检索结果-内蒙古大学图书馆

44th Annual international conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC)

作者： Narotamo, Hemaxi Ouarne, Marie Franco, Claudio Areias Silveira, Margarida Univ Lisbon Inst Syst & Robot ISR IST Inst Super Tecn LARSyS Lisbon Portugal Univ Lisbon Fac Med Inst Med Mol Joao Lobo Antunes Lisbon Portugal

ISBN: (数字)9781728127828

ISBN: (纸本)9781728127828

Fluorescence microscopy images of cell organelles enable the study of various complex biological processes. recently, deep learning (dL) models are being used for the accurate automatic analysis of these images. dL models present state-of-the-art performance in many image analysis tasks such as object classification, segmentation and detection. However, to train a dL model a large manually annotated dataset is required. Manual annotation of 3d microscopy images is a time-consuming task and must be performed by specialists in the area. Thus, only a few images with annotations are typically available. recent advances in generative adversarial networks (GANs) have allowed the translation of images with some conditions into realistic looking synthetic images. Therefore, in this work we explore approaches based on GANs to create synthetic 3d microscopy images. We compare four approaches that differ in the conditions of the input image. The quality of the generated images was assessed visually and using a quantitative objective GAN evaluation metric. The results showed that the GAN is able to generate synthetic images similar to the real ones. Hence, we have presented a method based on GANs to overcome the issue of small annotated datasets in the biomedical imaging field.

关键词： Measurement Analytical models Image segmentation Three-dimensional displays Annotations Microscopy Biological system modeling

来源：评论

学校读者我要写书评

暂无评论

Computational design and digital Fabrication 1

引用

international conference on recent advances in Manufacturing, RAM 2020

作者： Kyratsis, Panagiotis Tzotzis, Anastasios Manavis, Athanasios Department of Product and Systems Design Engineering University of Western Macedonia Kila Kozani50100 Greece

ISBN: (数字)9789813344662

ISBN: (纸本)9789813344655

design engineers can benefit by learning to use the programming tools of CAd systems. It is possible to increase their productivity and implement their ideas effectively. Moreover, they can focus on the important product development stage instead of consuming time in routine tasks. In the light of these considerations, the current paper presents the possibilities that derive from the use of the programming resources that are available in different CAd systems, and especially the ones related to product design and fabrication. Two CAd-based applications were developed via such techniques, and the case studies found in this work prove their validity and usefulness. Well-known, commercially available CAd systems were used for these purposes, namely SolidWorks™ and Rhino™. The development of the applications was achieved via the CAd-based programming tools such as the application programming interface of SolidWorks™, by using Visual Basic for Applications programming language, and Python™, a textual programming language combined with Rhino™ 3d modeling tools. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Application programming interface CAd Computational design digital fabrication

来源：评论

学校读者我要写书评

暂无评论

ERROR ANALYSIS OF AIRBORNE MULTISENSORY SYSTEMS

ERROR ANALYSIS OF AIRBORNE MULTISENSORY SYSTEMS

引用

Joint Symposium of ISPRS Commission IV / AutoCarto Annual conference

作者： Toth, C. Grejner-Brzezinska, d. Ohio State Univ Ctr Mapping Columbus OH 43210 USA

One aspect of the recent paradigm shift in geospatial information sciences is that data acquisition and processing systems have moved away from the single sensor-based model to advanced integrated multisensory systems, which typically include imaging and navigation sensors. Active sensors, such as Light detection and Ranging (LidAR) and Interferometric Synthetic Aperture Radar (IFSAR), are routinely used with conventional optical sensing where a new generation of high-performance digital camera systems have been developed in the past few years. The direct georeferencing of the remote sensing platform is usually provided by state-of-the-art navigation technology based on the Global Positioning System/Inertial Measurement Unit (GPS/IMU). As the number of sensors has increased, the error budget calculations for derived geospatial products has become more complex;the number of contributing terms has shown a multi-fold increase. The focus of calibration has shifted from individual sensor calibration to system calibration to consider interrelationships between multiple sensors. At the system calibration level, even the error contributions of in-scene objects play an increased role and must be more carefully considered. Research to date has been primarily focused on individual sensor calibration or calibration of a pair of sensors. The objective of this investigation is to combine the effects of all the sensor and sensor-related errors to obtain the overall error budget of airborne remote sensing sensor suites. The error budget should include all navigation errors, imaging sensor modeling errors, inter-sensor calibration errors, and object space characteristics.

