检索结果-内蒙古大学图书馆

ieee International conference on Advanced Robotics and Its Social Impacts (ARSO)

作者： Shimoda, Shingo Okajima, Shotaro Fujiwara, Takeshi Hirata, Hitoshi RIKEN Ctr Brain Sci Wako Saitama Japan TOYODA Dosei Co LTD Kiyosu Aichi Japan Nagoya Univ Nagoya Aichi Japan

ISBN: (纸本)9781665479660

Visual and auditory modalities are mainly used for the current online communications. Even though we can communicate with others using these modalities, we sometimes feel that something is lacking to satisfy the communication completely. We think that the factors that are unconsciously shared in face-to-face communication should play an important role for further satisfaction beyond the communication with vision and audio. The purpose of this special session is to clarify this point and discuss the killer application that can realize better communication beyond video and audio modalities. Remote palpation can be one of the important starting points of these discussions. We have so far clarified that the two signal pathways are simultaneously activated for completing the palpation, and the medical conditions are unconsciously shared between doctor and patient through palpation. This process should be an important model case when palpation is conducted online. In this special session, we introduce not only palpation but also other novel approaches to discuss the importance for the satisfaction of the communication.

关键词： visualization Medical conditions conferences Robots

来源：评论

学校读者我要写书评

暂无评论

Enhanced Simulation and Analysis of Air Pollutants Using Multi-Platform HPC and In-Situ visualization

Enhanced Simulation and Analysis of Air Pollutants Using Mul...

引用

ieee International conference on Cluster Computing Workshops and Posters (CLUSTER WORKSHOPS)

作者： Chongke Bi Fumiyoshi Shoji Kenji Ono Naohisa Sakamoto Jorji Nonaka Honggang Yin Wenjuan Cui Tianjin University RIKEN R-CCS Kyushu University Kobe University China Meteorological Administration Chinese Academy of Sciences

ISBN: (数字)9798350383454

ISBN: (纸本)9798350383461

Based on the strengths of both China and Japan in high-performance computing (HPC), this paper presents a collaborative project between the two countries. The project aims to develop a cross-platform atmospheric pollution simulation system and a visual analytics framework that can operate on HPC infrastructures in both sides. The project's objective is to enhance the precision of pollution simulations, and fulfilling the needs of analyzing pollution sources. The workflow comprises four segments: generation of high-resolution initial field data, pollutant simulation, in-situ visualization, and pollutant tracing. Utilizing the sparse observational data from the Meteorologi-cal Bureau of China, we construct high-resolution initial field data. By adjusting model parameters through intricate external source modeling, we improve simulation accuracy. visualization is conducted using Kyoto visualization System (KVS). Ultimately, based on the high-resolution initial fields and visualization results, we achieve pollutant tracing analysis.

关键词： Data analysis Atmospheric modeling conferences Visual analytics High performance computing Computational modeling Data visualization Collaboration Cluster computing Air pollution

来源：评论

学校读者我要写书评

暂无评论

Learning Multi-step Robotic Manipulation Policies from Visual Observation of Scene and Q-value Predictions of Previous Action 39

Learning Multi-step Robotic Manipulation Policies from Visua...

引用

ieee International conference on Robotics and Automation (ICRA)

作者： Kumra, Sulabh Joshi, Shirin Sahin, Ferat Rochester Inst Technol Rochester NY 14623 USA OSARO Inc San Francisco CA 94107 USA Siemens Corp Corp Technol Berkeley CA USA

