首页 > 最新文献

IEEE journal of radio frequency identification最新文献

英文 中文
Experimental Evaluation of a Cognitive Routing Strategy for Efficient Energy Management in DTN 针对 DTN 高效能源管理的认知路由策略的实验评估
Q2 ENGINEERING, ELECTRICAL & ELECTRONIC Pub Date : 2024-03-06 DOI: 10.1109/JRFID.2024.3397582
Ricardo Lent
This study conducts an experimental evaluation of a decentralized cognitive routing approach to improve the performance of Delay Tolerant Networks (DTNs) in challenging environments, particularly in space. The primary goal is to minimize latency while concurrently extending the operational lifetimes of nodes by strategically avoiding bundle transmission through low-charged relay nodes. The approach addresses multi-objective routing through a reinforcement learning formulation that considers either the delay or path length to the destination, jointly with the residual energy levels of nodes along the transmission path. It also defines suitable networking mechanisms to obtain accurate estimates of delay-energy metrics associated with node contacts. The paper provides details of the implementation strategy for the High-Rate Delay Tolerant Networking (HDTN) framework and the design of a battery emulation system that provides precise control over experimental conditions, ensuring test reproducibility. The results demonstrate significant reductions in bundle losses and extended network lifetimes while maintaining either delay or path lengths within reasonable bounds compared to what can be achieved with the current routing standard. The proposed approach holds the promise of significantly improving the reliability of DTN communications in space.
本研究对一种分散式认知路由方法进行了实验评估,以提高容错网络(DTN)在具有挑战性的环境中,尤其是在太空中的性能。其主要目标是最大限度地减少延迟,同时通过战略性地避免通过低电荷中继节点进行捆绑传输来延长节点的运行寿命。该方法通过强化学习公式解决多目标路由问题,该公式考虑了到目的地的延迟或路径长度,以及传输路径上节点的剩余能量水平。它还定义了合适的联网机制,以获得与节点接触相关的延迟-能量指标的精确估算。论文详细介绍了高速率延迟容限网络(HDTN)框架的实施策略以及电池仿真系统的设计,该系统可精确控制实验条件,确保测试的可重复性。结果表明,与目前的路由标准相比,在保持延迟或路径长度在合理范围内的同时,捆绑损耗大幅降低,网络寿命延长。所提出的方法有望显著提高空间 DTN 通信的可靠性。
{"title":"Experimental Evaluation of a Cognitive Routing Strategy for Efficient Energy Management in DTN","authors":"Ricardo Lent","doi":"10.1109/JRFID.2024.3397582","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3397582","url":null,"abstract":"This study conducts an experimental evaluation of a decentralized cognitive routing approach to improve the performance of Delay Tolerant Networks (DTNs) in challenging environments, particularly in space. The primary goal is to minimize latency while concurrently extending the operational lifetimes of nodes by strategically avoiding bundle transmission through low-charged relay nodes. The approach addresses multi-objective routing through a reinforcement learning formulation that considers either the delay or path length to the destination, jointly with the residual energy levels of nodes along the transmission path. It also defines suitable networking mechanisms to obtain accurate estimates of delay-energy metrics associated with node contacts. The paper provides details of the implementation strategy for the High-Rate Delay Tolerant Networking (HDTN) framework and the design of a battery emulation system that provides precise control over experimental conditions, ensuring test reproducibility. The results demonstrate significant reductions in bundle losses and extended network lifetimes while maintaining either delay or path lengths within reasonable bounds compared to what can be achieved with the current routing standard. The proposed approach holds the promise of significantly improving the reliability of DTN communications in space.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"506-515"},"PeriodicalIF":0.0,"publicationDate":"2024-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141333981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Lens Antenna Design Tool Based on Generalized Superformula 基于广义超公式的透镜天线设计工具
Q2 ENGINEERING, ELECTRICAL & ELECTRONIC Pub Date : 2024-03-02 DOI: 10.1109/JRFID.2024.3396333
Alberto Facchini;Francesco Paolo Chietera;Riccardo Colella;Luca Catarinucci;Pietro Bia;Luciano Mescia
In this work, the design of a novel class of 3D dielectric lens antennas through the use of a lab-made electromagnetic tool is presented. The lens antenna is modeled using a generalized superformula allowing additional degree of freedom which can be exploited to obtain complex lens shapes with flat surface regions, steep sides, a non-rotational symmetry, or a modulated and aspherical surface profile. Thanks to the free parameters characterizing this formula, the lens geometry can be adjusted in a simple and analytical way. The electromagnetic tool is based on the geometrical optics and tube tracing approximations as well as the physical optics approach. In this way, the multiple wave reflections within the lens region as well as the far field outside the lens can be calculated. Moreover, an efficient synthesis procedure based on swarm intelligence has been developed and integrated in the numerical code. Thanks to this design tool it is possible to identify the lens parameters yielding the optimal antenna characteristic and a desired radiation patterns with low computational burden.
