检索结果-内蒙古大学图书馆

9th international conference on signal and image Processing (ICSIP)

作者： Zhang, Huimin Du, Chaoyang Chen, Zhaofeng Si, Qintuya Liu, Yang Inner Mongolia Univ Coll Elect Informat Engn Hohhot Peoples R China Yancheng Inst Technolog 1 Middle Hope Ave Yancheng Peoples R China

ISBN: (纸本)9798350350920

The emergence of the internet of Things (IoT) has led to the development of Unmanned Aerial Vehicle (UAV) trajectory planning, aiming to enhance service quality in remote areas. However, traditional trajectory planning algorithms heavily rely on accurate environmental models, which pose challenges in achieving strategy convergence and minimizing the age of information (AoI). To address this issue, we propose an AoI-oriented UAV trajectory planning algorithm based on multi-agent noise dueling double deep Q-Network (MAND3QN). Considering data freshness as a priority, we initially model the multi-UAV trajectory planning problem as a problem of minimizing the average AoI. Subsequently, the Dueling structure is introduced to decompose the Q value into the value function of states and the dominance function of state-action pairs, which improves the learning efficiency and allows for a more accurate estimation of Q-values. Additionally, by incorporating noise parameters through NoisyNet implementation in neural networks, we introduce randomness to network output values and improve exploration capabilities within the state space. Simulation results demonstrate that our algorithm achieves stable and rapid convergence while significantly reducing AoI for UAVs-assisted IoT systems.

关键词： IoT UAVs trajectory planning Age of information multi-intelligence deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Adaptive Semantic Coding for image Transmission in Satellite-Integrated internet

Deep Learning-based Adaptive Semantic Coding for Image Trans...

引用

ieee/CIC international conference on Communications in China (ICCC)

作者： Yuan, Guangwei Jiao, Jian Zhang, Heqing Zhang, Ke Wang, Ye Zhang, Qinyu Peng Cheng Lab Shenzhen 518055 Peoples R China Harbin Inst Technol Shenzhen Shenzhen 518055 Peoples R China

ISBN: (纸本)9798350378412

Satellite-integrated internet will enable image transmission for ubiquitous terrestrial users in extreme climates, environments, and terrain in the upcoming 5G advanced (5G-A) and 6G network. However, the challenges posed by the limited onboard resources and bandwidth of satellite-to-ground link (SGL) in satellite-integrated internet present significant obstacles for image transmission. To address these challenges, we propose a deep learning-based adaptive semantic coding network (ASCN) for image transmission in satellite-integrated internet over shadowed-Rician (SR) channel. Our ASCN utilizes a single deep neural network (DNN) to adaptive adjust transmission rate based on input image features and time varying channel state information (CSI) under three types of SR fading levels. Specifically, we design a SR channel ModNet to match the semantic of transmitted image features based on CSI, which can achieve an optimized tradeoff between the image reconstruction quality and network utility. Experimental results demonstrate that our ASCN can effectively learn to match the semantic of transmitted image features based on CSI under three types of SR fading levels, and the image reconstruction quality significantly outperforms the state-of-the-art schemes.

关键词： Satellite-integrated internet semantic coding network image transmission time varying channel adaptive rate control

来源：评论

学校读者我要写书评

暂无评论

MultiView Markerless MoCap - MultiView Performance Capture, 3D Pose Motion Reconstruction and Comparison 17

MultiView Markerless MoCap - MultiView Performance Capture, ...

引用

17th international conference on signal-image technology and internet-based systems, SITIS 2023

作者： Bisht, Pratik Singh Colantoni, Philippe Muselet, Damien Tremeau, Alain Université de Lyon Université Jean Monnet Laboratoire Hubert Curien Umr 5516 France

ISBN: (纸本)9798350370911

This article explores the challenges and advancements in multi-view camera systems, 2D pose estimation, and 3D reconstruction for capturing and reconstructing live performances. It conducts a comparative analysis of methodologies at each stage of the pipeline, identifying strengths, weaknesses, and effective techniques. The study addresses the robustness of existing techniques in diverse scenarios and aims to integrate these fields into a unified framework for high-quality reconstructions. It contributes to the development of advanced multi-camera systems applicable across domains and serves as a valuable resource for future research in the field of performance capture and analysis. © 2023 ieee.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Lightweight Machine Sound Anomaly Detector based on Parallel Discrete Wavelet Transform

引用

ieee SENSORS JOURNAL 2025年第10期25卷 18529-18542页

作者： Choi, Eunhye Park, Hyunggon Agcy Def Dev Daejeon 34186 South Korea Ewha Womans Univ Dept Elect & Elect Engn Seoul 03760 South Korea

The development of Industrial internet of Things (IIoT) technology and network infrastructures has enabled the acquisition of substantial data, enabling data-driven condition monitoring and analysis. Detecting anomalies in machinery equipment is crucial in IIoT environments for safety enhancement, productivity, and reliability. To provide effective anomaly detection at IIoT edge nodes without delay, it is necessary to efficiently collect and process vast amounts of data from various sensors. While this demands a significant amount of computing resources, edge nodes only have limited data storage and processing capabilities. Therefore, our focus is on developing a lightweight anomaly detection algorithm for acoustic signal processing, considering the computational resources of the IIoT edge node. In this article, we propose the parallel discrete wavelet transform (PDWT) as an efficient method for compressing and processing acoustic signals received at edge nodes. This approach significantly alleviates memory consumption and reduces the computational time at the edge. In addition, by harnessing preprocessed features through PDWT, we can develop lightweight anomaly detection models suitable for deployment at the edge, making them highly practical for real-world implementation. The experimental results using real-world data collected from industrial machines confirm the effectiveness of the proposed solution.

