technology Department Luxembourg Institute of Science and Technology Belvaux Luxembourg Physics Department Free University Berlin Germany Fraunhofer Institute for Ceramic Technologies and Systems Dresden Germany

Nanoparticles occur in various environments as a consequence of man-made processes, which raises concerns about their impact on the environment and human health. To allow for proper risk assessment, a precise and statistically relevant analysis of particle characteristics (such as e.g. size, shape and composition) is required that would greatly benefit from automated image analysis procedures. While deep learning shows impressive results in object detection tasks, its applicability is limited by the amount of representative, experimentally collected and manually annotated training data. Here, we present an elegant, flexible and versatile method to bypass this costly and tedious data acquisition process. We show that using a rendering software allows to generate realistic, synthetic training data to train a state-of-the art deep neural network. Using this approach, we derive a segmentation accuracy that is comparable to man-made annotations for toxicologically relevant metal-oxide nanoparticle ensembles which we chose as examples. Our study paves the way towards the use of deep learning for automated, high-throughput particle detection in a variety of imaging techniques such as microscopies and spectroscopies, for a wide variety of studies and applications, including the detection of plastic micro- and nanoparticles. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Correlative X-ray and electron tomography for scale-bridging, quantitative analysis of complex, hierarchical particle systems

Tomography of Materials and Structures

引用

Tomography of Materials and Structures 2025年

作者： Alexander Götz Fabian Lutter Dennis Simon Possart Daniel Augsburger Usman Arslan Sabrina Pechmann Carmen Rubach Moritz Buwen Umair Sultan Alexander Kichigin Johannes Böhmer Nora Vorlaufer Peter Suter Tor Hildebrand Matthias Thommes Peter Felfer Nicolas Vogel Katharina Breininger Silke Christiansen Benjamin Apeleo Zubiri Erdmann Spiecker Institute of Micro- and Nanostructure Research (IMN) & Center for Nanoanalysis and Electron Microscopy (CENEM) Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg IZNF Cauerstraße 3 Erlangen Germany Fraunhofer-Institute for Ceramic Technologies and Systems – Correlative Microscopy and Materials Data Äußere Nürnberger Straße 62 Forchheim Germany Professur für Informatik (Pattern Recognition) Center for AI and Data Science (CAIDAS) Julius-Maximilians-Universität Würzburg John-Skilton-Str. 4a Würzburg Germany Institute of Particle Technology Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg Cauerstraße 4 Erlangen Germany Institute for General Materials Properties MSEI Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg Martenstraße 5 Erlangen Germany Lucid Concepts AG Zürich Switzerland Institute of Separation Science and Technology Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg Egerlandstraße 3 Erlangen Germany

This study presents a comprehensive workflow for investigating particulate materials through combined 360° electron tomography (ET), nano-computed X-ray tomography (nanoCT), and micro-computed X-ray tomography (microCT), alongside a versatile sample preparation routine. The workflow enables the investigation of size, morphology, and pore systems across multiple scales, from individual particles to large hierarchical structures. A customized tapered sample shape is created using focused ion beam milling to optimize the field of view for each imaging technique. This design enables high-resolution analysis of small volumes containing single particles using nanoCT and large-scale studies of thousands of particles for statistical significance using microCT. By correlating data from identical locations across different microCT and nanoCT imaging modalities - without any additional preparation that could affect the sample in between - the presented approach improves the precision of quantitative analyses. The study highlights the importance of cross-scale, correlative three-dimensional microscopy for a comprehensive understanding of complex hierarchical materials. Precise data registration, segmentation using machine learning, and multimodal imaging techniques are crucial for unlocking insights into process-structure-property relationships and thus to optimize functional, hierarchical materials.