在这项工作中,通过使用实验室制造的电磁工具,介绍了一类新型三维介质透镜天线的设计。透镜天线使用广义超公式建模,允许额外的自由度,可利用这些自由度获得具有平坦表面区域、陡峭侧面、非旋转对称或调制和非球面表面轮廓的复杂透镜形状。得益于该公式的自由参数,透镜的几何形状可以通过简单的分析方法进行调整。电磁学工具基于几何光学和管跟踪近似以及物理光学方法。通过这种方法,可以计算透镜区域内的多重波反射以及透镜外的远场。此外,还开发了一种基于蜂群智能的高效合成程序,并将其集成到数值代码中。借助这一设计工具,可以确定透镜参数,从而以较低的计算负担获得最佳的天线特性和理想的辐射模式。
{"title":"Lens Antenna Design Tool Based on Generalized Superformula","authors":"Alberto Facchini;Francesco Paolo Chietera;Riccardo Colella;Luca Catarinucci;Pietro Bia;Luciano Mescia","doi":"10.1109/JRFID.2024.3396333","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3396333","url":null,"abstract":"In this work, the design of a novel class of 3D dielectric lens antennas through the use of a lab-made electromagnetic tool is presented. The lens antenna is modeled using a generalized superformula allowing additional degree of freedom which can be exploited to obtain complex lens shapes with flat surface regions, steep sides, a non-rotational symmetry, or a modulated and aspherical surface profile. Thanks to the free parameters characterizing this formula, the lens geometry can be adjusted in a simple and analytical way. The electromagnetic tool is based on the geometrical optics and tube tracing approximations as well as the physical optics approach. In this way, the multiple wave reflections within the lens region as well as the far field outside the lens can be calculated. Moreover, an efficient synthesis procedure based on swarm intelligence has been developed and integrated in the numerical code. Thanks to this design tool it is possible to identify the lens parameters yielding the optimal antenna characteristic and a desired radiation patterns with low computational burden.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"476-483"},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10517938","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141308677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Secrecy Performance of Energy-Harvesting Backscatter Communication Network Under Different Tag Selection Schemes 不同标签选择方案下能量收集反向散射通信网络的保密性能
Q2 ENGINEERING, ELECTRICAL & ELECTRONIC Pub Date : 2024-02-29 DOI: 10.1109/JRFID.2024.3371877
Yasin Khan;Aaqib Afzal;Ankit Dubey;Alok Saxena
This paper investigates the secrecy performance of a Backscatter communication (BackCom) network considering a practical non-linear energy harvesting model with various tag selection schemes. The tag circuit reflects the signal by finding the optimal dynamic reflection coefficient that maximizes the backscattered signal power while satisfying the tag energy constraint. The channel gains of all links follow Rayleigh fading model. Accounting performance and complexity trade-offs, two computationally efficient sub-optimal and a random selection schemes are proposed and analyzed. The performance is analyzed by obtaining the secrecy outage probability (SOP) and probability of intercept (POI) in closed-form. To gain further insights, expressions for the asymptotic SOP and POI are also derived for all selection schemes. We compare the proposed selection schemes with optimal selection scheme and conclude that proposed schemes significantly reduce the complexity and performs satisfactorily in terms of SOP and POI.
