With the rapid adoption of artificial intelligence(AI)in domains such as power,transportation,and finance,the number of machine learning and deep learning models has grown exponentially.However,challenges such as dela...With the rapid adoption of artificial intelligence(AI)in domains such as power,transportation,and finance,the number of machine learning and deep learning models has grown exponentially.However,challenges such as delayed retraining,inconsistent version management,insufficient drift monitoring,and limited data security still hinder efficient and reliable model operations.To address these issues,this paper proposes the Intelligent Model Lifecycle Management Algorithm(IMLMA).The algorithm employs a dual-trigger mechanism based on both data volume thresholds and time intervals to automate retraining,and applies Bayesian optimization for adaptive hyperparameter tuning to improve performance.A multi-metric replacement strategy,incorporating MSE,MAE,and R2,ensures that new models replace existing ones only when performance improvements are guaranteed.A versioning and traceability database supports comparison and visualization,while real-time monitoring with stability analysis enables early warnings of latency and drift.Finally,hash-based integrity checks secure both model files and datasets.Experimental validation in a power metering operation scenario demonstrates that IMLMA reduces model update delays,enhances predictive accuracy and stability,and maintains low latency under high concurrency.This work provides a practical,reusable,and scalable solution for intelligent model lifecycle management,with broad applicability to complex systems such as smart grids.展开更多
针对基于You Only Look Once v2算法的目标检测存在精度低及稳健性差的问题,提出一种车辆目标实时检测的You Only Look Once v2优化算法;该算法以You Only Look Once v2算法为基础,通过增加网络深度,增强特征提取能力,同时,通过添加残...针对基于You Only Look Once v2算法的目标检测存在精度低及稳健性差的问题,提出一种车辆目标实时检测的You Only Look Once v2优化算法;该算法以You Only Look Once v2算法为基础,通过增加网络深度,增强特征提取能力,同时,通过添加残差模块,解决网络深度增加带来的梯度消失或弥散问题;该方法将网络结构中低层特征与高层特征进行融合,提升对小目标车辆的检测精度。结果表明,通过在KITTI数据集上进行测试,优化后的算法在检测速度不变的情况下,提高了车辆目标检测精度,平均精度达到0.94,同时提升了小目标检测的准确性。展开更多
To avoid suffering gouge and transient overshooting in high speed cutting machining, a novel parametefized curve interpolator model with velocity look-ahead algorithm is proposed. Based on a prearrangement step interp...To avoid suffering gouge and transient overshooting in high speed cutting machining, a novel parametefized curve interpolator model with velocity look-ahead algorithm is proposed. Based on a prearrangement step interpolation algorithm for parameterized curves and considering high curvature points, parameterized curve tool path is divided into acceleration segments and deceleration segments by look-ahead algorithm. Under condition of characteristics of acceleration and deceleration stored in control system, deceleration before high curvature points and acceleration after high curvature points are realized in real-time in high speed cutting machining. Based on new parameterized curve interpolator model with velocity look-ahead algorithm, a real cubic spline is machined simulativly. The simulation results show that velocity look-ahead algorithm improves velocity changing more smoothly.展开更多
