检索结果-内蒙古大学图书馆

BEV-Locator:an end-to-end visual semantic localization network using multi-view images

science China(information sciences) 2025年第2期68卷 134-150页

作者： Zhihuang ZHANG Meng XU Wenqiang ZHOU Tao PENG Liang LI Stefan POSLAD School of Vehicle and Mobility Tsinghua University School of Information Technology & Management University of International Business and Economics Qcraft Inc. School of Electronic Engineering and Computer Science Queen Mary University of London

Accurate localization ability is fundamental in autonomous driving. Traditional visual localization frameworks approach the semantic map-matching problem with geometric models, which rely on complex parameter tuning and thus hinder large-scale deployment. In this paper, we propose BEV-Locator: an end-to-end visual semantic localization neural network using multi-view camera images. Specifically, a visual BEV(bird-eye-view) encoder extracts and flattens the multi-view images into BEV space. While the semantic map features are structurally embedded as map query sequences. Then a cross-model transformer associates the BEV features and semantic map queries. The localization information of ego-car is recursively queried out by cross-attention modules. Finally, the ego pose can be inferred by decoding the transformer outputs. This end-to-end model speaks to its broad applicability across different driving environments, including high-speed scenarios. We evaluate the proposed method in large-scale nuScenes and Qcraft datasets. The experimental results show that the BEV-Locator is capable of estimating the vehicle poses under versatile scenarios, which effectively associates the cross-model information from multi-view images and global semantic maps. The experiments report satisfactory accuracy with mean absolute errors of 0.052 m, 0.135 m and 0.251° in lateral, longitudinal translation and heading angle degree.

关键词： visual localization semantic map bird-eye-view transformer pose estimation

来源：评论

学校读者我要写书评

暂无评论

Data Secure Storage Mechanism for IIoT Based on Blockchain

引用

computers, Materials & Continua 2024年第3期78卷 4029-4048页

作者： Jin Wang Guoshu Huang R.Simon Sherratt Ding Huang Jia Ni School of Computer Science and Mathematics Fujian University of TechnologyFuzhou350118China School of Computer&Communication Engineering Changsha University of Science&TechnologyChangsha410004China School of Systems Engineering The University of ReadingReadingRG66AYUK School of Computer Nanjing University of Information Science and TechnologyNanjing210044China

With the development of Industry 4.0 and big data technology,the Industrial Internet of Things(IIoT)is hampered by inherent issues such as privacy,security,and fault tolerance,which pose certain challenges to the rapid development of *** technology has immutability,decentralization,and autonomy,which can greatly improve the inherent defects of the *** the traditional blockchain,data is stored in a Merkle *** data continues to grow,the scale of proofs used to validate it grows,threatening the efficiency,security,and reliability of blockchain-based ***,this paper first analyzes the inefficiency of the traditional blockchain structure in verifying the integrity and correctness of *** solve this problem,a new Vector Commitment(VC)structure,Partition Vector Commitment(PVC),is proposed by improving the traditional VC ***,this paper uses PVC instead of the Merkle tree to store big data generated by *** can improve the efficiency of traditional VC in the process of commitment and ***,this paper uses PVC to build a blockchain-based IIoT data security storage mechanism and carries out a comparative analysis of *** mechanism can greatly reduce communication loss and maximize the rational use of storage space,which is of great significance for maintaining the security and stability of blockchain-based IIoT.

关键词： Blockchain IIoT data storage cryptographic commitment

来源：评论

学校读者我要写书评

暂无评论

Computing Resource Allocation for Blockchain-Based Mobile Edge Computing

引用

computer Modeling in engineering & sciences 2024年第7期140卷 863-885页

作者： Wanbo Zhang Yuqi Fan Jun Zhang Xu Ding Jung Yoon Kim School of Computer Science and Information Engineering Intelligent Interconnected Systems Laboratory of Anhui ProvinceHefei University of TechnologyHefei230601China Anhui Province Key Lab of Aerospace Structural Parts Forming Technology and Equipment Hefei University of TechnologyHefei230009China College of Future Industry Gachon UniversitySeongnam13120South Korea

Users and edge servers are not fullymutually trusted inmobile edge computing(MEC),and hence blockchain can be introduced to provide *** blockchain-basedMEC,each edge server functions as a node in bothMEC and blockchain,processing users’tasks and then uploading the task related information to the *** is,each edge server runs both users’offloaded tasks and blockchain tasks *** that there is a trade-off between the resource allocation for MEC and blockchain ***,the allocation of the resources of edge servers to the blockchain and theMEC is crucial for the processing delay of blockchain-based *** of the existing research tackles the problem of resource allocation in either blockchain or MEC,which leads to unfavorable performance of the blockchain-based MEC *** this paper,we study how to allocate the computing resources of edge servers to the MEC and blockchain tasks with the aimtominimize the total systemprocessing *** the problem,we propose a computing resource Allocation algorithmfor Blockchain-based MEC(ABM)which utilizes the Slater’s condition,Karush-Kuhn-Tucker(KKT)conditions,partial derivatives of the Lagrangian function and subgradient projection method to obtain the *** results show that ABM converges and effectively reduces the processing delay of blockchain-based MEC.