本文研究了背向散射通信(BackCom)网络的保密性能,考虑了一个实用的非线性能量采集模型和各种标签选择方案。标签电路通过寻找最优动态反射系数来反射信号,从而在满足标签能量约束的同时使反向散射信号功率最大化。所有链路的信道增益都遵循瑞利衰减模型。考虑到性能和复杂性的权衡,提出并分析了两种计算效率较高的次优方案和随机选择方案。通过闭合形式获得保密中断概率(SOP)和截获概率(POI),对性能进行了分析。为了进一步深入了解,还推导出了所有选择方案的渐近 SOP 和 POI 表达式。我们将提出的选择方案与最优选择方案进行了比较,得出的结论是,提出的方案大大降低了复杂性,在 SOP 和 POI 方面的表现令人满意。
{"title":"Secrecy Performance of Energy-Harvesting Backscatter Communication Network Under Different Tag Selection Schemes","authors":"Yasin Khan;Aaqib Afzal;Ankit Dubey;Alok Saxena","doi":"10.1109/JRFID.2024.3371877","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3371877","url":null,"abstract":"This paper investigates the secrecy performance of a Backscatter communication (BackCom) network considering a practical non-linear energy harvesting model with various tag selection schemes. The tag circuit reflects the signal by finding the optimal dynamic reflection coefficient that maximizes the backscattered signal power while satisfying the tag energy constraint. The channel gains of all links follow Rayleigh fading model. Accounting performance and complexity trade-offs, two computationally efficient sub-optimal and a random selection schemes are proposed and analyzed. The performance is analyzed by obtaining the secrecy outage probability (SOP) and probability of intercept (POI) in closed-form. To gain further insights, expressions for the asymptotic SOP and POI are also derived for all selection schemes. We compare the proposed selection schemes with optimal selection scheme and conclude that proposed schemes significantly reduce the complexity and performs satisfactorily in terms of SOP and POI.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"43-48"},"PeriodicalIF":0.0,"publicationDate":"2024-02-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140164191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Adaptive Multi-Task Learning for Multi-PAR in Real World 针对真实世界中多 PAR 的自适应多任务学习
Q2 ENGINEERING, ELECTRICAL & ELECTRONIC Pub Date : 2024-02-29 DOI: 10.1109/JRFID.2024.3371881
Haoyun Sun;Hongwei Zhao;Weishan Zhang;Liang Xu;Hongqing Guan
Multi-pedestrian attribute recognition (Multi-PAR) is a vital task for smart city surveillance applications, which requires identifying various attributes of multiple pedestrians in a single image. However, most existing methods are limited by the complex backgrounds and the time-consuming pedestrian detection preprocessing work in real-world scenarios, and cannot achieve satisfactory accuracy and efficiency. In this paper, we present a novel end-to-end solution, named Adaptive Multi-Task Network (AMTN), which jointly performs multiple tasks and leverages an adaptive feature re-extraction (AFRE) module to optimize them. Specially, We integrate pedestrian detection into AMTN to perform PAR preprocessing, and incorporate a person re-identification (ReID) task branch to track pedestrians in video streams, thereby selecting the clearest video frames for analysis instead of every video frame to improve analysis efficiency and recognition accuracy. Moreover, we design a dynamic weight fitting loss (DWFL) function to prevent gradient explosions and balance tasks during training. We conduct extensive experiments to evaluate the accuracy and efficiency of our approach, and compare it with the state-of-the-art methods. The experimental results demonstrate that our method outperforms other state-of-the-art algorithms, achieving 1.5%-4.9% improvement in accuracy on Multi-PAR. The experiments also show that the AMTN can greatly improve the efficiency of preprocessing by saving the computation of feature extraction through basic features sharing. Compared with the state-of-the-art detection algorithm Yolov5s, it can improve the efficiency by 42%.
多行人属性识别(Multi-PAR)是智慧城市监控应用中的一项重要任务,它要求在单幅图像中识别多个行人的各种属性。然而,现有的大多数方法受限于现实场景中复杂的背景和耗时的行人检测预处理工作,无法达到令人满意的精度和效率。在本文中,我们提出了一种新颖的端到端解决方案,名为自适应多任务网络(AMTN),它可以联合执行多项任务,并利用自适应特征再提取(AFRE)模块对其进行优化。特别是,我们在 AMTN 中集成了行人检测功能,以执行 PAR 预处理,并集成了人员再识别(ReID)任务分支,以跟踪视频流中的行人,从而选择最清晰的视频帧进行分析,而不是每个视频帧,以提高分析效率和识别准确率。此外,我们还设计了动态权重拟合损失(DWFL)函数,以防止训练过程中出现梯度爆炸和平衡任务。我们进行了大量实验来评估我们方法的准确性和效率,并将其与最先进的方法进行比较。实验结果表明,我们的方法优于其他最先进的算法,在 Multi-PAR 上的准确率提高了 1.5%-4.9%。实验还表明,AMTN 通过基本特征共享节省了特征提取的计算量,从而大大提高了预处理的效率。与最先进的检测算法 Yolov5s 相比,其效率提高了 42%。
{"title":"Adaptive Multi-Task Learning for Multi-PAR in Real World","authors":"Haoyun Sun;Hongwei Zhao;Weishan Zhang;Liang Xu;Hongqing Guan","doi":"10.1109/JRFID.2024.3371881","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3371881","url":null,"abstract":"Multi-pedestrian attribute recognition (Multi-PAR) is a vital task for smart city surveillance applications, which requires identifying various attributes of multiple pedestrians in a single image. However, most existing methods are limited by the complex backgrounds and the time-consuming pedestrian detection preprocessing work in real-world scenarios, and cannot achieve satisfactory accuracy and efficiency. In this paper, we present a novel end-to-end solution, named Adaptive Multi-Task Network (AMTN), which jointly performs multiple tasks and leverages an adaptive feature re-extraction (AFRE) module to optimize them. Specially, We integrate pedestrian detection into AMTN to perform PAR preprocessing, and incorporate a person re-identification (ReID) task branch