检索结果-内蒙古大学图书馆

ieee 15th Pacific visualization symposium (PacificVis)

作者： Klacansky, Pavol Miao, Haichao Gyulassy, Attila Townsend, Andrew Champley, Kyle Tringe, Joseph Pascucci, Valerio Bremer, Peer-Timo Univ Utah SCI Inst Salt Lake City UT 84112 USA LLNL Livermore CA USA

ISBN: (纸本)9781665423359

Advanced manufacturing techniques, such as additive manufacturing, enable the design of increasingly complex components for a wide range of industrial applications. However, this complexity makes qualification of the parts, determining whether a part is within some margin of error from the initial design, difficult. To inspect and qualify complex internal geometries that are not accessible with an external probe, parts are typically scanned with computed tomography (CT), and manually compared to the computer-aided design (CAD) model using visual inspections. Matching the CAD model to the 3D reconstructed object is challenging in a traditional desktop environment due to the lack of depth perception and 3D interaction. An additional challenge comes from the geometric complexity of CAD meshes and large-scale CT scans. We present a virtual reality (VR) system for manual qualification, providing a novel defect visualization method. First, we describe a semiautomatic CAD-to-Scan Registration approach in VR using a finite element mesh. Second, we introduce the Defect Box, which enables full-resolution inspection for massive scans and CAD-CT comparison of local defect regions. Finally, our system includes intuitive 3D Metrology methods that enable natural interactions for the measurement of features and defects in VR. We demonstrate our approach on both real and synthetic data and discuss feedback from four expert users in nondestructive qualification.

关键词： Human-centered computing visualization visualization systems and tools Human-centered computing visualization visualization application domains Scientific visualization Human-centered computing visualization Empirical studies in visualization

来源：评论

学校读者我要写书评

暂无评论

Boosting Performance of Visual Servoing Using Deep Reinforcement Learning From Multiple Demonstrations

引用

ieee ACCESS 2023年 11卷 26512-26520页

作者： Aflakian, Ali Rastegharpanah, Alireza Stolkin, Rustam Univ Birmingham Dept Met & Mat Sci Birmingham B15 2TT England Quad One Faraday Inst Harwell Sci & Innovat Campus Didcot OX11 0RA England

In this study, knowledge of multiple controllers was used and combined with deep reinforcement learning (RL) to train a visual servoing (VS) technique. Deep RL algorithms were successful in solving complicated control problems, however they generally require a large amount of data before they achieve an acceptable performance. We developed a method that generates online hyper-volume action bounds from demonstrations of multiple controllers (experts) to address the issue of insufficient data in RL. The agent then continues to explore the created bounds to find more optimized solutions and gain more rewards. By doing this, we cut out pointless agent explorations, which results in a reduction in training time as well as an improvement in performance of the trained policy. During the training process, we used domain randomization and domain adaptation to make the VS approach robust in the real world. As a result, we showed a 51% decrease in training time to achieve the desired level of performance, compared to the case when RL was used solely. The findings showed that the developed method outperformed other baseline VS methods (image-based VS, position-based VS, and hybrid-decoupled VS) in terms of VS error convergence speed and maintained higher manipulability.

关键词： Cameras Robots Visual servoing Training Reinforcement learning visualization Task analysis reinforcement learning online action bounding reinforcement learning from demonstrations manipulability

来源：评论

学校读者我要写书评

暂无评论

LIV-GaussMap: LiDAR-Inertial-Visual Fusion for Real-Time 3D Radiance Field Map Rendering

引用

ieee ROBOTICS AND AUTOMATION LETTERS 2024年第11期9卷 9765-9772页

作者： Hong, Sheng He, Junjie Zheng, Xinhu Zheng, Chunran Hong Kong Univ Sci & Technol Dept Elect Comp Engn Hong Kong Peoples R China Hong Kong Univ Sci & Technol Syst Hub Guangzhou 511453 Peoples R China Univ Hong Kong Dept Mech Engn Hong Kong Peoples R China

