检索结果-内蒙古大学图书馆

An Efficient Lane Following Navigation Strategy With Fusion Attention for Autonomous Drones in Urban Areas

IEEE Transactions on Vehicular technology 2023年第3期73卷 3094-3105页

作者： Lee, Chao-Yang Khanum, Abida Wang, Neng-Chung Karuparthi, Bala Syam Kumar Yang, Chu-Sing the Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Douliou64002 Taiwan the Computer Science and Communication Engineering National Cheng Kung University Tainan701 Taiwan the Department of Computer Science and Information Engineering National United University Miao-Li36003 Taiwan the Department of Aeronautical Engineering National Formosa University Huwei632 Taiwan the Department of Electrical Engineering National Cheng Kung University Tainan701 Taiwan

—Drones are a vital part of our daily lives because of their flexible flying nature and low operation and maintenance costs. Navigation is the most important aspect in the autonomous drone era. With that being said, recent studies have tackled the greatly challenging task of obtaining the most feasible and safest path. In this work, we focus on safe and reliable unmanned aerial vehicle navigation in densely populated city environments to efficiently follow the lane. We present herein a deep learning method through which a drone can autonomously navigate by following a lane in a dynamic urban environment. This drone perceives the environment by using two cameras facing front and down. A convolutional neural network (CNN) is used to capture the high-level feature representation through the attention and residual mechanism of the drone’s raw visual inputs. The CNN concurrent pipelines used for three raw visual inputs can output high-level features and follow the concurrent feature fusion into the self-head attention mechanism that encapsulates both dynamic and static information to predict yaw and linear velocity. These predictions are modulated into the final control commands to obtain smooth and continuous inputs that are delivered to the drone. The experimental evaluation results show that the proposed method can learn the drone’s navigation strategy for a lane following a guidance system. The high performance of the trained navigation policy is observed in the simulations with different scenarios. In conclusion, our proposed approach outperforms both existing and current state-of-the-art ImageNet models. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Transformers for Vision: A Survey on Innovative Methods for computer Vision

引用

IEEE Access 2025年 13卷 95496-95523页

作者： Hassija, Vikas Palanisamy, Balamurugan Chatterjee, Arpita Mandal, Arpita Chakraborty, Debanshi Pandey, Amit Chalapathi, Gss Kumar, Dhruv Deemed to be University School of Computer Engineering Odisha Bhubaneswar751024 India Bennett University School of CSET Gautam Buddha Nagar Greater Noida201310 India Department of Electrical and Electronics Engineering Birla Institute of Technology and Science Pilani xPilani Campus Vidya Vihar Rajasthan Pilani333031 India Department of Computer Science and Information Systems Birla Institute of Technology and Science Pilani Pilani Campus Vidya Vihar Rajasthan Pilani333031 India

Transformers have emerged as a groundbreaking architecture in the field of computer vision, offering a compelling alternative to traditional convolutional neural networks (CNNs) by enabling the modeling of long-range dependencies and global context through self-attention mechanisms. Originally developed for natural language processing, transformers have now been successfully adapted for a wide range of vision tasks, leading to significant improvements in performance and generalization. This survey provides a comprehensive overview of the fundamental principles of transformer architectures, highlighting the core mechanisms such as self-attention, multi-head attention, and positional encoding that distinguish them from CNNs. We delve into the theoretical adaptations required to apply transformers to visual data, including image tokenization and the integration of positional embeddings. A detailed analysis of key transformer-based vision architectures such as ViT, DeiT, Swin Transformer, PVT, Twins, and CrossViT are presented, alongside their practical applications in image classification, object detection, video understanding, medical imaging, and cross-modal tasks. The paper further compares the performance of vision transformers with CNNs, examining their respective strengths, limitations, and the emergence of hybrid models. Finally, current challenges in deploying ViTs, such as computational cost, data efficiency, and interpretability, and explore recent advancements and future research directions including efficient architectures, self-supervised learning, and multimodal integration are discussed. © 2013 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Distributed Learning with Quantized Finite-Time Coordination 63