to track pedestrians in video streams, thereby selecting the clearest video frames for analysis instead of every video frame to improve analysis efficiency and recognition accuracy. Moreover, we design a dynamic weight fitting loss (DWFL) function to prevent gradient explosions and balance tasks during training. We conduct extensive experiments to evaluate the accuracy and efficiency of our approach, and compare it with the state-of-the-art methods. The experimental results demonstrate that our method outperforms other state-of-the-art algorithms, achieving 1.5%-4.9% improvement in accuracy on Multi-PAR. The experiments also show that the AMTN can greatly improve the efficiency of preprocessing by saving the computation of feature extraction through basic features sharing. Compared with the state-of-the-art detection algorithm Yolov5s, it can improve the efficiency by 42%.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"357-366"},"PeriodicalIF":0.0,"publicationDate":"2024-02-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140924704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Advanced RFID-Robot With Rotating Antennas for Smart Inventory in High-Density Shelving Systems 带旋转天线的先进 RFID 机器人,用于高密度货架系统的智能盘点
Q2 ENGINEERING, ELECTRICAL & ELECTRONIC Pub Date : 2024-02-23 DOI: 10.1109/JRFID.2024.3369470
Andrea Motroni;Salvatore D’Avella;Alice Buffi;Paolo Tripicchio;Matteo Unetti;Glauco Cecchi;Paolo Nepa
This paper presents the development and testing of a robot designed for automated inventory and 3D localization of items in high-density shelving systems. To enhance accuracy in locating UHF-RFID tagged objects by using synthetic aperture-based methods, rotating antennas are installed on the robot. This allows more degrees of freedom in antenna trajectory, by reaching large synthetic apertures that may deliver high-performance localization. The robot can navigate complex environments by utilizing a depth camera and a visual odometry system, and it can effectively avoid obstacles with the help of a Laser Imaging Detection And Ranging system. Extensive testing is conducted in a realistic shop-like scenario where tagged products are placed on either wooden shelves or hung on metal racks. The robot navigation capabilities are verified together with its inventory and localization performance for different visibility conditions of the tagged items.
本文介绍了一种机器人的开发和测试情况,该机器人专为高密度货架系统中物品的自动盘点和三维定位而设计。为了利用基于合成孔径的方法提高 UHF-RFID 标签物品定位的准确性,机器人上安装了旋转天线。这样,天线轨迹的自由度更大,合成孔径也更大,可以实现高性能定位。该机器人可利用深度摄像头和视觉里程测量系统在复杂环境中导航,并可在激光成像探测和测距系统的帮助下有效避开障碍物。在类似商店的真实场景中进行了广泛的测试,将贴有标签的产品放在木制货架上或挂在金属架上。测试验证了机器人的导航能力,以及在不同可见度条件下标记物品的清点和定位性能。
{"title":"Advanced RFID-Robot With Rotating Antennas for Smart Inventory in High-Density Shelving Systems","authors":"Andrea Motroni;Salvatore D’Avella;Alice Buffi;Paolo Tripicchio;Matteo Unetti;Glauco Cecchi;Paolo Nepa","doi":"10.1109/JRFID.2024.3369470","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3369470","url":null,"abstract":"This paper presents the development and testing of a robot designed for automated inventory and 3D localization of items in high-density shelving systems. To enhance accuracy in locating UHF-RFID tagged objects by using synthetic aperture-based methods, rotating antennas are installed on the robot. This allows more degrees of freedom in antenna trajectory, by reaching large synthetic apertures that may deliver high-performance localization. The robot can navigate complex environments by utilizing a depth camera and a visual odometry system, and it can effectively avoid obstacles with the help of a Laser Imaging Detection And Ranging system. Extensive testing is conducted in a realistic shop-like scenario where tagged products are placed on either wooden shelves or hung on metal racks. The robot navigation capabilities are verified together with its inventory and localization performance for different visibility conditions of the tagged items.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"559-570"},"PeriodicalIF":0.0,"publicationDate":"2024-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10443987","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141422474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Mitigation of Metal Body Proximity Effect in Magnetically Coupled HF RFID Systems 缓解磁耦合高频射频识别系统中的金属体接近效应
Q2 ENGINEERING, ELECTRICAL & ELECTRONIC Pub Date : 2024-02-22 DOI: 10.1109/JRFID.2024.3368882
Somnath Mukherjee;Debidas Kundu;Ashis Khan
The deleterious effect of eddy current due to the presence of a metal in magnetically coupled resonant high-frequency radio frequency identification (HF RFID) systems is addressed, and remediation using a resonant loop is discussed. The proposed solution is much more economic than conventional ferrite-based shielding. The resonant loop, which is referred to as auxiliary coil in this paper, does not increase the profile of the existing HF RFID tag. Analysis is carried out using full-wave numerical simulation resulting in an equivalent circuit model, and validated with measurements. The technique is illustrated through applications like HF RFID tags in close proximity to a metal seal required for induction sealing, as well for extending read range of readers compelled to operate near metallic environment.