关键词： nanoCT microCT electron tomography correlative microscopy scale-bridging tomography identical location machine learning segmentation pore and particle analysis

来源：评论

学校读者我要写书评

暂无评论

Front Cover: Synthetic Image Rendering Solves Annotation Problem in Deep Learning Nanoparticle Segmentation (Small Methods 7/2021)

引用

Small Methods 2021年第7期5卷

作者： Leonid Mill David Wolff Nele Gerrits Patrick Philipp Lasse Kling Florian Vollnhals Andrew Ignatenko Christian Jaremenko Yixing Huang Olivier De Castro Jean-Nicolas Audinot Inge Nelissen Tom Wirtz Andreas Maier Silke Christiansen Pattern Recognition Lab Friedrich-Alexander-University Erlangen-Nuremberg 91058 Erlangen Germany Institute of Optics Information and Photonics Friedrich-Alexander-University Erlangen-Nuremberg 91058 Erlangen Germany Institut für Nanotechnologie und korrelative Mikroskopie 91301 Forchheim Germany Health Unit Flemish Institute for Technological Research Mol 2400 Belgium Advanced Instrumentation for Ion Nano-Analytics Materials Research and Technology Department Luxembourg Institute of Science and Technology Belvaux L-4422 Luxembourg Physics Department Free University 14195 Berlin Germany Correlative Microscopy and Material Data Department Fraunhofer Institute for Ceramic Technologies and Systems 01277 Dresden Germany

来源：评论

学校读者我要写书评

暂无评论

A modified version of StaMPS for the detection of localized surface displacement 8

A modified version of StaMPS for the detection of localized ...

引用

8th European Conference on Synthetic Aperture Radar, EUSAR 2010

作者： Alexander, Schunert Markus, Even Uwe, Sorgel Karsten, Schulz Institute of Photogrammetry and GeoInformation Leibniz University Hanover Germany Fraunhofer Research Institute for Optronics and Patter Recognition Ettlingen Germany

ISBN: (纸本)9783800732722

In the last decade the Persistent Scatterer (PS) technique became a valuable tool for the estimation of surface deformation from stacks of differential interferograms. In order to extract the deformation with reasonable accuracy, PS methods restrict the analysis to a set of radar resolution cells showing a stable phase behaviour. This is done by estimation and evaluation of the phase noise. However, estimation of the phase noise requires assumptions about the spatio-temporal behaviour of all other phase contributions, underlying the noise term. While general principles apply for most phase contributions like those due to orbit errors and atmosphere the deformation phase often demands specific modelling. Within the Stanford Method for Persistent Scatterers (StaMPS) the deformation phase is assumed to be correlated in space and in time. This constraint leads to an underestimation of the quality of a resolution cell undergoing localized deformation, as this deformation is interpreted as phase noise. We propose an extension to StaMPS coping with localized deformation by only presuming correlation in time. The method is applied to a TerraSAR-X data stack acquired over a test site in Germany. In order to be capable to compare the results with ground truth, height-adjustable corner reflectors were placed within the imaged scene. Every comer refector is adjusted in accordance with a predefined patter. The obtained results are in good agreement with this reference data. © VDE VERLAG GMBH · Berlin · Offenbach.

关键词： Phase noise

来源：评论

学校读者我要写书评

暂无评论

Atmospheric phase screen-estimation for PSInSAR applied to TerraSAR-X high resolution spotlight-data

Atmospheric phase screen-estimation for PSInSAR applied to T...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Markus Even Alexander Schunert Karsten Schulz Uwe Soergel Fraunhofer Research Institute of Optronics and Pattern Recognition Ettlingen Germany Institute of Photogrammetry and GeoInformation Leibniz Universität Hannover Germany

The PSInSAR technique, invented by Ferretti et. al. ten years ago, meanwhile has proven it's capability for very precise measurement of surface deformations. To achieve this, the influence of the atmospheric phase screen (APS) has to be removed. We investigated the APS for two series of TerraSAR-X high resolution spotlight data of a scene in Bavaria. Our approach was to consider the APS as composed of a phase ramp, a part stratified with height and a turbulent component. We estimated the turbulent component via kriging. The variograms show for short distances a regime which is not visible for lower resolutions. In this paper we discuss the choice of appropriate variogram models with respect to our data.