关键词： Error propagation Sensor and system calibration digital camera LidAR Georeferencing

来源：评论

学校读者我要写书评

暂无评论

Effect of micro-scale morphological parameters on meso-scale response of Asphalt Concrete

Effect of micro-scale morphological parameters on meso-scale...

引用

12th ISAP international conference on Asphalt Pavements

作者： Onifade, Ibrahim Jelagin, denis Guarin, Alvaro Birgisson, Bjorn Kringos, Nicole KTH Royal Inst Technol Stockholm Sweden

ISBN: (纸本)9781315736754;9781138026933

With recent advancement in the use of X-Ray Computed Tomography to capture the internal structure of Asphalt Concrete (AC), results have shown several possibilities to account for the distribution of the different phases in the mix and quantify them in a reliable way. The morphology of asphalt mixtures which includes the aggregate size gradation and the distribution of the air-voids and bitumen phase are captured in a single morphological parameter called the Primary Structure (PS) coating thickness-(T-ps). In this study, the effect of variations in the morphological micro-structural property on the mesoscale response of three (3) AC samples is examined using the 3d Finite Element Method (FEM). The AC internal geometry is acquired using X-Ray Computed Tomography (CT);the distribution of the aggregates, mastic and air-voids phase is considered and obtained using digital imaging Processing (dIP) techniques. Using a surface-based cohesive behavior and assuming a predominant adhesive failure at the interface between the mastic and aggregate, a maximum traction criterion is used to obtain the damage propensity of the different mixtures. The result of the analysis shows that the microstructural morphological parameter T-ps adequately captures the meso-scale response of the mixtures;there exist an inverse relationship between mixture strength characterization and the morphological parameter T-ps.

关键词： X-Ray Computed Tomography asphalt concrete morphology digital Image Processing damage micromechanical modeling

来源：评论

学校读者我要写书评

暂无评论

An Efficient deep Landmark detection Network for PLAX EF Estimation Using Sparse Annotations

An Efficient Deep Landmark Detection Network for PLAX EF Est...

引用

conference on Medical imaging - Image-Guided Procedures, Robotic Interventions, and modeling

作者： Goco, Jamie Alexis d. Jafari, Mohammad H. Luong, Christina Tsang, Teresa Abolmaesumi, Purang Univ British Columbia Dept Elect & Comp Engn Vancouver BC Canada Vancouver Gen Hosp Vancouver BC Canada Univ British Columbia Dept Med Vancouver BC Canada

ISBN: (纸本)9781510649446;9781510649439

The parasternal long axis (PLAX) is a routine imaging plane used by clinicians to assess the overall function of the left ventricle during an echocardiogram. Measurements from the PLAX view, in particular left ventricle internal dimension at both end-diastole (LVIdd) and end-systole (LVIds), are significant markers used to identify cardiovascular disease and can provide an estimation of ejection fraction (EF). However, due to the user-dependent nature of echocardiograms, these measurements suffer from a large amount of inter-observer variability, which greatly affect the sensitive formula used to calculate PLAX EF. While few previous works have attempted to reduce this variability by automating LVId measurements, their models not only lack reliable accuracy and precision, but also generally are not suited to be adapted in point-of-care ultrasound (POCUS) which has limited computing resources. In this paper, we propose a fully automatic, light-weight landmark detection network for detecting LVId and rapidly estimating PLAX EF. Our model is built upon recent advances in deep video landmark tracking with extremely sparse annotations.(1) The model is trained on only two frames in the cardiac cine that contain either the LVIdd or LVIds measurements labeled by clinicians. Using data from 34,305 patients for our experiments, the proposed model accurately tracks the contraction of left ventricular walls. Our model achieves a mean absolute error and standard deviation of 2.65 +/- 2.36 mm, 2.77 +/- 2.58 mm, and 8.45 +/- 7.43% for predicting LVIdd length, LVIds length, and PLAX EF, respectively. As a light-weight network with less than 125,000 parameters, our model is extremely accessible for POCUS applications.