本文探讨了在磁耦合谐振高频射频识别(HF RFID)系统中由于金属的存在而产生的涡流有害影响,并讨论了使用谐振回路进行补救的问题。所提出的解决方案比传统的铁氧体屏蔽更经济。谐振回路在本文中被称为辅助线圈,不会增加现有高频射频识别(RFID)标签的外形尺寸。分析采用全波数值模拟,得出等效电路模型,并通过测量进行验证。该技术的应用实例包括高频射频识别(RFID)标签靠近感应密封所需的金属密封件,以及扩大阅读器的读取范围,这些阅读器必须在金属环境附近工作。
{"title":"Mitigation of Metal Body Proximity Effect in Magnetically Coupled HF RFID Systems","authors":"Somnath Mukherjee;Debidas Kundu;Ashis Khan","doi":"10.1109/JRFID.2024.3368882","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3368882","url":null,"abstract":"The deleterious effect of eddy current due to the presence of a metal in magnetically coupled resonant high-frequency radio frequency identification (HF RFID) systems is addressed, and remediation using a resonant loop is discussed. The proposed solution is much more economic than conventional ferrite-based shielding. The resonant loop, which is referred to as auxiliary coil in this paper, does not increase the profile of the existing HF RFID tag. Analysis is carried out using full-wave numerical simulation resulting in an equivalent circuit model, and validated with measurements. The technique is illustrated through applications like HF RFID tags in close proximity to a metal seal required for induction sealing, as well for extending read range of readers compelled to operate near metallic environment.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"421-430"},"PeriodicalIF":0.0,"publicationDate":"2024-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141073591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multi-Class Road Target Detection Based on Multi-Gradient Flow Residual Structure 基于多梯度流残差结构的多类道路目标检测
Q2 ENGINEERING, ELECTRICAL & ELECTRONIC Pub Date : 2024-02-21 DOI: 10.1109/JRFID.2024.3368226
Leilei Xie;Zheng Li;Fenghua Zhu
Aiming at the problem of false and missed detection due to the varied and dense target scale changes, the presence of occlusion, and insufficient light in the target detection task of complex road scenes for self-driving vehicles, an improved model YOLOv8-AUT based on YOLOv8 complex road target detection is proposed. Firstly, the MFR module is designed based on the multi-gradient flow residual structure of the attention mechanism, and the parallel gradient flow branches are added to the module to enrich the gradient flow of the model, so as to enhance the ability to extract the detailed information, and to improve the omission and misdetection of the small targets on the road. Secondly, the spatial pyramid network structure is improved using full-dimensional dynamic convolution to increase the sensory field of the model and improve the model’s ability to detect targets of different scales in complex backgrounds. Finally, the soft-NMS suppression algorithm is introduced to solve the problem of severe target leakage detection in obstacle-target dense regions. The experimental data show that on the BDD100K dataset, the improved algorithm improves the average accuracy mean by 7.7% compared with the original algorithm, mAP@0.5:0.9 by 5.7%, which proves that YOLOv8-AUT can better satisfy the demand for target detection in complex road scenarios of autonomous driving.