We introduce an integrated precise LiDAR, Inertial, and Visual (LIV) multimodal sensor fused mapping system that builds on the differentiable Gaussians to improve the mapping fidelity, quality, and structural accuracy. Notably, this is also a novel form of tightly coupled map for LiDAR-visual-inertial sensor fusion. This system leverages the complementary characteristics of LiDAR and visual data to capture the geometric structures of large-scale 3D scenes and restore their visual surface information with high fidelity. The initialization for the scene's surface Gaussians and the sensor's poses of each frame are obtained using a LiDAR-inertial system with the feature of size-adaptive voxels. Then, we optimized and refined the Gaussians using visual-derived photometric gradients to optimize their quality and density. Our method is compatible with various types of LiDAR, including solid-state and mechanical LiDAR, supporting both repetitive and non-repetitive scanning modes. Bolstering structure construction through LiDAR and facilitating real-time generation of photorealistic renderings across diverse LIV datasets. It showcases notable resilience and versatility in generating real-time photorealistic scenes potentially for digital twins and virtual reality, while also holding potential applicability in real-time SLAM and robotics domains. We release our software and hardware and self-collected datasets on Github to benefit the community.

关键词： Three-dimensional displays Laser radar Point cloud compression Harmonic analysis visualization Cloud computing Simultaneous localization and mapping LiDAR multi-sensor fusion mapping radiance field 3D gaussian splatting

来源：评论

学校读者我要写书评

暂无评论

POTENTIAL OF DEEP LEARNING FOR FOREST HEIGHT ESTIMATION FROM TANDEM-X BISTATIC INSAR data

POTENTIAL OF DEEP LEARNING FOR FOREST HEIGHT ESTIMATION FROM...

引用

ieee International Geoscience and Remote Sensing symposium (IGARSS)

作者： Carcereri, Daniel Rizzoli, Paola Ienco, Dino Bruzzone, Lorenzo German Aerosp Ctr DLR Microwaves & Radar Inst Cologne Germany Univ Trento UNITN Trento Italy Univ Montpellier Natl Res Inst Agr Food & Environm INRAE Montpellier France

ISBN: (纸本)9798350320107

large-scale and up-to-date canopy height model (CHM) estimates are key to forest resources assessment and disturbance analysis. In this work we present an investigation of the potential of Deep Learning (DL) for the regression of forest height from TanDEM-X bistatic InSAR data. We propose a novel fully convolutional neural network (CNN) framework, trained and tested on four tropical sites in Gabon, Africa, together with a series of experiments for assessing the impact of different input features with specific focus on bistatic InSAR. The obtained results are extremely promising and already in line with state-of-the-art methods based on theoretical modelling, with the remarkable advantage of requiring only one single TanDEM-X acquisition at inference time.

关键词： forest monitoring forest height deep learning InSAR TanDEM-X

来源：评论

学校读者我要写书评

暂无评论

Enhanced Control of WLCSP Wafer Dicing through Big data Automation and analysis 40

Enhanced Control of WLCSP Wafer Dicing through Big Data Auto...

引用

40th ieee International Electronics Manufacturing Technology, IEMT 2024

作者： Seah, J.W. Shong, L.M. Azhar, Arisha Mohd Choy, Kevin Nxp Semiconductors Global Osat Package Engineering Kuala Lumpur Malaysia Nxp Semiconductors Kuala Lumpur Malaysia

