检索结果-内蒙古大学图书馆

17th IEEE international conference on Automation Science and Engineering (CASE)

作者： Anand, Harish Rees, Stephen A. Chen, Zhiang Poruthukaran, Ashwin Jose Bearman, Sarah Antervedi, Lakshmi Gana Prasad Das, Jnaneshwar Sch Earth & Space Explorat Tempe AZ 85287 USA Vanderbilt Univ 221 Kirkland Hall Nashville TN 37235 USA

ISBN: (纸本)9781665418737

Simulations play a crucial role in robotics research and education. this paper presents the OpenUAV testbed, an open-source, easy-to-use, web-based, and reproducible software system that enables students and researchers to run robotic simulations on the cloud. We have built upon our previous work and have addressed some of the educational and research challenges associated with the prior work. the critical contributions of the paper to the robotics and automation community are threefold: First, OpenUAV saves students and researchers from tedious and complicated software setups by providing web-browser-based Linux desktop sessions with standard robotics software like Gazebo, ROS, and flight autonomy stack. Second, a method for saving an individual's research work with its dependencies for the work's future reproducibility. third, the platform provides a mechanism to support photorealistic robotics simulations by combining Unity game engine-based camera rendering and Gazebo physics. the paper addresses a research need for photorealistic simulations and describes a methodology for creating a photorealistic aquatic simulation. We also present the various academic and research use-cases of this platform to improve robotics education and research, especially during times like the COVID-19 pandemic, when virtual collaboration is necessary. Github: https://***/Open-UAV/openuav-turbovnc Webpage: https://***

关键词： Cloud computing Automation Robot vision systems Collaboration Software systems Rendering (computer graphics) Reproducibility of results

来源：评论

学校读者我要写书评

暂无评论

Improved analysis of membrane potential oscillations in the network of cells from islet of Langerhans 23

Improved analysis of membrane potential oscillations in the ...

引用

23rd international conference on computer graphics and vision, graphicon 2013

作者： Špelič, Denis Dolenšek, Jurij Stožer, Andraž Rupnik, Marjan Slak Žalik, Borut Mongus, Domen Faculty of Electrical Engineering and Computer Science University of Maribor Smetanova 17 MariborSI-2000 Slovenia Institute of Physiology Faculty of Medicine University of Maribor Slomškov trg 15 MariborSI-2000 Slovenia Centre for Open Innovations and Research University of Maribor Slomškov trg 15 MariborSI-2000 Slovenia

ISBN: (纸本)9785804414024

this paper proposes a new method for the visualisation of changes in the membrane potentials of biological cells, where the low image resolution and high presence of noise within an original series of images (i.e. a video) prevents accurate observations of this natural phenomenon. this method applies an alpha-trimmed mean filter within time-domain for decomposing a series into high and low frequency bands. Θ-mapping is then applied in order to identify and denoise the signal. Finally, the output images are constructed by suppressing the low-frequency band, whilst high-frequencies are emphasised. As shown by the results, visualisation is significantly improved in this way, whilst the signal-characteristics remain well-preserved. © 23rd international conference on computer graphics and vision, graphicon 2013 - conference Proceedings. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Lightweight Monocular Depth Estimation with an Edge Guided Network

Lightweight Monocular Depth Estimation with an Edge Guided N...

引用

international conference on Control, Automation, Robotics and vision (ICARCV)

作者： Xingshuai Dong Matthew A. Garratt Sreenatha G. Anavatti Hussein A. Abbass Junyu Dong School of Engineering and Information Technology University of New South Wales Canberra Australia School of Computer Science and Technology Ocean University of China Qingdao China

ISBN: (纸本)9781665476881

Monocular depth estimation is an important task that can be applied to many robotic applications. Existing methods focus on improving depth estimation accuracy via training increasingly deeper and wider networks, however these suffer from large computational complexity. Recent studies found that edge information are important cues for convolutional neural networks (CNNs) to estimate depth. Inspired by the above observations, we present a novel lightweight Edge Guided Depth Estimation Network (EGD-Net) in this study. In particular, we start out with a lightweight encoder-decoder architecture and embed an edge guidance branch which takes as input image gradients and multi-scale feature maps from the backbone to learn the edge attention features. In order to aggregate the context information and edge attention features, we design a transformer-based feature aggregation module (TRFA). TRFA captures the long-range dependencies between the context information and edge attention features through cross-attention mechanism. We perform extensive experiments on the NYU depth v2 dataset. Experimental results show that the proposed method runs about 96 fps on a Nvidia GTX 1080 GPU whilst achieving the state-of-the-art performance in terms of accuracy.

关键词： Training Image edge detection Aggregates Estimation graphics processing units Feature extraction Transformers

来源：评论

学校读者我要写书评

暂无评论

Efficient Face Detector Using Spatial Attention Module in Real-Time Application on an Edge Device 17th

Efficient Face Detector Using Spatial Attention Module in Re...

