针对含光伏(photovoltaic,PV)、电动汽车(electric vehicle,EV)及家庭电器负荷的智能社区,以车入户(vehicle to home,V2H)的形式将EV纳入家庭需求响应框架,利用EV的双向输能特性并考虑EV充/放电带来的电池容量退化成本,协同PV、电网的...针对含光伏(photovoltaic,PV)、电动汽车(electric vehicle,EV)及家庭电器负荷的智能社区,以车入户(vehicle to home,V2H)的形式将EV纳入家庭需求响应框架,利用EV的双向输能特性并考虑EV充/放电带来的电池容量退化成本,协同PV、电网的实时电价和用户需求的可容忍时延,基于Lyapunov优化理论提出随机环境下V2H用户的EV充/放电调度策略和每户家庭的负荷响应策略,最小化家庭用户的长期平均购电成本。并提出一种智能社区在线能量交易方案,旨在最小化智能社区总的购电成本、最大限度提高社区能源利用率。理论分析和仿真结果表明,所提算法无需实时电价、PV出力、用户负荷需求的先验概率信息,仅基于当前系统状态就可使优化目标趋于最优值,实现家庭用户的能量调度和家庭用户之间的能量共享,减少家庭购电成本,提高用户之间能量交易的灵活性。展开更多
This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagno...This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagnostic performance and computational efficiency.To this end,a total of 3234 high-resolution images(2400×1080)were collected from three major rice diseases Rice Blast,Bacterial Blight,and Brown Spot—frequently found in actual rice cultivation fields.These images served as the training dataset.The proposed YOLOv5-V2 model removes the Focus layer from the original YOLOv5s and integrates ShuffleNet V2 into the backbone,thereby resulting in both model compression and improved inference speed.Additionally,YOLOv5-P,based on PP-PicoDet,was configured as a comparative model to quantitatively evaluate performance.Experimental results demonstrated that YOLOv5-V2 achieved excellent detection performance,with an mAP 0.5 of 89.6%,mAP 0.5–0.95 of 66.7%,precision of 91.3%,and recall of 85.6%,while maintaining a lightweight model size of 6.45 MB.In contrast,YOLOv5-P exhibited a smaller model size of 4.03 MB,but showed lower performance with an mAP 0.5 of 70.3%,mAP 0.5–0.95 of 35.2%,precision of 62.3%,and recall of 74.1%.This study lays a technical foundation for the implementation of smart agriculture and real-time disease diagnosis systems by proposing a model that satisfies both accuracy and lightweight requirements.展开更多
针对柑橘病虫害图像实时采集与检测过程中无人机运动和摄像头对焦不准导致的模糊问题,提出了一种高效的去模糊算法,即在目标检测算法前增加去模糊预处理环节,旨在提升图像清晰度,并增强检测精度和鲁棒性。本研究在DeblurGAN-v2主干网络...针对柑橘病虫害图像实时采集与检测过程中无人机运动和摄像头对焦不准导致的模糊问题,提出了一种高效的去模糊算法,即在目标检测算法前增加去模糊预处理环节,旨在提升图像清晰度,并增强检测精度和鲁棒性。本研究在DeblurGAN-v2主干网络中采用FPN-MobileNetv3-small轻量化结构,并引入SKNet(Selective Kernel Networks)注意力机制自适应选择卷积核尺寸,以实现轻量化和高效去模糊。此外,使用自校准卷积网络(Self-Calibrated Convolutions)动态调整卷积视场,丰富卷积表达,实际解决去模糊过程中细节易丢失、特征融合效果不理想的问题。试验结果表明:与原始模型相比,改进后模型的峰值信噪比(Peak Signal to Noise Ratio,PSNR)提升了3.25 dB,结构相似性指数(Structural Similarity,SSIM)提升了9.26%,模型大小为16.4 M,处理速度为41.7 FPS。利用YOLOv8模型进行目标检测,在模型召回率没有明显降低的情况下,模型的准确率(Precision,P)和平均检测精度均值(Mean of Average Precision,mAP)分别提升了3.8、1.8个百分点,验证了该去模糊算法的有效性。本研究为柑橘病虫害检测提供了更高质量的图像,对实现精准农业和提高农产品经济价值具有重要意义。展开更多
In real-world autonomous driving tests,unexpected events such as pedestrians or wild animals suddenly entering the driving path can occur.Conducting actual test drives under various weather conditions may also lead to...In real-world autonomous driving tests,unexpected events such as pedestrians or wild animals suddenly entering the driving path can occur.Conducting actual test drives under various weather conditions may also lead to dangerous situations.Furthermore,autonomous vehicles may operate abnormally in bad weather due to limitations of their sensors and GPS.Driving simulators,which replicate driving conditions nearly identical to those in the real world,can drastically reduce the time and cost required for market entry validation;consequently,they have become widely used.In this paper,we design a virtual driving test environment capable of collecting and verifying SiLS data under adverse weather