Asynchronous Distributed Learning with Quantized Finite-Time...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Bastianello, Nicola Rikos, Apostolos I. Johansson, Karl H. Kth Royal Institute of Technology School of Electrical Engineering and Computer Science and Digital Futures Sweden Artificial Intelligence Thrust of the Information Hub Guangzhou China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Clear Water Bay Hong Kong

ISBN: (纸本)9798350316339

In this paper we address distributed learning problems over peer-to-peer networks. In particular, we focus on the challenges of quantized communications, asynchrony, and stochastic gradients that arise in this set-up. We first discuss how to turn the presence of quantized communications into an advantage, by resorting to a finite-time, quantized coordination scheme. This scheme is combined with a distributed gradient descent method to derive the proposed algorithm. Secondly, we show how this algorithm can be adapted to allow asynchronous operations of the agents, as well as the use of stochastic gradients. Finally, we propose a variant of the algorithm which employs zooming-in quantization. We analyze the convergence of the proposed methods and compare them to state-of-the-art alternatives. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Modeling User Quality of Experience in Adaptive Point Cloud Video Streaming 26

Modeling User Quality of Experience in Adaptive Point Cloud ...

引用

26th International Symposium on Multimedia, ISM 2024

作者： Nguyen, Duc V. Quang, Nguyen Long Hien, Tran Thuy Huyen, Nguyen Ngoc Huong, Truong Thu Nam, Pham Ngoc Tohoku Insitute of Technology Faculty of Engineering Sendai Japan Hanoi University of Science and Technology School of Electrical and Electronic Engineering Hanoi Viet Nam VinUniversity College of Engineering and Computer Science Hanoi Viet Nam

ISBN: (纸本)9798331511111

Point cloud video streaming over networks is challenging because of the high data rate of uncompressed point cloud data. Adaptive point cloud video streaming has been proposed to deal with this challenge. However, temporal quality variation and stalling might occur under unstable network conditions, potentially degrading users' Quality of Experience (QoE). This paper aims to evaluate and model the impacts of temporal quality variations and stalling on users' QoE in adaptive point cloud video streaming. We first conduct a large-scale subjective study to construct a QoE database. Then, based on the constructed database, the effects of individual factors are analyzed, and two novel QoE prediction models are presented. Experiment results show that the proposed QoE models achieve high prediction performance in PLCC, SROCC, and RMSE across various point cloud videos. © 2024 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

A Speech Enhancement Algorithm Combining Wavelet Transform and Adaptive Filters 6

A Speech Enhancement Algorithm Combining Wavelet Transform a...

引用

6th IEEE International Conference on Image Processing, Applications and Systems, IPAS 2025

作者： Shrestha, Aayam Ghorshi, Seyed Joorabchi, Marjan Panahi, Issa Firouzeh, Fereshteh Fakhar The University of Texas at Tyler Department of Electrical and Computer Engineering TX United States Sharif University of Technology School of Science and Engineering Iran The University of Texas at Dallas Department of Electrical and Computer Engineering TX United States

ISBN: (纸本)9798331506520

Noise as an unwanted interference can significantly degrade speech signals, especially those recorded by many microphones. This interference is modeled as additive noise that originates from a range of sources including White Gaussian Noise (WGN), babble, crowd, large city, and traffic noises. These disturbances can alter the characteristics of speech signals reducing both their quality and intelligibility. This paper introduces a novel approach designed to reduce noise and enhance the quality and intelligibility of speech signals. The proposed method combines Wavelet Transform with Adaptive Filters, specifically the Wiener filter and RLS filter. The evaluation process involves testing noisy speech signals under realistic conditions with different signal-to-noise ratios (SNRs) and different types of additive noise. The objective measure is used for evaluation, including the perceptual evaluation of speech quality (PESQ). Results show that combining Wiener or RLS filtering with Wavelet Transform significantly improves noise reduction, outperforming the use of Wavelet Transform alone. © 2025 IEEE.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Multi-Server Stable Rendezvous for the Metaverse