引用

17th international conference on Intelligent Computing, ICIC 2021

作者： Putro, Muhamad Dwisnanto Nguyen, Duy-Linh Jo, Kang-Hyun Department of Electrical Electronic and Computer Engineering University of Ulsan Ulsan44616 Korea Republic of

ISBN: (纸本)9783030845216

the practical application requires a vision-based face detector to work in real-time. the robot application uses the face detection method as the initial process for the face analysis system. During its development, it utilizes an edge device to be used to process sensor information. Jetson Nano is a mini portable computer that is easily synchronized with sensors and actuators. However, traditional detectors can work fast on this device but have low performance for occlusion cases, multiple poses, and small faces. On the other hand, CNN-based detectors that implement deep layers are slow to run on low memory GPU devices. In this work, an efficient real-time face detector using a simple spatial attention module was developed to localize faces rapidly. the proposed architecture consists of the backbone module to efficiently extract features, the light connection module to reduce the size of the detection layer, and multi-scale detection to perform prediction of faces on various scales. As a result, the proposed detector achieves competitive performance from state-of-the-art fast detectors on several benchmark datasets. In addition, this efficient detector can run at 55 frames per second in video graphics array resolution on a Jetson Nano. © 2021, Springer Nature Switzerland AG.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of YOLOv4 and SSD Mobilenet V2 for Foreign Object Debris (FOD) Detection at Airport Runway Using Custom Dataset

Performance Analysis of YOLOv4 and SSD Mobilenet V2 for Fore...

引用

international conference on QiR (Quality in Research)

作者： Muhammad Reza Fairuzi Fitri Yuli Zulkifli Faculty of Engineering Universitas Indonesia Depok Indonesia

ISBN: (纸本)9781665496971

Indonesia is a country that has heavy air traffic every day. therefore, safety is a very important thing to pay attention to, one of them is the runway safety. the runway is an important component in aviation activities because aircraft use it for takeoff and landing. Foreign objects or FOD (Foreign Object Debris) could appear on the runway which can cause damage to the aircraft and may result in an accident. therefore, we need a security system that can detect foreign objects in real-time. One approach that can be done is to use computer vision technology by using a camera. this method utilizes Artificial Intelligence (AI) technology for FOD detection. Various methods or algorithms have been developed for computer vision, SSD and YOLO are the most frequently used methods for real-time detection because of their high FPS and accuracy performance. Where in this study it was found that SSD MobileNet V2 can reach up to 12 FPS with mAP 0.5 value of 86.8% and for YOLOv4 can reach up to 31 FPS with mAP 0.5 value of 98.73%.

关键词： computer vision graphics processing units User interfaces Cameras Real-time systems Safety Performance analysis

来源：评论

学校读者我要写书评

暂无评论

A survey on the current state of the art on deep learning 3D reconstruction

A survey on the current state of the art on deep learning 3D...

引用

IEEE international conference on Intelligent computer Communication and Processing (ICCP)

作者： Bogdan Maxim Sergiu Nedevschi Technical University of Cluj-Napoca Cluj-Napoca Romania

ISBN: (纸本)9781665409773

Efficient 3D reconstruction from different kind of inputs is a long standing effort of computer vision. Recent advancements in the field of machine learning, specifically deep learning, have started an interest in studying how well these techniques apply to the 3D reconstruction problem. Current efforts employ two main research directions: techniques applied to a single object, trying to reconstruct the surface as closely as possible from different kind of inputs and techniques applied to scenes made from multiple objects, which deal with topological representations, color, illumination and resource consumption. With a plethora of applications in computer graphics and computer vision, the results given by the deep learning techniques start to gain a serious position in the field of 3D reconstruction, yet no survey exist on the recent advancements on these new techniques. this survey summarizes the recent trend and applications of the deep-learning 3D reconstruction methods. We focus on learnable reconstruction methods from inputs like single image, multi-image and point cloud, using different representations, such as voxels, meshes and signed distance fields. Starting by presenting the datasets used, we follow by showing the main deep learning methods using different representations, presenting advantages and disadvantages. the second half of this survey focuses on scene reconstructions and open problems. Finally we conclude with a discussion of the importance of the 3D reconstruction and its possible applications in different fields such as automotive and mixed reality.

关键词： Deep learning Point cloud compression computer vision Surface reconstruction three-dimensional displays Scalability Mixed reality

来源：评论

学校读者我要写书评

暂无评论

Real Time Pedestrian Detection Using Robust Enhanced Tiny-YOLOv3 17

Real Time Pedestrian Detection Using Robust Enhanced Tiny-YO...