conditions using multi-source images.The proposed method generates a virtual testing environment that incorporates various events,including weather,time of day,and moving objects,that cannot be easily verified in real-world autonomous driving tests.By setting up scenario-based virtual environment events,multi-source image analysis and verification using real-world DCUs(Data Concentrator Units)with V2X-Car edge cloud can effectively address risk factors that may arise in real-world situations.We tested and validated the proposed method with scenarios employing V2X communication and multi-source image analysis.展开更多
V2X communication enables vehicles to share real-time traffic and road-condition data,but binding messages to persistent identifiers enables location tracking.Furthermore,since forged reports from malicious vehicles c...V2X communication enables vehicles to share real-time traffic and road-condition data,but binding messages to persistent identifiers enables location tracking.Furthermore,since forged reports from malicious vehicles can distort trust decisions and threaten road safety,privacy-preserving trust management is essential.Lu et al.previously presented BARS,an anonymous reputation mechanism founded on blockchain technology to establish a privacy-preserving trust architecture for V2X communication.In this system,reputation certificates without a vehicle identifier ensure anonymity,while two authorities jointly manage certificate issuance and reputation updates.However,the centralized certificate updates introduce scalability limitations,and the authorities can trace vehicle behavioral information,which threatens privacy guarantees.Several subsequent systems derived from BARS still rely on centralized certificate management and are subject to authority-side privacy leakage.As a result,a key challenge in this line of research remains unresolved:how to decentralize the certificate-update process while preserving privacy against the authorities in privacy-preservingV2X trustmanagement.In this paper,we propose a distributed anonymous reputation system for V2X communication,based on an anonymous reputation system for crowdsensing.In our proposed system for V2X communication,the server is distributed to a certificate authority(CA)and roadside units(RSUs).Each vehicle shows the reputation level to the nearest RSU at the beginning of each time interval,and registers a short-time public key.In the interval,the messages from the vehicle are authenticated under the public key and are scored.At the end of the interval,the nearest RSU updates the certificate anonymously.Our solution decentralizes the certificate-update process by assigning each update to the nearest RSU.A zero-knowledge-proof-based show protocol removes the need for any central authority to handle vehicle certificates and thus prevents the authorities from tracing vehicle activities.Compared with BARS,where centralized authorities must update the reputation certificates of many vehicles and may incur communication and processing delays,our system performs each update locally at the nearest RSUonce per interval.The required interaction consists only of a fewkilobytes of communication and a zero-knowledge proof that is almost fully precomputed on the vehicle side,while the RSU-side processing is estimated to take about 40 ms based on timingmeasurements of the underlying cryptographic operations.This distributed updatemodel avoids the centralized bottleneck of BARS and simultaneously removes the privacy risk arising from authority collusion.展开更多