关键词： Atmospheric modeling Estimation Data models Delay Atmospheric measurements Orbits

来源：评论

学校读者我要写书评

暂无评论

Detection and tracking of objects with direct integration of perception and expectation

Detection and tracking of objects with direct integration of...

引用

2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009

作者： Jüngling, Kai Arens, Michael Research Institute for Optronics and Pattern Recognition Ettlingen Germany

ISBN: (纸本)9781424444427

One of the main challenges in video-based multi-target tracking is the consistent maintenance of object identities over time. We present a novel approach to that challenge that integrates tracking and detection in a single process. We thereby inherently solve the identity problem and gain additional stability of the object detection performance. For that purpose, we extend a state-of-the-art local-feature based object detector by integrating expectations resulting from tracking directly into the detection procedure on the level of features. By that combination of newly gathered and expected local features we are able to directly integrate new data-evidence with object knowledge collected in the past without changing the detection approach itself. Since our tracking approach is solely based on local features, without employing other features like color or shape, it works independently of underlying video-data characteristics and preserves the general applicability independent of object-class specifics. ©2009 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Segmentation and Fusion of Building Features Based on InSAR and Optical Data

Segmentation and Fusion of Building Features Based on InSAR ...

引用

SPIE Conference on Remote Sensing for Environmental Monitoring, GIS Applications, and Geology IX

作者： Thiele, A. Wegner, J. D. Cadario, E. Schulz, K. Soergel, U. FGAN-Research Institute for Optronics and Pattern Recognition (Germany) Leibniz Univ. Hannover (Germany)

ISBN: (纸本)9780819477835

The new generation of space borne SAR sensors provides geometric resolution of one meter, airborne systems even higher. In this high resolution data many features of urban objects become visible, which were beyond the scope of radar remote sensing only a few years ago. Focusing on elevated objects (e.g., urban area), layover, and occlusion issues inevitably arise because of the side-looking SAR sensor principle. In order to support interpretation, SAR data are often analyzed using additional information provided by maps or other remote sensing imagery. The focus of this paper is on building extraction in urban scenes by means of combined InSAR data and optical aerial imagery.

关键词： Remote Sensing Fusion Feature Extraction InSAR Data Optical Data Urban Area

来源：评论

学校读者我要写书评

暂无评论

A new triangulation-based method for disparity estimation in image sequences

引用

16th Scandinavian Conference on Image Analysis, SCIA 2009

作者： Bulatov, Dimitri Wernerus, Peter Lang, Stefan Research Institute for Optronics and Pattern Recognition Gutleuthausstr. 1 76275 Ettlingen Germany

ISBN: (纸本)3642022294

We give a simple and efficient algorithm for approximating computation of disparities in a pair of rectified frames of an image sequence. The algorithm consists of rendering a sparse set of correspondences, which are triangulated, expanded and corrected in the areas of occlusions and homogeneous texture by a color distribution algorithm. The obtained approximations of the disparity maps are refined by a semi-global algorithm. The algorithm was tested for three data sets with rather different data quality. The results of the performance of our method are presented and areas of applications and future research are outlined. © 2009 Springer Berlin Heidelberg.

关键词： Triangulation

来源：评论

学校读者我要写书评

暂无评论

Optical limiting performance of nanoparticles in liquid and solid media

Optical limiting performance of nanoparticles in liquid and ...

引用

Electro-Optical and Infrared Systems: Technology and Applications VI

作者： Dengler, S. Ritt, G. Eberle, B. FGAN-FOM Research Institute for Optronics and Pattern Recognition Gutleuthausstr. 1 76275 Ettlingen Germany

ISBN: (纸本)9780819477873

We present our investigation of the optical limiting behaviour of different metal and semiconductor nanoparticles in liquid and solid media. Nonlinear transmission measurements were performed by the use of nanosecond laser pulses at 532 nm and 1064 nm. For the various nanoparticles in liquid media large differences in the limiting response were found. Foremost the solid state samples are promising in terms of laser protection devices. © 2009 SPIE.

关键词： Liquids

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：