针对自动驾驶车辆在复杂道路场景目标检测任务中,由于目标尺度变化多样且密集、存在遮挡、光线不足等原因导致的误检和漏检问题,提出了基于YOLOv8复杂道路目标检测的改进模型YOLOv8-AUT。首先,基于注意力机制的多梯度流残差结构设计了MFR模块,并在该模块中加入平行梯度流分支,丰富了模型的梯度流,从而增强了对细节信息的提取能力,改善了对路面小目标的遗漏和误检。其次,利用全维动态卷积改进空间金字塔网络结构,增加模型的感知场,提高模型对复杂背景下不同尺度目标的检测能力。最后,引入软 NMS 抑制算法,解决了障碍物-目标密集区域目标漏检严重的问题。实验数据表明,在 BDD100K 数据集上,改进算法的平均准确率比原始算法提高了 7.7%,mAP@0.5:0.9,提高了 5.7%,证明 YOLOv8-AUT 能够更好地满足自动驾驶复杂道路场景下的目标检测需求。
{"title":"Multi-Class Road Target Detection Based on Multi-Gradient Flow Residual Structure","authors":"Leilei Xie;Zheng Li;Fenghua Zhu","doi":"10.1109/JRFID.2024.3368226","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3368226","url":null,"abstract":"Aiming at the problem of false and missed detection due to the varied and dense target scale changes, the presence of occlusion, and insufficient light in the target detection task of complex road scenes for self-driving vehicles, an improved model YOLOv8-AUT based on YOLOv8 complex road target detection is proposed. Firstly, the MFR module is designed based on the multi-gradient flow residual structure of the attention mechanism, and the parallel gradient flow branches are added to the module to enrich the gradient flow of the model, so as to enhance the ability to extract the detailed information, and to improve the omission and misdetection of the small targets on the road. Secondly, the spatial pyramid network structure is improved using full-dimensional dynamic convolution to increase the sensory field of the model and improve the model’s ability to detect targets of different scales in complex backgrounds. Finally, the soft-NMS suppression algorithm is introduced to solve the problem of severe target leakage detection in obstacle-target dense regions. The experimental data show that on the BDD100K dataset, the improved algorithm improves the average accuracy mean by 7.7% compared with the original algorithm, mAP@0.5:0.9 by 5.7%, which proves that YOLOv8-AUT can better satisfy the demand for target detection in complex road scenarios of autonomous driving.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"348-356"},"PeriodicalIF":0.0,"publicationDate":"2024-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140924705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
UnstrPrompt: Large Language Model Prompt for Driving in Unstructured Scenarios UnstrPrompt:用于非结构化场景驾驶的大型语言模型提示
Q2 ENGINEERING, ELECTRICAL & ELECTRONIC Pub Date : 2024-02-20 DOI: 10.1109/JRFID.2024.3367975
Yuchen Li;Luxi Li;Zizhang Wu;Zhenshan Bing;Zhe Xuanyuan;Alois Christian Knoll;Long Chen
The integration of language descriptions or prompts with Large Language Models (LLMs) into visual tasks is currently a focal point in the advancement of autonomous driving. This study has showcased notable advancements across various standard datasets. Nevertheless, the progress in integrating language prompts faces challenges in unstructured scenarios, primarily due to the limited availability of paired data. To address this challenge, we introduce a groundbreaking language prompt set called “UnstrPrompt.” This prompt set is derived from three prominent unstructured autonomous driving datasets: IDD, ORFD, and AutoMine, collectively comprising a total of 6K language descriptions. In response to the distinctive features of unstructured scenarios, we have developed a structured approach for prompt generation, encompassing three key components: scene, road, and instance. Additionally, we provide a detailed overview of the language generation process and the validation procedures. We conduct tests on segmentation tasks, and our experiments have demonstrated that text-image fusion can improve accuracy by more than 3% on unstructured data. Additionally, our description architecture outperforms the generic urban architecture by more than 0.1%. This work holds the potential to advance various aspects such as interaction and foundational models in this scenario.