精确的环境感知是实现自主代客泊车(automated valet parking,AVP)功能的基础,传统的AVP系统主要依赖于单车的感知,但随着场端智能技术的不断发展,车端与场端之间协同交互成为自主代客泊车落地的必然趋势。本文提出了一种基于V2X车场协...精确的环境感知是实现自主代客泊车(automated valet parking,AVP)功能的基础,传统的AVP系统主要依赖于单车的感知,但随着场端智能技术的不断发展,车端与场端之间协同交互成为自主代客泊车落地的必然趋势。本文提出了一种基于V2X车场协同的地下停车场全域感知方法,该方法将地下停车场的全域感知问题转化为大规模图模型的构建与优化问题。通过输入场端激光雷达、摄像头的传感器信息以及智能网联车的感知数据,以车辆位姿为节点,建立多种边约束关系。为了提高感知精度,本文提出了一种融合车道级地图信息的大规模图模型方法,通过将停放车辆作为半静态信息约束,并结合车道级地图信息构建横向约束,在求解过程中引入滑动窗口以减小图模型的规模,最终以地图形式输出感知结果供车端使用。通过仿真实验和在占地面积为2 500 m^(2)以上的地下停车场场景中进行实地实验,结果表明,该方法显著提升了在复杂停车场环境下的感知能力,实现了地下停车场的全域感知。展开更多
文摘针对含光伏(photovoltaic,PV)、电动汽车(electric vehicle,EV)及家庭电器负荷的智能社区,以车入户(vehicle to home,V2H)的形式将EV纳入家庭需求响应框架,利用EV的双向输能特性并考虑EV充/放电带来的电池容量退化成本,协同PV、电网的实时电价和用户需求的可容忍时延,基于Lyapunov优化理论提出随机环境下V2H用户的EV充/放电调度策略和每户家庭的负荷响应策略,最小化家庭用户的长期平均购电成本。并提出一种智能社区在线能量交易方案,旨在最小化智能社区总的购电成本、最大限度提高社区能源利用率。理论分析和仿真结果表明,所提算法无需实时电价、PV出力、用户负荷需求的先验概率信息,仅基于当前系统状态就可使优化目标趋于最优值,实现家庭用户的能量调度和家庭用户之间的能量共享,减少家庭购电成本,提高用户之间能量交易的灵活性。
文摘This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagnostic performance and computational efficiency.To this end,a total of 3234 high-resolution images(2400×1080)were collected from three major rice diseases Rice Blast,Bacterial Blight,and Brown Spot—frequently found in actual rice cultivation fields.These images served as the training dataset.The proposed YOLOv5-V2 model removes the Focus layer from the original YOLOv5s and integrates ShuffleNet V2 into the backbone,thereby resulting in both model compression and improved inference speed.Additionally,YOLOv5-P,based on PP-PicoDet,was configured as a comparative model to quantitatively evaluate performance.Experimental results demonstrated that YOLOv5-V2 achieved excellent detection performance,with an mAP 0.5 of 89.6%,mAP 0.5–0.95 of 66.7%,precision of 91.3%,and recall of 85.6%,while maintaining a lightweight model size of 6.45 MB.In contrast,YOLOv5-P exhibited a smaller model size of 4.03 MB,but showed lower performance with an mAP 0.5 of 70.3%,mAP 0.5–0.95 of 35.2%,precision of 62.3%,and recall of 74.1%.This study lays a technical foundation for the implementation of smart agriculture and real-time disease diagnosis systems by proposing a model that satisfies both accuracy and lightweight requirements.
文摘针对柑橘病虫害图像实时采集与检测过程中无人机运动和摄像头对焦不准导致的模糊问题,提出了一种高效的去模糊算法,即在目标检测算法前增加去模糊预处理环节,旨在提升图像清晰度,并增强检测精度和鲁棒性。本研究在DeblurGAN-v2主干网络中采用FPN-MobileNetv3-small轻量化结构,并引入SKNet(Selective Kernel Networks)注意力机制自适应选择卷积核尺寸,以实现轻量化和高效去模糊。此外,使用自校准卷积网络(Self-Calibrated Convolutions)动态调整卷积视场,丰富卷积表达,实际解决去模糊过程中细节易丢失、特征融合效果不理想的问题。试验结果表明:与原始模型相比,改进后模型的峰值信噪比(Peak Signal to Noise Ratio,PSNR)提升了3.25 dB,结构相似性指数(Structural Similarity,SSIM)提升了9.26%,模型大小为16.4 M,处理速度为41.7 FPS。利用YOLOv8模型进行目标检测,在模型召回率没有明显降低的情况下,模型的准确率(Precision,P)和平均检测精度均值(Mean of Average Precision,mAP)分别提升了3.8、1.8个百分点,验证了该去模糊算法的有效性。本研究为柑橘病虫害检测提供了更高质量的图像,对实现精准农业和提高农产品经济价值具有重要意义。
基金supported by Institute of Information and Communications Technology Planning and Evaluation(IITP)grant funded by the Korean government(MSIT)(No.2019-0-01842,Artificial Intelligence Graduate School Program(GIST))supported by Korea Planning&Evaluation Institute of Industrial Technology(KEIT)grant funded by the Ministry of Trade,Industry&Energy(MOTIE,Republic of Korea)(RS-2025-25448249+1 种基金Automotive Industry Technology Development(R&D)Program)supported by the Regional Innovation System&Education(RISE)programthrough the(Gwangju RISE Center),funded by the Ministry of Education(MOE)and the Gwangju Metropolitan City,Republic of Korea(2025-RISE-05-001).