关键词： Segmentation Network Video Landmark detection Mobile deployment Left Ventricle Internal dimension Ejection Fraction Echocardiography

来源：评论

学校读者我要写书评

暂无评论

3d Shape-Adapted Garment Generation with Sketches 38th

3D Shape-Adapted Garment Generation with Sketches

引用

38th Computer Graphics international conference (CGI)

作者： Chen, Yijing Xian, Chuhua Jin, Shuo Li, Guiqing South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China BlueFire AI Hong Kong Peoples R China

ISBN: (纸本)9783030890285;9783030890292

Garment generation or reconstruction is becoming extremely demanding for many digital applications, and the traditional process is time-consuming. In recent years, garment reconstruction from sketch leveraging deep learning and principal component analysis (PCA) has made great progress. In this paper, we present a data-driven approach wherein 3d garments are directly generated from sketches combining given body shape parameters. Our framework is an encoder-decoder architecture. In our network, sketch features extracted by denseNet and body shape parameters were encoded to latent code respectively. Then, the new latent code obtained by adding two latent codes of the sketch and human body shape is decoded by a fully convolutional mesh decoder. Our network enables the body shape adapted detailed 3d garment generation by leveraging garment sketch and body shape parameters. With the fully convolutional mesh decoder, the network can show the effect of body shape and sketch on the generated garment. Experimental results show that the fully convolutional mesh decoder we used to reconstruct the garment performs higher accuracy and maintains lots of detail compared with the PCA-based method.

关键词： 3d Garment Reconstruction Sketch-based modeling Body shape adapted Mesh decoder

来源：评论

学校读者我要写书评

暂无评论

Advanced Multi-Spectral Image Processing Techniques for Enhanced Remote Sensing and Comprehensive Environmental Monitoring in diverse Ecosystems

Advanced Multi-Spectral Image Processing Techniques for Enha...

引用

2024 IEEE international conference on recent advances in Science and Engineering Technology, ICRASET 2024

作者： Jagannathan, J. Ponmalar, A. Pandiarajan, Rajkumar Sudha, I. Ramesh, P.S. Vellore Institute of Technology School of Computer Science Engineering and Information Systems Department of Software and Systems Engineering Katpadi Vellore India R.M.K. Engineering College Tamilnadu Chennai India School of Computing Kalasalingam Academy Of Research and Education Department of Information and Technology Krishnankoil Virudhunagar India Saveetha Institute of Medical and Technical Sciences Simats University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350388602

The research is aimed at improvement of multi-spectral image analysis for remote sensing and monitoring the environment at various ecosystems. A combined spectral imagery encompasses several spectrums at a time compared to single spectral imagery that takes only one spectrum at an instance or at a given area to cover all these spectrums. The study employs digital high resolution satellite images and ground based data to quantify the vegetation vigour, water quality, soil characteristics and changes in land cover. Features, indexes, and classification routines are employed to process the data that is collected with the aid of avionics and other peripherals. This provincial level modelling highlights important gains in environmental status, which includes the general improvement in vegetation condition, water quality as well as physical properties of the soil in the province. This study focuses on the complementary possibilities of integration of multi-spectral imaging with other remote sensing technologies and the high performance of data processing. These techniques play significant roles if used to give current and comprehensive information in the management and conservation of the environment as highlighted in the study. © 2024 IEEE.

关键词： data analysis environmental monitoring image processing techniques machine learning Multi-spectral imaging remote sensing soil properties vegetation health water quality

来源：评论

学校读者我要写书评

暂无评论

Clinical implementations of 4d pencil beam scanned particle therapy: Report on the 4d treatment planning workshop 2016 and 2017

引用

PHYSICA MEdICA-EUROPEAN JOURNAL OF MEdICAL PHYSICS 2018年 54卷 121-130页

作者： Trnkova, Petra Knaeusl, Barbara Actis, Oxana Bert, Christoph Biegun, Aleksandra K. Boehlen, Till T. Furtado, Hugo McClelland, Jamie Mori, Shinichiro Rinaldi, Ilaria Rucinski, Antoni Knopf, Antje C. HollandPTC POB 5046 NL-2600 GA Delft Netherlands Erasmus MC POB 5201 NL-3008 AE Rotterdam Netherlands Med Univ Vienna Christian Doppler Lab Med Radiat Res Radiat Oncol Dept Radiat Oncol Div Med Radiat PhysAKH Vienna Austria PSI CH-5232 Villigen Switzerland Friedrich Alexander Univ Erlangen Nurnberg Univ KliniKum Erlangen Dept Radiat Oncol Erlangen Germany Univ Groningen Ctr Adv Radiat Technol KVI Groningen Netherlands UCL Ctr Med Image Comp Dept Med Phys & Biomed London England Natl Inst Radiol Sci Charged Particle Therapy Chiba Japan Lyon 1 Univ F-69622 Villeurbanne France CNRS IN2P3 UMR 5822 F-69622 Villeurbanne France MAASTRO Clin POB 3035 NL-6202 NA Maastricht Netherlands Inst Nucl Phys PAN Krakow Poland Univ Groningen Univ Med Ctr Groningen Dept Radiat Oncol Groningen Netherlands