ISBN: (纸本)9781728196817

In this work, we focus on multi-step manipulation tasks that involve long-horizon planning and considers progress reversal. Such tasks interlace high-level reasoning that consists of the expected states that can be attained to achieve an overall task and low-level reasoning that decides what actions will yield these states. We propose a sample efficient Previous Action Conditioned Robotic Manipulation Network (PAC-RoManNet) to learn the action-value functions and predict manipulation action candidates from visual observation of the scene and action-value predictions of the previous action. We define a Task Progress based Gaussian (TPG) reward function that computes the reward based on actions that lead to successful motion primitives and progress towards the overall task goal. To balance the ratio of exploration/exploitation, we introduce a Loss Adjusted Exploration (LAE) policy that determines actions from the action candidates according to the Boltzmann distribution of loss estimates. We demonstrate the effectiveness of our approach by training PAC-RoManNet to learn several challenging multi-step robotic manipulation tasks in both simulation and real-world. Experimental results show that our method outperforms the existing methods and achieves state-of-the-art performance in terms of success rate and action efficiency. The ablation studies show that TPG and LAE are especially beneficial for tasks like multiple block stacking. Additional experiments on Ravens-10 benchmark tasks suggest good generalizability of the proposed PAC-RoManNet.

关键词： Training visualization Stacking Reinforcement learning Benchmark testing Boltzmann distribution Cognition

来源：评论

学校读者我要写书评

暂无评论

Underwater Corrosive Material Identification and Image Enhancement

Underwater Corrosive Material Identification and Image Enhan...

引用

2025 International conference on Visual Analytics and Data visualization, ICVADV 2025

作者： Keerthana, N.V. Srija, V. Poornima Devi, R. Roopini, B. Sharumathi, J.M. Velalar College of Engineering and Technology Department of Information Technology TamilNadu Erode Thindal India

ISBN: (纸本)9798331521394

One of the most essential problems underwater during the transmission of gas or crude oil through carbon steel pipelines is corroded, it is the critical issue - the subject of numerous research employing a variety of methodologies. The main goal of this research is to create a reliable and competent model that can precisely detect corrosion using certain algorithms specifically underwater image enhancement for corrosion pipeline inspection to improve the input photos, a dependable algorithm is used. The findings of this detection model show that the underwater image enhancement for corrosion pipeline inspection could be easily identified using a resized image and edge detection. © 2025 ieee.

关键词： Pipeline corrosion

来源：评论

学校读者我要写书评

暂无评论

VEHICLE: Validation and Exploration of the Hierarchical Integration of Conflict Event Data

引用

COMPUTER GRAPHICS FORUM 2021年第3期40卷 1-12页

作者： Mayer, B. Lawonn, K. Donnay, K. Preim, B. Meuschke, M. Univ Magdeburg Dept Simulat & Graph Magdeburg Germany Univ Jena Dept Comp Sci Jena Germany Univ Zurich Dept Polit Sci Zurich Switzerland

The exploration of large-scale conflicts, as well as their causes and effects, is an important aspect of socio-political analysis. Since event data related to major conflicts are usually obtained from different sources, researchers developed a semi-automatic matching algorithm to integrate event data of different origins into one comprehensive dataset using hierarchical taxonomies. The validity of the corresponding integration results is not easy to assess since the results depend on user-defined input parameters and the relationships between the original data sources. However, only rudimentary visualization techniques have been used so far to analyze the results, allowing no trustworthy validation or exploration of how the final dataset is composed. To overcome this problem, we developed VEHICLE, a web-based tool to validate and explore the results of the hierarchical integration. For the design, we collaborated with a domain expert to identify the underlying domain problems and derive a task and workflow description. The tool combines both traditional and novel visual analysis techniques, employing statistical and map-based depictions as well as advanced interaction techniques. We showed the usefulness of VEHICLE in two case studies and by conducting an evaluation together with conflict researchers, confirming domain hypotheses and generating new insights.

关键词： CCS Concepts • Human-centered computing → information visualization Geographic visualization visualization toolkits

来源：评论

学校读者我要写书评

暂无评论

Indoor Localization for Quadrotors using Invisible Projected Tags 39

Indoor Localization for Quadrotors using Invisible Projected...