文摘In real-world autonomous driving tests,unexpected events such as pedestrians or wild animals suddenly entering the driving path can occur.Conducting actual test drives under various weather conditions may also lead to dangerous situations.Furthermore,autonomous vehicles may operate abnormally in bad weather due to limitations of their sensors and GPS.Driving simulators,which replicate driving conditions nearly identical to those in the real world,can drastically reduce the time and cost required for market entry validation;consequently,they have become widely used.In this paper,we design a virtual driving test environment capable of collecting and verifying SiLS data under adverse weather conditions using multi-source images.The proposed method generates a virtual testing environment that incorporates various events,including weather,time of day,and moving objects,that cannot be easily verified in real-world autonomous driving tests.By setting up scenario-based virtual environment events,multi-source image analysis and verification using real-world DCUs(Data Concentrator Units)with V2X-Car edge cloud can effectively address risk factors that may arise in real-world situations.We tested and validated the proposed method with scenarios employing V2X communication and multi-source image analysis.
文摘V2X communication enables vehicles to share real-time traffic and road-condition data,but binding messages to persistent identifiers enables location tracking.Furthermore,since forged reports from malicious vehicles can distort trust decisions and threaten road safety,privacy-preserving trust management is essential.Lu et al.previously presented BARS,an anonymous reputation mechanism founded on blockchain technology to establish a privacy-preserving trust architecture for V2X communication.In this system,reputation certificates without a vehicle identifier ensure anonymity,while two authorities jointly manage certificate issuance and reputation updates.However,the centralized certificate updates introduce scalability limitations,and the authorities can trace vehicle behavioral information,which threatens privacy guarantees.Several subsequent systems derived from BARS still rely on centralized certificate management and are subject to authority-side privacy leakage.As a result,a key challenge in this line of research remains unresolved:how to decentralize the certificate-update process while preserving privacy against the authorities in privacy-preservingV2X trustmanagement.In this paper,we propose a distributed anonymous reputation system for V2X communication,based on an anonymous reputation system for crowdsensing.In our proposed system for V2X communication,the server is distributed to a certificate authority(CA)and roadside units(RSUs).Each vehicle shows the reputation level to the nearest RSU at the beginning of each time interval,and registers a short-time public key.In the interval,the messages from the vehicle are authenticated under the public key and are scored.At the end of the interval,the nearest RSU updates the certificate anonymously.Our solution decentralizes the certificate-update process by assigning each update to the nearest RSU.A zero-knowledge-proof-based show protocol removes the need for any central authority to handle vehicle certificates and thus prevents the authorities from tracing vehicle activities.Compared with BARS,where centralized authorities must update the reputation certificates of many vehicles and may incur communication and processing delays,our system performs each update locally at the nearest RSUonce per interval.The required interaction consists only of a fewkilobytes of communication and a zero-knowledge proof that is almost fully precomputed on the vehicle side,while the RSU-side processing is estimated to take about 40 ms based on timingmeasurements of the underlying cryptographic operations.This distributed updatemodel avoids the centralized bottleneck of BARS and simultaneously removes the privacy risk arising from authority collusion.
文摘精确的环境感知是实现自主代客泊车(automated valet parking,AVP)功能的基础,传统的AVP系统主要依赖于单车的感知,但随着场端智能技术的不断发展,车端与场端之间协同交互成为自主代客泊车落地的必然趋势。本文提出了一种基于V2X车场协同的地下停车场全域感知方法,该方法将地下停车场的全域感知问题转化为大规模图模型的构建与优化问题。通过输入场端激光雷达、摄像头的传感器信息以及智能网联车的感知数据,以车辆位姿为节点,建立多种边约束关系。为了提高感知精度,本文提出了一种融合车道级地图信息的大规模图模型方法,通过将停放车辆作为半静态信息约束,并结合车道级地图信息构建横向约束,在求解过程中引入滑动窗口以减小图模型的规模,最终以地图形式输出感知结果供车端使用。通过仿真实验和在占地面积为2 500 m^(2)以上的地下停车场场景中进行实地实验,结果表明,该方法显著提升了在复杂停车场环境下的感知能力,实现了地下停车场的全域感知。