关键词： Anomaly detection Feature extraction image edge detection Acoustics Industrial internet of Things Computational modeling Training Autoencoders Transforms Discrete wavelet transforms Acoustic signal anomaly detection autoencoder discrete wavelet transform (DWT) edge computing Industrial internet of Things (IIoT)

来源：评论

学校读者我要写书评

暂无评论

MAS-EGNN: A Multi-Agent EGNN-based Spectrum Allocation Optimization Framework for V2X Communications

MAS-EGNN: A Multi-Agent EGNN-based Spectrum Allocation Optim...

引用

9th international conference on signal and image Processing (ICSIP)

作者： He, Yingxue Peng, Li Jiangnan Univ Sch Internet Things Engn Wuxi Jiangsu Peoples R China

ISBN: (纸本)9798350350920

With the development of V2X technology, efficient spectrum resource management is critical to ensure the reliability and overall system performance of vehicle-to-vehicle communications. Traditional spectrum allocation methods often do not take into account inter-vehicle interference. In this paper, we introduce an innovative approach to eliminate interference in vehicle-to-vehicle communication, the MAS-EGNN framework. Initially, an Equivariant Graph Neural Networks (EGNN) is utilized to dynamically update the graph representation through node and edge conditions to effectively capture the relationships and dependencies between vehicles. Subsequently, multi-intelligence reinforcement learning techniques allow multiple intelligences to interact simultaneously within the environment, with each independently adapting to changes in the surrounding environment to optimize overall network performance. The effectiveness of the approach in improving communication quality and system throughput is verified through the simulation of V2X communication scenarios and the implementation of corresponding optimization strategies. The experimental results show that the method significantly reduces interference and optimizes V2X spectrum allocation compared with the traditional spectrum allocation strategy.

关键词： V2X Communication Spectrum Resource Management Equivariant Graph Neural Networks Multi-Agent Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

TGIEN: An Interpretable image Editing Method for IoT Applications based on Text Guidance 17

TGIEN: An Interpretable Image Editing Method for IoT Applica...

引用

ieee Congress on Cybermatics: 17th ieee international conference on internet of Things, iThings 2024, 20th ieee international conference on Green Computing and Communications, GreenCom 2024, 17th ieee international conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th ieee international conference on Smart Data, SmartData 2024

作者： Wang, Yifei Pan, Mengzhu Li, Qianmu Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798350351637

In response to the demands and challenges of image editing in the internet of Things (IoT) domain, we have proposed an interpretable image editing method guided by text(TGIEN), aiming to address the limitations of existing image editing models based on Generative Adversarial Networks (GANs) for better application in IoT. This method utilizes a Contrastive Language-image Pre-trained Model (CLIP) to guide the editing of the StyleGAN latent space, enabling manipulation of real images through text prompts. The model incorporates a mapping module conditioned on text embeddings to edit the latent space code of StyleGAN and learns an attention map corresponding to the text across all layers of StyleGAN. These attention maps highlight focus areas during editing, providing an intuitive explanation of the model's behavior. Additionally, during the image generation process, the attention map functions as a mask to guide local fusion between original and modified features. Furthermore, the model integrates editability losses to ensure that editing operations align closely with the text prompts. Through the aforementioned design, spatial disentanglement is explicitly achieved, enhancing the transparency and interpretability of the model and in turn increasing the capacity of image editing technology in the IoT domain for practical application and system optimization. Both qualitative and quantitative experiments demonstrate the superiority of this method over other state-of-the-art methods in terms of editing quality and decoupling of edits. In the IoT domain, this method holds promise for applications such as smart surveillance systems, smart healthcare and virtual reality, offering more intelligent and efficient image processing and analysis for these scenarios. © 2024 ieee.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Dataset of Infrared images for Deep Learning based Drone Detection 17

A Dataset of Infrared Images for Deep Learning based Drone D...