ISBN: (纸本)9798350388824

Wafer dicing is a crucial step in the semiconductor industry, particularly with blade sawing leading to small PPM (Parts Per Million) of chip and crack defects. This issue is intensified in Wafer Level Chip Scale Package (WLCSP) devices as die sizes decrease and thicknesses become thinner. Ensuring quality without compromising device shipment requires meticulous control over the wafer dicing process. While Fault Detection Classification (FDC) is a common method for enhanced control, its high setup costs and capital requirements can be prohibitive. This paper proposes a cost-effective alternative, demonstrating the team's approach of automating machine data logs from the wafer dicing machine for monitoring. Control is achieved through statistical analytical techniques, offering a proactive methodology for problem-solving and process improvement. The paper outlines a Proof of Concept with four main steps: automated machine data log, data pre-processing, algorithm investigation and visualization/package solution for ad-hoc analysis. The resulting dashboard facilitates monitoring of key dicing and blade input /output responses, incorporating statistical analyses such as outlier analysis and comparative methods for mean and variance. © 2024 ieee.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Putting Annotations to the Test

Putting Annotations to the Test

引用

25th Eurographics Conference on visualization, EuroVis 2023

作者： Becker, F. Ertl, T. University of Stuttgart Institute for Visualization and Interactive Systems Germany

ISBN: (纸本)9783038682202

When users work with interactive visualization systems, they get to see more accessible representations of raw data and interact with these, e.g. by filtering the data or modifying the visualization parameters like color. Internal representations such as hunches about trends, outliers or data points of interest, relationships and more are usually not visualized and integrated in systems, i.e. they are not externalized. In addition, how externalizations in visualization systems can affect users in terms of memory, post-analysis recall, speed or analysis quality is not yet completely understood. We present a visualization-agnostic externalization framework that lets users annotate visualizations, automatically connect them to related data and store them for later retrieval. In addition, we conducted a pilot study to test the framework’s usability and users’ recall of exploratory analysis results. In two tasks, one without and one with annotation features available, we asked participants to answer a question with the help of visualizations and report their findings with concrete examples afterwards. Qualitative analysis of the summaries showed that there are only minor differences in terms of detail or completeness, which we suspect is due to the short task time and consequently more shallow analyses made by participants. We discuss how to improve our framework’s usability and modify our study design for future research to gain more insight into externalization effects on post-analysis recall. © 2023 The Authors.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

Shopping Review data analysis Based on BP Neural Network Modeling 6

Shopping Review Data Analysis Based on BP Neural Network Mod...

引用

2023 ieee 6th International Conference on Information Systems and Computer Aided Education, ICISCAE 2023

作者： Wang, Ziqian Yang, Hao Deng, Yuhong Hunan University Changsha China

ISBN: (纸本)9798350313444

The proliferation of e-commerce platforms in the digital age has generated a large number of consumer reviews that are critical for informing consumers and merchants. To this end, our research introduces a sophisticated mathematical framework for in-depth analysis of textual data from e-commerce reviews. The aim of this paper is to develop a mathematical model that combines word frequency statistics, word cloud visualization, sentiment analysis and prediction techniques. The study validates the validity and reliability of the model in e-commerce decision making and analysis. © 2023 ieee.

关键词： BP neural network E-commerce semantic parsing word frequency

来源：评论

学校读者我要写书评

暂无评论

CELL NUCLEI SEGMENTATION USING DEEP HYBRID REPRESENTATION LEARNING FOR 2D AND 3D MICROSCOPY IMAGES 21

CELL NUCLEI SEGMENTATION USING DEEP HYBRID REPRESENTATION LE...

引用

21st ieee International symposium on Biomedical Imaging (ISBI)

作者： Meyer, J. Dong, X. Rohr, K. Heidelberg Univ Biomed Comp Vision Grp BioQuant IPMB Heidelberg Germany

ISBN: (纸本)9798350313345;9798350313338

Cell segmentation is a central task in biomedical image analysis. We introduce a 3D deep neural network for 3D cell nuclei segmentation that performs multi-task learning to generate different representations from 3D microscopy images. The network exploits information about cell regions, cell contours, and cell distances. It consists of a 3D Residual U-Net with Squeeze-and-Excitation operations and is trained with a recently introduced loss function that suppresses image regions away from cell borders. To improve cell splitting, we propose a novel representation named signed Instance Distance. Cell instance segmentation is achieved by combining the learned representations to determine cell seeds for a watershed algorithm. We also introduce a 2D version of the network. The method was applied to large-scale 3D micro-CT and 3D electron microscopy datasets from NucMM as well as to 2D fluorescence and phase-contrast microscopy datasets from the Cell Tracking Challenge. For the 3D datasets, the method achieves a large improvement compared to existing methods. For the 2D datasets, the method yields the best segmentation accuracy out of 39 methods for one of the datasets.