关键词： Mobile edge computing blockchain resource allocation

来源：评论

学校读者我要写书评

暂无评论

Autonomous embodied navigation task generation from natural language dialogues

引用

science China(information sciences) 2025年第5期68卷 119-132页

作者： Haifeng XU Yongchang LI Lumeng MA Chunwen LI Yanzhi DONG Xiaohu YUAN Huaping LIU Department of Automation Tsinghua University School of Physics and Electronic Information Yantai University School of Electrical and Electronic Engineering Shanghai Institute of Technology Department of Computer Science and Technology Tsinghua University

Robots are increasingly being deployed in densely populated environments, such as homes, hotels, and office buildings, where they rely on explicit instructions from humans to perform tasks. However, complex tasks often require multiple instructions and prolonged monitoring, which can be time-consuming and demanding for users. Despite this, there is limited research on enabling robots to autonomously generate tasks based on real-life scenarios. Advanced intelligence necessitates robots to autonomously observe and analyze their environment and then generate tasks autonomously to fulfill human requirements without explicit commands. To address this gap, we propose the autonomous generation of navigation tasks using natural language dialogues. Specifically, a robot autonomously generates tasks by analyzing dialogues involving multiple persons in a real office environment to facilitate the completion of item transportation between various *** propose the leveraging of a large language model(LLM) through chain-of-thought prompting to generate a navigation sequence for a robot from dialogues. We also construct a benchmark dataset consisting of 625 multiperson dialogues using the generation capability of LLMs. Evaluation results and real-world experiments in an office building demonstrate the effectiveness of the proposed method.

关键词： proactive robot robot navigation service robot large language model

来源：评论

学校读者我要写书评

暂无评论

Link Budget and Enhanced Communication Distance for Ambient Internet of Things

引用

ZTE Communications 2024年第1期22卷 16-23页

作者： YANG Yibing LIU Ming XU Rongtao WANG Gongpu GONG Wei School of Computer and Information Technology Beijing Jiaotong UniversityBeijing 100044China School of Electronic and Information Engineering Beijing Jiaotong UniversityBeijing 100044China School of Computer Science and Technology University of Science and Technology of ChinaHefei 230026China

Backscatter communications will play an important role in connecting everything for beyond 5G(B5G)and 6G *** open challenge for backscatter communications is that the signals suffer a round-trip path loss so that the communication distance is *** this paper,we first calculate the communication distance upper bounds for both uplink and downlink by measuring the tag sensitivity and reflection *** is found that the activation voltage of the envelope detection diode of the downlink tag is the main factor limiting the back-scatter communication *** on this analysis,we then propose to implement a low-noise amplifier(LNA)module before the envelope detection at the tag to enhance the incident signal *** experimental results on the hardware platform show that our method can increase the downlink communication range by nearly 20 m.

关键词： ambient IoT(AIoT) B5G backscatter communication link budget low-noise amplifier(LNA) Release 19 tag chip sensitivity upper bounds

来源：评论

学校读者我要写书评

暂无评论

Underwater Image Color Analysis and Indicators Based on Statistical Characteristics 4

Underwater Image Color Analysis and Indicators Based on Stat...

引用

4th International Conference on computer Vision, Image and Deep Learning, CVIDL 2023

作者： Peng, Jin Yu, Haiyang Wang, Zhe School of Computer Science and Information Engineering Hefei University of Technology Anhui Hefei China

ISBN: (纸本)9798350326444

When light propagates in water, different wavelengths of light have different degrees of attenuation, resulting in the color cast of underwater images. Color characteristics are important to solve the problem of color cast. Therefore qualitative and quantitative analysis of underwater image color characteristics and color indicators studies in RGB space are carried out in this paper. A qualitative comparative analysis between underwater images and land color cast-free images is carried out. It is concluded that there are differences in histogram and statistical characteristics between RGB channels of underwater images. Then a set of color characteristics indicators is established that can measure the degree of color cast and the differences between color channels of the underwater images. Finally, experiments on quantitative analysis of color characteristics are carried out. Different turbidity levels and colors of the water environment are set up to analyze the changes and differences of color characteristics. Underwater image color characteristics are obtained by comprehensive analysis. © 2023 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Index-Based Mode Adjustment for Energy Saving of Service Vehicles and Robots in Vehicular Networks 9

Index-Based Mode Adjustment for Energy Saving of Service Veh...