引用

17th international conference on signal-image technology and internet-based systems, SITIS 2023

作者： Bhattacharya, Purbaditya Nowak, Patrick Ahlers, Daniel Zolzer, Udo Helmut Schmidt University Dept. of Signal Proc. and Comm. Hamburg Germany

ISBN: (纸本)9798350370911

Recently, drone detection has become a topic of interest due to the widespread usage of drones in various applications, particularly for recreational purposes. Such detection tasks are usually performed by deep learning models which require different kinds of image datasets to be trained on. Hence, a dataset of infrared images for drone detection is introduced in this paper. In order to generate the dataset, videos of drones are captured initially with multiple cameras at two different locations. The video frames are then extracted and the drones are annotated with the help of an annotation tool and an automated script. A comprehensive analysis of the dataset is provided and multiple configurations of a selection of CNN models are trained on a fraction of the dataset. The trained models are employed on the test dataset and their performance is evaluated. © 2023 ieee.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

AN IOT based FRAMEWORK FOR PREDICTION OF ENVIORNMENT QUALITY USING ARTIFICIAL INTELLIGENCE 7

AN IOT BASED FRAMEWORK FOR PREDICTION OF ENVIORNMENT QUALITY...

引用

ieee 7th international conference on Advanced Technologies, signal and image Processing (ATSIP)

作者： Alqahtani, Omar Saad Kshirsagar, Pravin Ramdas King Khalid Univ Dept Comp Sci Abha Saudi Arabia JD Coll Engn & Management Dept Elect & Telecommun Engn Nagpur Maharashtra India

ISBN: (纸本)9798350351491;9798350351484

Environmental phenomena affect our everyday life greatly. This included flexible structures the resources of life, including the pure water and air of our planet. The word climate is characterized as a platform that provides numerous facilities for several atmospheric applications in the areas of water allocation, poor air quality, meteorological conditions, radioactive detection, wastewater treatment, catastrophic event as well as many other predisposing factors. Monitoring system, modeling and management provide a better knowledge of key development and environmental changing management methods. Over time, the problem of emissions has increased owing to a number of reasons, such as increasing population and usage of cars, urban development, which has a significant impact on workers' health. This article proposes AI and IoT for the predictions and modeling of the environmental quality assessment system. The Artificial Intelligence method can evaluate data extremely efficiently and take accurate choices on services in many kinds. The IoT gateway includes the entire application software from sensor level to environmental information systems. The test data suggest that the new approach offers an efficient means of analyzing environmental information over a lengthy period of time.

关键词： Environment Quality Monitoring System internet of Things[IoT] Artificial Intelligence [AI] Air Quality Water Pollution Radiation Pollution Accuracy Efficiency Performance

来源：评论

学校读者我要写书评

暂无评论

ISP2DLA: Automated Deep Learning Accelerator Design for On-Sensor image signal Processing 35

ISP2DLA: Automated Deep Learning Accelerator Design for On-S...

引用

35th ieee international conference on Application-Specific systems, Architectures and Processors (ASAP)

作者： Won, Dong-eon Kim, Yeeun Lee, Janghwan Lee, Minjae Bae, Jonghyun Park, Jongjoo Song, Jeongyong Choi, Jungwook Hanyang Univ Seoul South Korea SK Hynix Inc Icheon Gyeonggi Do South Korea

ISBN: (纸本)9798350349641;9798350349634

Deep neural network-based image signal processing (ISP-DNN) improves image quality with techniques such as demosaicing, but these models pose substantial computational and memory challenges when implemented on CMOS image sensors, particularly due to the high-resolution inputs that increase memory requirements for activations. Layer fusion reduces memory usage by combining consecutive processing steps, yet it increases computational demands, a critical issue in resource-limited on-sensor environments. To address these challenges, we introduce ISP2DLA, an automated deep learning accelerator design framework that balances computational and memory demands for on-sensor ISP. This framework optimizes hardware designs by adjusting line buffer sizes and the number of MAC units, reducing gate counts by 14-79% across two ISP-DNN models, thus enabling efficient on-sensor ISP model inference within constrained resources.

关键词： image signal processing On-sensor deep learning acceleration Automatic accelerator design

来源：评论

学校读者我要写书评

暂无评论

Shore Livecams: A Maritime Dataset for Deep Learning based Object Detection 17

Shore Livecams: A Maritime Dataset for Deep Learning based O...

引用

17th international conference on signal-image technology and internet-based systems, SITIS 2023

作者： Ahlers, Daniel Bhattacharya, Purbaditya Nowak, Patrick Zolzer, Udo Helmut Schmidt University Dept. of Signal Proc. and Comm Hamburg Germany

ISBN: (纸本)9798350370911

Datasets of maritime objects are very important for training applications related to activity monitoring in locations around ports and shores. This paper introduces a maritime dataset for object detection, named as the shore livecam dataset. The dataset is a collection of high definition (HD), full high definition (FHD), and ultra high definition (UHD) images captured from live video feeds recorded across various port based areas of Germany. These images contain multiple instances of objects which are primarily classified into three different classes and annotated accordingly. The widely varying object sizes contribute to the uniqueness of this dataset whose content is thoroughly analysed and described. Finally, a selection of deep learning models is used on this dataset for evaluation. The dataset is available at https://***/HSU-ANT/shore-livecams/ © 2023 ieee.

关键词： Object detection

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：