Multi-Server Stable Rendezvous for the Metaverse

引用

2023 IEEE International Conference on Metaverse Computing, Networking and Applications, MetaCom 2023

作者： Su, Ningxin Li, Baochun Li, Bo University of Toronto The Department of Electrical and Computer Engineering Canada Hong Kong University of Science and Technology The Department of Computer Science Hong Kong

ISBN: (纸本)9798350333336

When the real world and the digital world meet, they create a shared virtual space called the metaverse, involving multiple virtual communities in which users interact with one another in a highly immersive and interactive fashion. Due to the pressing need for scalability when handling millions of users in the metaverse regardless of the applications and services provided, it is imperative to deploy multiple servers across geographically distributed datacenters around the world. In this paper, we envision, design, and implement a new rendezvous service between a large number of users and a collection of geographically distributed servers, taking into account the latencies and pair-wise network bandwidth between the users and the servers, as well as bandwidth and processing capacity constraints on the servers themselves when handling the users. Our new rendezvous service is designed with simplicity and efficiency as its primary objective, and uses a revised design of the Deferred Acceptance algorithm to guarantee a stable matching between the users in the metaverse and its servers. As a case study, our rendezvous service has been implemented in the context of a federated learning application. © 2023 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Enabled Bi-level Robust Parameter Optimization of Hydropower-dominated Systems for Damping Ultra-low Frequency Oscillation

引用

Journal of Modern Power Systems and Clean Energy 2023年第6期11卷 1770-1783页

作者： Guozhou Zhang Junbo Zhao Weihao Hu Di Cao Nan Duan Zhe Chen Frede Blaabjerg School of Mechanical and Electrical Engineering University of Electronic Science and Technology of ChinaChengdu 610054China IEEE Department of Electrical and Computer Engineering University of ConnecticutStorrsCT06269USA Lawrence Livermore National Laboratory LivermoreUSA Department of Energy Technology Aalborg University9220 AalborgDenmark

This paper proposes a robust and computationally efficient control method for damping ultra-low frequency oscillations(ULFOs) in hydropower-dominated systems. Unlike the existing robust optimization based control formulation that can only deal with a limited number of operating conditions, the proposed method reformulates the control problem into a bi-level robust parameter optimization model. This allows us to consider a wide range of system operating conditions. To speed up the bi-level optimization process, the deep deterministic policy gradient(DDPG) based deep reinforcement learning algorithm is developed to train an intelligent agent. This agent can provide very fast lower-level decision variables for the upper-level model, significantly enhancing its computational efficiency. Simulation results demonstrate that the proposed method can achieve much better damping control performance than other alternatives with slightly degraded dynamic response performance of the governor under various types of operating conditions.

关键词： Bi-level robust parameter optimization deep reinforcement learning deep deterministic policy gradient ultralow frequency oscillation damping control stability

来源：评论

学校读者我要写书评

暂无评论

Edge-Enabled Metaverse:The Convergence of Metaverseand Mobile Edge Computing

引用

Tsinghua science and technology 2024年第3期29卷 795-805页

作者： Nyothiri Aung Sahraoui Dhelim Liming Chen Huansheng Ning Luigi Atzori Tahar Kechadi Information Engineering College Xinjiang Institute of EngineeringUrumqi 830023Chinaand also with School of Computer ScienceUniversity College DublinDublinD04 V1W8Ireland School of Computing Ulster UniversityBelfastBT151EDUK School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China Department of Electrical and Electronic Engineering University of CagliariSardinia 09124Italy School of Computer Science University College DublinDublinD04 V1W8Ireland