引用

9th International Conference on computer and Communications, ICCC 2023

作者： Yan, Degao Wang, Lusheng Kai, Caihong Peng, Min Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China

ISBN: (纸本)9798350317251

Vehicular networks with service robots and vehicles have been widely studied in the past few years, and a large number of these vehicles and robots may appear in people's lives, such as in science and technology park, university town, restaurant, and public transportation hub. Energy-saving in vehicular networks becomes a key issue in these scenarios for ensuring the endurance time of vehicles and robots, so it is useful to dynamically adjust their working modes based on the pedestrian flow density around them. In this paper, we predict the peaks and troughs of the pedestrian flow based on four technical indexes, and adjust between active and ordinary modes for the vehicles and robots to save their energy while still guaranteeing their services. Simulation results show that the used technical indexes can predict the peaks and troughs of a pedestrian flow, hence the proposal effectively reduces the energy consumption of the vehicular networks. © 2023 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Modeling method of skylight polarization patterns based on distribution of neutral point 4

Modeling method of skylight polarization patterns based on d...

引用

4th International Conference on computer Vision, Image and Deep Learning, CVIDL 2023

作者： Gui, Ceding Wei, Kun School of Computer Science and Information Engineering Hefei University of Technology AnHui Hefei China

ISBN: (纸本)9798350326444

The skylight polarization patterns are essential in polarization navigation and remote sensing. The available models are unable to properly describe the distribution characteristics of skylight polarization patterns due to the complexity of actual atmospheric conditions. The neutral point is one of the important distribution properties of skylight polarization patterns, which represent the primary difference between measured patterns and theoretical skylight polarization patterns based on single Rayleigh scattering. In this paper, the actual spatial locations of the neutral points are calculated based on the crossover characteristics of the neutral lines and the projection model of the fisheye lens, and the distribution characteristic of the neutral point is analyzed. Based on the distribution of neutral points under actual atmospheric conditions and the equidistant projection mode of measurement equipment, a simulation model of skylight polarization patterns is constructed, taking into account the influence of skylight intensity and sky clarity. The simulation results reveal that the proposed model is more consistent with the measured skylight polarization patterns than the Rayleigh model. © 2023 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Survey of Edge Caching:Key Issues and Challenges

引用

Tsinghua science and technology 2024年第3期29卷 818-842页

作者： Hanwen Li Mingtao Sun Fan Xia Xiaolong Xu Muhammad Bilal School of Computer Science Nanjing University of Information Science and TechnologyNanjing 210044China Shandong Provincial University Laboratory for Protected Horticulture Weifang University of Science and TechnologyWeifang 262700China Reading Academy Nanjing University of Information Science and TechnologyNanjing 210044China School of Software Nanjing University of Information Science and TechnologyNanjing 210044China Department of Computer Engineering Hankuk University of Foreign StudiesYongin-si 17035Republic of Korea

With the rapid development of mobile communication technology and intelligent applications,the quantity of mobile devices and data traffic in networks have been growing exponentially,which poses a great burden to networks and brings huge challenge to servicing user *** caching,which utilizes the storage and computation resources of the edge to bring resources closer to end users,is a promising way to relieve network burden and enhance user *** this paper,we aim to survey the edge caching techniques from a comprehensive and systematic *** first present an overview of edge caching,summarizing the three key issues regarding edge caching,i.e.,where,what,and how to cache,and then introducing several significant caching *** then carry out a detailed and in-depth elaboration on these three issues,which correspond to caching locations,caching objects,and caching strategies,*** particular,we innovate on the issue“what to cache”,interpreting it as the classification of the“caching objects”,which can be further classified into content cache,data cache,and service ***,we discuss several open issues and challenges of edge caching to inspire future investigations in this research area.

关键词： edge caching edge computing caching location caching object caching strategy 5G networkarchitecture Internet of Things(IoT)

来源：评论

学校读者我要写书评

暂无评论

Underwater image recovery method considering target polarization characteristics 4

Underwater image recovery method considering target polariza...

引用

4th International Conference on computer Vision, Image and Deep Learning, CVIDL 2023

作者： Wang, Zhe Yu, Haiyang Peng, Jin School of Computer Science and Information Engineering Hefei University of Technology AnHui Hefei China

ISBN: (纸本)9798350326444

In underwater polarization imaging, the estimation of the polarization characteristics of the target is also the key to recover the original image. Most current recovery methods ignore the polarization characteristics of the target and require manual selection of the region for parameter estimation. This not only causes errors in the recovery results, but also has the limitation that a background region must exist. In this paper, we derive the reconstruction model of the original underwater image from the underwater imaging model and the polarization imaging model, considering the polarization characteristics of the target. In this paper, the background light polarization degree is obtained using the filtered median algorithm, and the bright channel principle is used to obtain the background light at infinity. Compared with the traditional method, the method in this paper can reduce the error. Finally, this paper makes improvements to the perfect reflection algorithm and enhances the recovered image. © 2023 IEEE.

关键词： Image enhancement

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：