Global look-up table strategy proposed recently has been proven to be an efficient method to accelerate the interpolation, which is the most time-consuming part in the iterative sub-pixel digital image correlation （...Global look-up table strategy proposed recently has been proven to be an efficient method to accelerate the interpolation, which is the most time-consuming part in the iterative sub-pixel digital image correlation （DIC） algorithms. In this paper, a global look-up table strategy with cubic B-spline interpolation is developed for the DIC method based on the inverse compositional Gauss-Newton （IC-GN） algorithm. The performance of this strategy, including accuracy, precision, and computation efficiency, is evaluated through a theoretical and experimental study, using the one with widely employed bicubic interpolation as a benchmark. The global look-up table strategy with cubic B-spline interpolation improves significantly the accuracy of the IC-GN algorithm-based DIC method compared with the one using the bicubic interpolation, at a trivial price of computation efficiency.展开更多
The new version of“Dreamlike Lijiang”is now on stage with a brand-new appearance in Guilin,Guangxi,China. The show has been performing successfully over four years so far! As a leading role in the local show market,...The new version of“Dreamlike Lijiang”is now on stage with a brand-new appearance in Guilin,Guangxi,China. The show has been performing successfully over four years so far! As a leading role in the local show market,“Dreamlike Lijiang”has become a successful quintessence during the last four years,with its popularity and the applause from the audiences.As a famous brand in show industry,“展开更多
针对交通路口图像复杂,小目标难测且目标之间易遮挡以及天气和光照变化引发的颜色失真、噪声和模糊等问题,提出一种基于YOLOv9(You Only Look Once version 9)的交通路口图像的多目标检测算法ITD-YOLOv9(Intersection Target Detection-...针对交通路口图像复杂,小目标难测且目标之间易遮挡以及天气和光照变化引发的颜色失真、噪声和模糊等问题,提出一种基于YOLOv9(You Only Look Once version 9)的交通路口图像的多目标检测算法ITD-YOLOv9(Intersection Target Detection-YOLOv9)。首先,设计CoT-CAFRNet(Chain-of-Thought prompted Content-Aware Feature Reassembly Network)图像增强网络,以提升图像质量,并优化输入特征;其次,加入通道自适应特征融合(iCAFF)模块,以增强小目标及重叠遮挡目标的提取能力;再次,提出特征融合金字塔结构BiHS-FPN(Bi-directional High-level Screening Feature Pyramid Network),以增强多尺度特征的融合能力;最后,设计IF-MPDIoU(Inner-Focaler-Minimum Point Distance based Intersection over Union)损失函数,以通过调整变量因子,聚焦关键样本,并增强泛化能力。实验结果表明,在自制数据集和SODA10M数据集上,ITD-YOLOv9算法的检测精度分别为83.8%和56.3%,检测帧率分别为64.8 frame/s和57.4 frame/s。与YOLOv9算法相比,ITD-YOLOv9算法的检测精度分别提升了3.9和2.7个百分点。可见,所提算法有效实现了交通路口的多目标检测。展开更多