将语言描述或提示与大型语言模型(LLM)整合到视觉任务中,是目前自动驾驶技术发展的一个焦点。这项研究在各种标准数据集方面取得了显著进展。然而,在非结构化场景中,整合语言提示的进展面临挑战,这主要是由于配对数据的可用性有限。为了应对这一挑战,我们推出了一个突破性的语言提示集,名为 "UnstrPrompt"。该提示集来自三个著名的非结构化自动驾驶数据集:IDD、ORFD 和 AutoMine,总共包含 6K 条语言描述。针对非结构化场景的显著特点,我们开发了一种结构化的提示生成方法,包括三个关键组成部分:场景、道路和实例。此外,我们还详细介绍了语言生成过程和验证程序。我们对分割任务进行了测试,实验证明,文本-图像融合可将非结构化数据的准确率提高 3% 以上。此外,我们的描述架构比一般的城市架构高出 0.1% 以上。这项工作有望推动该场景中交互和基础模型等各个方面的发展。
{"title":"UnstrPrompt: Large Language Model Prompt for Driving in Unstructured Scenarios","authors":"Yuchen Li;Luxi Li;Zizhang Wu;Zhenshan Bing;Zhe Xuanyuan;Alois Christian Knoll;Long Chen","doi":"10.1109/JRFID.2024.3367975","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3367975","url":null,"abstract":"The integration of language descriptions or prompts with Large Language Models (LLMs) into visual tasks is currently a focal point in the advancement of autonomous driving. This study has showcased notable advancements across various standard datasets. Nevertheless, the progress in integrating language prompts faces challenges in unstructured scenarios, primarily due to the limited availability of paired data. To address this challenge, we introduce a groundbreaking language prompt set called “UnstrPrompt.” This prompt set is derived from three prominent unstructured autonomous driving datasets: IDD, ORFD, and AutoMine, collectively comprising a total of 6K language descriptions. In response to the distinctive features of unstructured scenarios, we have developed a structured approach for prompt generation, encompassing three key components: scene, road, and instance. Additionally, we provide a detailed overview of the language generation process and the validation procedures. We conduct tests on segmentation tasks, and our experiments have demonstrated that text-image fusion can improve accuracy by more than 3% on unstructured data. Additionally, our description architecture outperforms the generic urban architecture by more than 0.1%. This work holds the potential to advance various aspects such as interaction and foundational models in this scenario.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"367-375"},"PeriodicalIF":0.0,"publicationDate":"2024-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140924703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Thin Microwave Absorber Based on Laser-Induced Graphene Frequency Selective Surfaces 基于激光诱导石墨烯频率选择性表面的薄型微波吸收器
Q2 ENGINEERING, ELECTRICAL & ELECTRONIC Pub Date : 2024-02-20 DOI: 10.1109/JRFID.2024.3368005
Yann Houeix;Francisco J. Romero;Francisco G. Ruiz;Diego P. Morales;Noel Rodriguez;Darine Kaddour
This study presents a pioneering approach to fabricating single-layer Frequency Selective Surfaces (FSS) using Laser-Induced Graphene (LIG). The FSS structure proposed consists of periodic resistive patterns of LIG synthesized through a one-step laser photothermal process directly on the surface of a thin polyimide substrate. The structural and electrical properties of LIG were thoroughly investigated to develop an electrical model aiming at optimizing the design and absorbing properties. After that, a 12 mm thick LIG-FSS microwave absorber prototype was fabricated and tested under real conditions, demonstrating over 90% absorption in the frequency band from 1.69 to 2.91 GHz with a thickness of only 0.068 times the maximum wavelength $(lambda _{mathrm{ max}})$ , demonstrating good agreement with the simulations and theoretical results. Additionally, we discuss the tunability of the frequency response of the absorber by adjusting accordingly the induced material’s properties. Finally, we also demonstrate the versatility of this approach for the fabrication of FSS structures based on alternative patterns. The findings presented in this work highlight the promising potential of sustainable microwave absorbers based on LIG-FSS structures.