In 2016 and 2017, the 8th and 9th 4d treatment planning workshop took place in Groningen (the Netherlands) and Vienna (Austria), respectively. This annual workshop brings together international experts to discuss research, advances in clinical implementation as well as problems and challenges in 4d treatment planning, mainly in spot scanned proton therapy. In the last two years several aspects like treatment planning, beam delivery, Monte Carlo simulations, motion modeling and monitoring, QA phantoms as well as 4d imaging were thoroughly discussed. This report provides an overview of discussed topics, recent findings and literature review from the last two years. Its main focus is to highlight translation of 4d research into clinical practice and to discuss remaining challenges and pitfalls that still need to be addressed and to be overcome.

关键词： Proton therapy Moving targets 4d imaging 4d dosimetry

来源：评论

学校读者我要写书评

暂无评论

New perspectives in gamma-ray imaging with CdZnTe/CdTe

New perspectives in gamma-ray imaging with CdZnTe/CdTe

引用

2004 Nuclear Science Symposium, Medical imaging conference, Symposium on Nuclear Power Systems and the 14th international Workshop on Room Temperature Semiconductor X- and Gamma- Ray detectors

作者： Verger, L. drezet, A. Gros d'Aillon, E. Mestais, C. Monnet, O. Montémont, G. dierre, F. Peyret, O. LETI-CEA Recherches Technologiques CEA Grenoble 17 rue des Martyrs 38054 Grenoble Cedex 9 France

Increasing interest in CdTe/CZT for gamma-ray imaging has marked the last ten years with progress in crystal growth, device technology, integrated electronics and signal processing. The purpose of this paper is to present recent advances in these four fields. A new method to grow very large dimension CZT up to 300 mm in diameter is presented. MS-contact process control allows design of very small electrodes (100μm pitch) and results on long-term stability are presented. The development of low-noise front-end integrated electronics and new interconnects technologies have made "pixel detectors" feasible. Significant effort has been focused on reaching high-energy resolution as well as high detection efficiency. The combination of signal processing such as bi-parametric (BP) approaches and electrode design presents an interest in charge loss compensation for a large range of μτ products, tailing reduction due to geometric effect and depth of interaction information. New digital approaches may give drastic advantages to push the limit of spectrometric performance. In the field of gamma-ray applications, homeland security and molecular imaging are the most promising ones. By using a tailored "mixed" electrode and a BP correction, an energy resolution of 1% at 662keV has been demonstrated with CZT based 8×8×15 mm 3 detector. New results of 3d CZT detectors for μPET imaging are presented with a measured coincidence time of 2.6ns FWHM and an expected spatial resolution of 1mm FWTM. © 2004 IEEE.

关键词： imaging techniques

来源：评论

学校读者我要写书评

暂无评论

Multi-scale 3d data Acquisition of Maize 1

引用

11th IFIP WG 5.14 international conference on Computer and Computing Technologies in Agriculture (CCTA)

作者： Wen, Weiliang Guo, Xinyu Lu, Xianju Wang, Yongjian Yu, Zetao Beijing Res Ctr Informat Technol Agr Beijing Peoples R China Beijing Key Lab Digital Plant Beijing Peoples R China

ISBN: (数字)9783030061371

ISBN: (纸本)9783030061371;9783030061364

In recent years, three-dimensional (3d) data acquisition and model reconstruction of plants have been developed as a hot topic of plant scientific researches. However, the morphological structure of plants is very complex and it is hard to describe the details. The data acquisition approaches are diverse for different parts of plants. This study introduces the data acquisition methods of different scales of maize. The grain, leaf and ear, individual plant and maize colony represents the target models for different scales. 3d data acquisition instruments are used to acquire the morphometric of each target. It is found that the organ scale is the simplest to obtain and process. The smallest grain needs high-resolution scanner to acquire the morphological details, while the plant canopy is the hardest one for point cloud process and modeling. The data and reconstructed models are oriented to digital plant, phenotyping analysis, FSPMs research, and popular science education application.

关键词： Maize Three-dimensional scanning Three-dimensional point cloud Phenotypic

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：