关键词： Biomedical imaging 3D image data cell instance segmentation deep learning electron microscopy micro-CT light microscopy

来源：评论

学校读者我要写书评

暂无评论

EchoGuide: Active Acoustic Guidance for LLM-Based Eating Event analysis from Egocentric Videos

EchoGuide: Active Acoustic Guidance for LLM-Based Eating Eve...

引用

ACM International Joint Conference on Pervasive and Ubiquitous Computing / ACM International symposium on Wearable Computers (UbiComp/ISWC)

作者： Parikh, Vineet Mahmud, Saif Agarwal, Devansh Li, Ke Guimbretiere, Francois Zhang, Cheng Cornell Univ Ithaca NY 14850 USA

ISBN: (纸本)9798400710599

Self-recording eating behaviors is a step towards a healthy lifestyle recommended by many health professionals. However, the current practice of manually recording eating activities using paper records or smartphone apps is often unsustainable and inaccurate. Smart glasses have emerged as a promising wearable form factor for tracking eating behaviors, but existing systems primarily identify when eating occurs without capturing details of the eating activities (E.g., what is being eaten). In this paper, we present EchoGuide, an application and system pipeline that leverages low-power active acoustic sensing to guide head-mounted cameras to capture egocentric videos, enabling efficient and detailed analysis of eating activities. By combining active acoustic sensing for eating detection with video captioning models and large-scale language models for retrieval augmentation, EchoGuide intelligently clips and analyzes videos to create concise, relevant activity records on eating. We evaluated EchoGuide with 9 participants in naturalistic settings involving eating activities, demonstrating high-quality summarization and significant reductions in video data needed, paving the way for practical, scalable eating activity tracking.

关键词： Eating Detection Acoustic Sensing Activity Recognition Foundation Models

来源：评论

学校读者我要写书评

暂无评论

THREE-DIMENSIONAL NUCLEI SYNTHESIS FOR FLUORESCENCE MICROSCOPY IMAGE analysis 20

THREE-DIMENSIONAL NUCLEI SYNTHESIS FOR FLUORESCENCE MICROSCO...

引用

20th ieee International symposium on Biomedical Imaging (ISBI)

作者： Wu, Liming Chen, Alain Salama, Paul Dunn, Kenneth W. Delp, Edward J. Purdue Univ Video & Image Proc Lab Sch Elect & Comp Engn W Lafayette IN 47907 USA Indiana Univ Purdue Univ Dept Elect & Comp Engn Indiana PA USA Indiana Univ Div Nephrol Sch Med Indiana PA USA

ISBN: (纸本)9781665473583

Three-dimensional tissue cytometry is an important technique for quantitative analysis of cell structures in large fluorescence microscopy volumes. Accurate nuclei detection and segmentation is an important step for 3D tissue cytometry. Deep learning methods have shown promising results for nuclei detection and segmentation. However, manually annotating ground truth for training deep learning methods is labor-intensive and not practical for large 3D volumes. In this paper, we propose a 3D nuclei synthesis method, known as 3DSpCycleGAN, for generating 3D ground truth volumes along with corresponding synthetic microscopy volumes. Experimental results using fluorescence microscopy volumes demonstrate that our method generates more realistic 3D volumes when evaluated both visually and quantitatively than previously reported. We also show that using the synthetic volumes generated by 3DSpCycleGAN as training data improves segmentation accuracy for deep learning segmentation techniques.

关键词： synthetic data generation generative adversarial networks nuclei segmentation fluorescence microscopy

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：