引用

ieee International conference on Robotics and Automation (ICRA)

作者： Li, Jinjie Han, Liang Ren, Zhang Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China Beihang Univ Sino French Engn Sch Beijing 100191 Peoples R China

ISBN: (纸本)9781728196817

Augmented reality (AR) technology has been introduced into the robotics field to narrow the visual gap between indoor and outdoor environments. However, without signals from satellite navigation systems, flight experiments in these indoor AR scenarios need other accurate localization approaches. This work proposes a real-time centimeter-level indoor localization method based on psycho-visually invisible projected tags (IPT), requiring a projector as the sender and quadrotors with high-speed cameras as the receiver. The method includes a modulation process for the sender, as well as demodulation and pose estimation steps for the receiver, where screen-camera communication technology is applied to hide fiducial tags using human vision property. Experiments have demonstrated that IPT can achieve accuracy within ten centimeters and a speed of about ten FPS. Compared with other localization methods for AR robotics platforms, IPT is affordable by using only a projector and high-speed cameras as hardware consumption and convenient by omitting a coordinate alignment step. To the authors' best knowledge, this is the first time screen-camera communication is utilized for AR robot localization.

关键词： Location awareness visualization Robot kinematics Robot vision systems Receivers Cameras Satellite navigation systems

来源：评论

学校读者我要写书评

暂无评论

Flow Synthesis Based Visual Servoing Frameworks for Monocular Obstacle Avoidance Amidst High-Rises 18

Flow Synthesis Based Visual Servoing Frameworks for Monocula...

引用

ieee 18th International conference on Automation Science and Engineering (ieee CASE)

作者： Sankhla, Harshit K. Qureshi, M. Nomaan Narayanan, Shankara, V Mittal, Vedansh Gupta, Gunjan Pandya, Harit Krishna, K. Madhava IIIT Hyderabad Robot Res Ctr Hyderabad India Toshiba Europe Cambridge Res Lab Cambridge England

ISBN: (数字)9781665490429

ISBN: (纸本)9781665490429

We propose a novel flow synthesis based visual servoing framework enabling long-range obstacle avoidance for Micro Air Vehicles (MAV) flying amongst tall skyscrapers. Recent deep learning based frameworks use optical flow to do high-precision visual servoing. In this paper, we explore the question: can we design a surrogate flow for these high-precision visual-servoing methods, which leads to obstacle avoidance? We revisit the concept of saliency for identifying high-rise structures in/close to the line of attack amongst other competing skyscrapers and buildings as a collision obstacle. A synthesised flow is used to displace the salient object segmentation mask. This flow is so computed that the visual servoing controller maneuvers the MAV safely around the obstacle. In this approach, we use a multi-step Cross-Entropy Method (CEM) based servo control to achieve flow convergence, resulting in obstacle avoidance. We use this novel pipeline to successfully and persistently maneuver high-rises and reach the goal in simulated and photo-realistic real-world scenes. We conduct extensive experimentation and compare our approach with optical flow and short-range depth-based obstacle avoidance methods to demonstrate the proposed framework's merit. Additional Visualisation can be found at https://***/view/monocular-obstacle/home

关键词： visualization Navigation Green buildings Buildings Benchmark testing Visual servoing Trajectory

来源：评论

学校读者我要写书评

暂无评论

Comparative visualization of Longitudinal 24-hour Ambulatory Blood Pressure Measurements in Pediatric Patients with Chronic Kidney Disease

Comparative Visualization of Longitudinal 24-hour Ambulatory...

引用

25th Eurographics conference on visualization, EuroVis 2023

作者： Özmen, M. Jabarulla, M.Y. Grabitz, C.R. Melk, A. Wühl, E. Oeltze-Jafra, S. TU Braunschweig Hannover Medical School Peter L. Reichertz Institute for Medical Informatics Germany Hannover Medical School Department of Pediatric Kidney Liver and Metabolic Diseases Germany Heidelberg University Hospital Division of Pediatric Nephrology Center for Pediatrics and Adolescent Medicine Germany