Metaverse is a virtual environment where users are represented by their avatars to navigate a virtual world having strong links with its physical *** state-of-the-art Metaverse architectures rely on a cloud-based approach for avatar physics emulation and graphics rendering *** current centralized architecture of such systems is unfavorable as it suffers from several drawbacks caused by the long latency of cloud access,such as low-quality *** this end,we propose a Fog-Edge hybrid computing architecture for Metaverse applications that leverage an edge-enabled distributed computing *** applications leverage edge devices’computing power to perform the required computations for heavy tasks,such as collision detection in the virtual universe and high-computational 3D physics in virtual *** computational costs of a Metaverse entity,such as collision detection or physics emulation,are performed at the device of the associated physical *** validate the effectiveness of the proposed architecture,we simulate a distributed social Metaverse *** simulation results show that the proposed architecture can reduce the latency by 50%when compared with cloud-based Metaverse applications.

关键词： industrial Metaverse edge computing Blockchain virtual environment task offloading fog computing

来源：评论

学校读者我要写书评

暂无评论

MQTT based monitoring and control system for remote stations in automotive industry

MQTT based monitoring and control system for remote stations...

引用

2023 IEEE Zooming Innovation in Consumer Technologies Conference, ZINC 2023

作者： Ivanovic, Denis Job, Josip Puntaric, Marko Herceg, Marijan TTTech-Auto CX Osijek Croatia Faculty of Electrical Engineering Computer Science and Information Technology Department of Software Engineering Osijek Croatia Faculty of Electrical Engineering Computer Science and Information Technology Department of Communications Osijek Croatia

ISBN: (纸本)9798350347722

In this paper is presented implementation of a lightweight supervisory control and data acquisition system for remote test stations as a part of a larger test house in the automotive industry. It is necessary to allow remote set up and monitoring of the test stations, which means defining the structure of a system with numerous test stations as endpoints. The test stations are meant to be virtual machines but can be both virtual and physical machines. A communication protocol must be used that enables this within the organization's network, regardless of actual distance and location. The parameters of the test stations to be monitored can be defined according to the needs and purpose. Even when creating your own tool, this function is not unique, i.e. on one test station parameters of operating system resources such as memory usage can be monitored, while on another test station logged-in users or running programs, reported system errors and others must be monitored. Data storage is one of the mandatory functions of this system. This process allows viewing data throughout history and more detailed analysis of events. There are numerous benefits that can be drawn and used from the data stored in the database. It is necessary to pay attention to the data stored as well as the scope and retention throughout history. The correct and secure setup of a database is one of the prerequisites for any serious system that processes data. Appropriate views should be created for users involved in the data monitoring process using all the elements mentioned so far. Creating a visually acceptable and easy-To-use interface that serves the main purpose is the final presentation of the entire system to users. A complete system leads to higher productivity, profitability and better organization of the company. It also allows project managers to better plan the use and occupancy of test stations. At any time, they have insight into the status of individual test stations, their activitie

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Data Association With Camera Parameters Estimation for Object Tracking From Drones

引用

Journal of Advances in Information Fusion 2024年第1期19卷 45-56页

作者： Tian, Zijiao Bar-Shalom, Yaakov Yang, Rong Huang, Hong'An Jack Ng, Gee W.A.H. Department of Electrical and Computer Engineering University of Connecticut StorrsCT06269 United States DSO National Laboratories Singapore118225 Singapore Team Science and Technology Agency 138507 Singapore

This paper considers the problem of inaccurate measurement-to-track association (M2TA) and poor tracking caused by camera motion changes in drone-captured video. The camera often changes its feld of view to track targets;however, the sudden change leads to inaccurate M2TA and degrades tracking performance. Previous work estimated the 3D camera motion parameter vector (zoom ratio, panning, and tilting) and associated measurements and tracks only between two consecutive frames. This paper extends the camera motion parameter to 4D by including rolling and sequentially associates (forward) measurements to tracks over the entire data. The estimated camera parameters improve the predicted measurements and achieve better M2TA. Results on real data illustrate the benefts of the proposed method (association with 4D camera parameters estimation) that yields better associations and improves tracking accuracy compared to the state-of-the-art gating method based on infated covariances. © 2024 JAIF.

关键词： Drones

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：