本研究提出了一种利用激光诱导石墨烯(LIG)制造单层频率选择表面(FSS)的开创性方法。所提出的 FSS 结构由通过一步激光光热工艺直接在聚酰亚胺薄基底表面合成的 LIG 周期性电阻图案组成。对 LIG 的结构和电气特性进行了深入研究,以建立一个电气模型,优化设计和吸收特性。之后,我们制作了一个 12 毫米厚的 LIG-FSS 微波吸收器原型,并在实际条件下进行了测试,在 1.69 至 2.91 GHz 的频段内显示出超过 90% 的吸收率,而其厚度仅为最大波长 $(lambda _{mathrm{ max}})$ 的 0.068 倍,与模拟和理论结果非常吻合。此外,我们还讨论了通过相应调整诱导材料的特性来调整吸收器频率响应的可调性。最后,我们还展示了这种方法在基于替代模式制造 FSS 结构方面的多功能性。这项研究成果凸显了基于 LIG-FSS 结构的可持续微波吸收器的巨大潜力。
{"title":"Thin Microwave Absorber Based on Laser-Induced Graphene Frequency Selective Surfaces","authors":"Yann Houeix;Francisco J. Romero;Francisco G. Ruiz;Diego P. Morales;Noel Rodriguez;Darine Kaddour","doi":"10.1109/JRFID.2024.3368005","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3368005","url":null,"abstract":"This study presents a pioneering approach to fabricating single-layer Frequency Selective Surfaces (FSS) using Laser-Induced Graphene (LIG). The FSS structure proposed consists of periodic resistive patterns of LIG synthesized through a one-step laser photothermal process directly on the surface of a thin polyimide substrate. The structural and electrical properties of LIG were thoroughly investigated to develop an electrical model aiming at optimizing the design and absorbing properties. After that, a 12 mm thick LIG-FSS microwave absorber prototype was fabricated and tested under real conditions, demonstrating over 90% absorption in the frequency band from 1.69 to 2.91 GHz with a thickness of only 0.068 times the maximum wavelength \u0000<inline-formula> <tex-math>$(lambda _{mathrm{ max}})$ </tex-math></inline-formula>\u0000, demonstrating good agreement with the simulations and theoretical results. Additionally, we discuss the tunability of the frequency response of the absorber by adjusting accordingly the induced material’s properties. Finally, we also demonstrate the versatility of this approach for the fabrication of FSS structures based on alternative patterns. The findings presented in this work highlight the promising potential of sustainable microwave absorbers based on LIG-FSS structures.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"168-175"},"PeriodicalIF":0.0,"publicationDate":"2024-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10440440","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140880810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Practical Guide to Optimal Impedance Matching for UHF RFID Chip 超高频 RFID 芯片最佳阻抗匹配实用指南
Q2 ENGINEERING, ELECTRICAL & ELECTRONIC Pub Date : 2024-02-19 DOI: 10.1109/JRFID.2024.3367452
Nicolas Barbot;Ionela Prodan;Pavel Nikitin
This paper shows that the classical conjugate impedance matching used in the UHF RFID is not optimal anymore with new chips that have high sensitivity. The optimal matching allowing to maximize the read range of an RFID system (reader and tag) is introduced. The principle relies on finding the optimal trade-off between the power received by the tag and the modulated power backscattered to the reader. This matching depends on both tag and reader parameters. The proposed method is optimal and can be applied to any tag (passive and semi-passive). Compared to classical conjugate impedance matching, we show that this new approach can increase the read range by 22% and 8% in two examples: for a semi-passive tag based on Monza X8-K Dura chip and a passive tag based on Monza R6-P chip, respectively. Finally, a practical guide is proposed for antenna designers to optimize the matching in practical applications.
本文表明,超高频射频识别(UHF RFID)中使用的经典共轭阻抗匹配对于具有高灵敏度的新型芯片来说已不再是最佳匹配。本文介绍了可最大化 RFID 系统(读取器和标签)读取范围的最佳匹配方法。其原理在于找到标签接收功率与读取器反向散射调制功率之间的最佳平衡点。这种匹配取决于标签和阅读器的参数。所提出的方法是最优的,可应用于任何标签(无源和半无源)。与传统的共轭阻抗匹配相比,我们在两个例子中展示了这种新方法能将读取范围分别提高 22% 和 8%:一个是基于 Monza X8-K Dura 芯片的半无源标签,另一个是基于 Monza R6-P 芯片的无源标签。最后,还为天线设计人员提出了在实际应用中优化匹配的实用指南。
{"title":"A Practical Guide to Optimal Impedance Matching for UHF RFID Chip","authors":"Nicolas Barbot;Ionela Prodan;Pavel Nikitin","doi":"10.1109/JRFID.2024.3367452","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3367452","url":null,"abstract":"This paper shows that the classical conjugate impedance matching used in the UHF RFID is not optimal anymore with new chips that have high sensitivity. The optimal matching allowing to maximize the read range of an RFID system (reader and tag) is introduced. The principle relies on finding the optimal trade-off between the power received by the tag and the modulated power backscattered to the reader. This matching depends on both tag and reader parameters. The proposed method is optimal and can be applied to any tag (passive and semi-passive). Compared to classical conjugate impedance matching, we show that this new approach can increase the read range by 22% and 8% in two examples: for a semi-passive tag based on Monza X8-K Dura chip and a passive tag based on Monza R6-P chip, respectively. Finally, a practical guide is proposed for antenna designers to optimize the matching in practical applications.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"145-153"},"PeriodicalIF":0.0,"publicationDate":"2024-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140880762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
IEEE journal of radio frequency identification
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1