ISBN: (纸本)9783038682202

Pediatric chronic kidney disease (CKD) increases the risk of cardiovascular disease, stroke and other life-threatening conditions. Monitoring blood pressure in CKD patients is crucial to managing these risks. 24-hour ambulatory blood pressure monitoring (ABPM) is recommended for its comprehensive and accurate assessment of blood pressure over 24 hours. Analyzing and comparing 24-hour ABPM data of multiple diagnostic visits is a challenging task. Traditional methods involve comparing individual visits using paper printouts, which can be time-consuming and lacks a systematic overview of deviations over time. In this work, we present a dashboard visualization that allows clinicians (i) to assess the evolution of ABPM data over multiple diagnostic visits, (ii) to compare ABPM data of CKD patients with reference data of a healthy cohort, and (iii) to perform a detailed intra-individual comparison of the ABPM data acquired at two subsequent diagnostic visits. We demonstrate the dashboard in a case study of a patient with mild-to-moderate-stage CKD. © 2023 The Authors.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

On Guiding Visual Attention with Language Specification

On Guiding Visual Attention with Language Specification

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Nasseri, Keyan Petryk, Suzanne Gonzalez, Joseph Dunlap, Lisa Darrell, Trevor Rohrbach, Anna Univ Calif Berkeley Berkeley CA 94720 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

While real world challenges typically define visual categories with language words or phrases, most visual classification methods define categories with numerical indices. However, the language specification of the classes provides an especially useful prior for biased and noisy datasets, where it can help disambiguate what features are task-relevant. Recently, large-scale multimodal models have been shown to recognize a wide variety of high-level concepts from a language specification even without additional image training data, but they are often unable to distinguish classes for more fine-grained tasks. CNNs, in contrast, can extract subtle image features that are required for fine-grained discrimination, but will overfit to any bias or noise in datasets. Our insight is to use high-level language specification as advice for constraining the classification evidence to task-relevant features, instead of distractors. To do this, we ground task-relevant words or phrases with attention maps from a pretrained large-scale model. We then use this grounding to supervise a classifier's spatial attention away from distracting context. We show that supervising spatial attention in this way improves performance on classification tasks with biased and noisy data, including similar to 3-15% worst-group accuracy improvements and similar to 41-45% relative improvements on fairness metrics.

关键词： visualization Computer vision Image recognition Training data Feature extraction Pattern recognition Numerical models

来源：评论

学校读者我要写书评

暂无评论

A MULTI-CHANNEL FAULT information BEARING FAULT DIAGNOSIS METHOD BASED ON IMPROVED VISION TRANSFORMER 14

A MULTI-CHANNEL FAULT INFORMATION BEARING FAULT DIAGNOSIS ME...

引用

14th International conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering, QR2MSE 2024

作者： Liu, Qiang Lai, Hongxi Dai, Zhengwei Chen, Minghao Chen, Peirong Liang, Youlin Hou, Mingxin Xu, Xiaoming Wang, Guangbin School of Mechanical Engineering Guangdong Ocean University Zhanjiang China Guangdong Provincial Key Laboratory of Intelligent Equipment for South China Sea Marine Ranching Guangdong Ocean University Zhanjiang China Guangdong Marine Equipment and Manufacturing Engineering Research Center Zhanjiang China School of Mechanical and Electrical Engineering Lingnan Normal University Zhanjiang China

ISBN: (纸本)9781837242672

Bearings are crucial components of modern mechanical equipment and their failure can lead to equipment downtime, economic losses, and potential threats personal safety. Therefore, it is essential to carry out fault diagnosis of bearings. In this paper, Multichannel Signal Transformer (MST) model is employed for diagnosing bearing faults. Initially, a single vibration signal and two motor current signals are collected and combined into a multichannel signal. This multichannel signal is then used to train and test the MST model. The performance of the MST model is subsequently compared with that of an established one-dimensional CNN. The feasibility of the method is verified by comparing the accuracy and loss function values of the two models in fault diagnosis. Finally, the confusion matrix of the MST model for fault classification is analyzed, and the t-SNE visualization is performed on the features of the fully-connected layer. The results demonstrate that the MST model has a higher accuracy in fault diagnosis. © The Institution of Engineering & Technology 2024.

关键词： Bearings (machine parts)

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：