引用

17th IEEE India Council international conference, INDICON 2020

作者： Murthy, Chintakindi Balaram Farukh Hashmi, Mohammad National Institute of Technology Warangal Electronics and Communication Engineering Telangana India

ISBN: (纸本)9781728169163

One of the key components in developing smart cities in countries like India, autonomous pedestrian detection plays a very crucial role in computer vision tasks such as smart video surveillance and intelligent traffic monitoring system. In self-driving cars, real time performance is required without scarifying the detection accuracy, while detecting smaller pedestrians. In the proposed paper, a robust Enhanced Tiny-Yolov3 Network is designed by introducing an anti-residual module which helps to improve network's feature extraction ability. Second, the loss function is improved which reduces bounding box loss error and optimizes the network. third one prediction scale of size 26 x 26 is removed from the Tiny-Yolov3 network so the computational complexity of the network is reduced. the proposed network is trained on the extracted pedestrian images from Pascal Voc-2007 dataset. Experimental results show this network improves the detection accuracy while detecting smaller pedestrians and it still meets the real-time requirements. © 2020 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Preface

Communications in Computer and Information Science

引用

Communications in computer and Information Science 2023年 1815 CCIS卷 v-vii页

作者： de Sousa, A. Augusto Paljic, Alexis Hurter, Christophe Farinella, Giovanni Maria Bouatouch, Kadi Debattista, Kurt Ziat, Mounia Purchase, Helen Radeva, Petia University of Porto Porto Portugal Mines ParisTech Paris France Toulouse France Department of Mathematics University of Catania Catania Italy IRISA University of Rennes 1 Rennes France University of Warwick Coventry United Kingdom Bentley University WalthamMA United States Monash University MelbourneVIC Australia Computer Vision Center University of Barcelona Barcelona Spain

来源：评论

学校读者我要写书评

暂无评论

Calculation of the probabilistic safety analysis and reliability by the fault trees and event trees methods 29

Calculation of the probabilistic safety analysis and reliabi...

引用

29th international conference on computer graphics and vision, graphicon 2019

作者： Berberova, M.A. Dmitriev, A.V. Golubkov, A.V. Elizarov, A.I. International Nuclear Safety Center Moscow Russia Open Joint Stock Company «All-Russian Research Institute for Nuclear Power Plants Operation» Moscow Russia

One of the main requirements for ensuring a high level of safety and economic efficiency of nuclear power units at all stages of the life cycle - designing new ones, operating existing power units and decommissioning them - is a probabilistic safety analysis of nuclear power units. the most widely used method for probabilistic safety analysis is the fault tree method. NPP power units are a complex system consisting of a large number of units of equipment, systems and units that are interconnected functionally and affect each other. In addition, to increase the adequacy of the developed probabilistic model of a power unit, it is necessary to take into account equipment failures for general reasons and the human factor. the resulting in-depth probabilistic models of power units can contain tens of thousands of fault trees and, as a result, hundreds or more of thousands of minimum sections and require lengthy calculations to obtain acceptable accuracy of the results. this complicates the application of this method, especially when monitoring risk in real time, when it is necessary to promptly make changes to the model and assess the impact of these changes on the current risk. the novelty of the project is the use of a modified modularization method, which significantly accelerates the generation of many minimal sections. Copyright © 2019 for this paper by its authors.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Risk-informed security system. the use of surveillance cameras for the particularly hazardous facilities safety 29

Risk-informed security system. The use of surveillance camer...

引用

29th international conference on computer graphics and vision, graphicon 2019

作者： Berberova, M.A. Oboimov, A.S. Khakimova, A.Kh. Zolotarev, O.V. International Nuclear Safety Center Moscow Russia ANO «Scientific and Research Center for Information in Physics and Technique» Nizhny Novgorod Russia ANO «Russian New University» Moscow Russia

In the context of a difficult criminal situation in the world, taking into account the globalization of world development processes, international political and economic relations, which pose new risks for the development of the individual, society and the state. In the Russian Federation, as well as throughout the world, threats to the safety of industrial facilities are steadily increasing. Moreover, in connection with the improvement of organization and the expansion of the technical equipment of potential violators (terrorists, extremists, etc.), the improvement of methods and methods of illegal actions, issues related to the rationalization of technologies aimed at protecting vital interests and resources of enterprises. One of such technologies includes the creation of an effective automated security system and counteraction against unauthorized entry of individuals - a physical protection system, technically based on a set of engineering and technical means. the process of designing a set of engineering and technical means of a physical protection system for industrial facilities includes two main stages: conceptual and detailed design, and the optimality of design and engineering solutions in general depends on the successful implementation of work at the conceptual design stage. the assessment of the scale of the intruder's invasion is characterized by the time spent by the intruders in the control zone by television cameras, their tactics of overcoming this zone, time of day, illumination, etc. In this work, we use the analysis of images obtained from surveillance cameras. Copyright © 2019 for this paper by its authors.

关键词： Security systems

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：