针对目前传统安检方法对于车辆底盘表面藏匿的违禁物品的检测效率低、漏检率高、便携性差等不足,设计了一个基于云端的移动式智能车底藏匿物检测系统,通过机器人、网络通信、图像处理及目标检测等技术,实现藏匿物智能化检测。基于SIFT(S...针对目前传统安检方法对于车辆底盘表面藏匿的违禁物品的检测效率低、漏检率高、便携性差等不足,设计了一个基于云端的移动式智能车底藏匿物检测系统,通过机器人、网络通信、图像处理及目标检测等技术,实现藏匿物智能化检测。基于SIFT(Scale-Invariant Feature Transform)算法提取图像特征信息并获取车底局部全景图像,使用YOLOv5(You Only Look Once version 5)深度神经网络模型检测4种车底藏匿物,搭建云数据库存储车辆信息,轮式机器人、上位机、云数据库之间通过TCP/IP(Transmission Control Protocol/Internet Protocol)协议进行通信。经测试,该系统能在特定场景下完成车底藏匿物检测,图像拼接成功率达81.7%,目标检测准确率达83.7%,在车底安检领域具有一定的实用价值。展开更多
针对传统课堂质量评价手段主要依靠人工观察,存在效率低和精度差等问题,提出了一种基于改进YOLOv5s(You Only Look Once version 5 small)的轻量化课堂评价模型。通过采用该模型和层次分析法建立完善的课堂评价体系。该模型在颈部网络...针对传统课堂质量评价手段主要依靠人工观察,存在效率低和精度差等问题,提出了一种基于改进YOLOv5s(You Only Look Once version 5 small)的轻量化课堂评价模型。通过采用该模型和层次分析法建立完善的课堂评价体系。该模型在颈部网络中融入CBAM(Convolutional Block Attention Module)注意力机制,提高了模型的识别精度;通过在骨干网络中融合Ghost模块,显著降低了模型的复杂度;通过采用Focal Loss损失函数,有效地缓解了类别不平衡的问题。实验结果表明,与YOLOv5s模型相比,改进后的模型平均精度提升了7.3%,参数量减少了42.0%,计算量减少33.1%,检测速度提升了4%。最后结合层次分析法和熵权法建立课堂质量评价体系,动态显示当前课堂质量的评分,可满足实际课堂需求。展开更多
为推动输电线路智能化巡检模式,本文针对人机协同巡检模式下的图像差异大及干扰因素多等问题,提出一种轻量化改进型YOLOv8(you only look once version 8)的多类别绝缘子缺陷检测算法。首先在特征提取网络中融合可变形大核注意力的同时...为推动输电线路智能化巡检模式,本文针对人机协同巡检模式下的图像差异大及干扰因素多等问题,提出一种轻量化改进型YOLOv8(you only look once version 8)的多类别绝缘子缺陷检测算法。首先在特征提取网络中融合可变形大核注意力的同时进行轻量化,提升网络对不同目标轮廓与尺寸的适用性;其次引入渐进的特征融合策略以改善不同层次特征间的语义差距,提高网络的检测精度;并设计轻量化非对称检测头,进一步减少参数冗余;最后改进边框损失函数有效降低由密集遮挡造成的漏检和误检数量。实验结果表明,本文算法相较于原算法检测精度提升了7.7%,参数量和计算量分别减少了26.4%和30.2%,并在密集、遮挡、多类别目标缺陷检测中的评价指标均领先于当前主流的几类目标检测算法,显著提高了复杂环境下的多类别绝缘子缺陷检测,实现了检测精度和速度的双重提升。展开更多
针对小尺度目标在检测时精确率低且易出现漏检和误检等问题,提出一种改进的YOLOv3(You Only Look Once version 3)小目标检测算法。在网络结构方面,为提高基础网络的特征提取能力,使用DenseNet-121密集连接网络替换原Darknet-53网络作...针对小尺度目标在检测时精确率低且易出现漏检和误检等问题,提出一种改进的YOLOv3(You Only Look Once version 3)小目标检测算法。在网络结构方面,为提高基础网络的特征提取能力,使用DenseNet-121密集连接网络替换原Darknet-53网络作为其基础网络,同时修改卷积核尺寸,进一步降低特征图信息的损耗,并且为增强检测模型对小尺度目标的鲁棒性,额外增加第4个尺寸为104×104像素的特征检测层;在对特征图融合操作方面,使用双线性插值法进行上采样操作代替原最近邻插值法上采样操作,解决大部分检测算法中存在的特征严重损失问题;在损失函数方面,使用广义交并比(GIoU)代替交并比(IoU)来计算边界框的损失值,同时引入Focal Loss焦点损失函数作为边界框的置信度损失函数。实验结果表明,改进算法在VisDrone2019数据集上的均值平均精度(mAP)为63.3%,较原始YOLOv3检测模型提高了13.2百分点,并且在GTX 1080 Ti设备上可实现52帧/s的检测速度,对小目标有着较好的检测性能。展开更多
Unmanned Aerial Vehicles(UAVs)are increasingly employed in traffic surveillance,urban planning,and infrastructure monitoring due to their cost-effectiveness,flexibility,and high-resolution imaging.However,vehicle dete...Unmanned Aerial Vehicles(UAVs)are increasingly employed in traffic surveillance,urban planning,and infrastructure monitoring due to their cost-effectiveness,flexibility,and high-resolution imaging.However,vehicle detection and classification in aerial imagery remain challenging due to scale variations from fluctuating UAV altitudes,frequent occlusions in dense traffic,and environmental noise,such as shadows and lighting inconsistencies.Traditional methods,including sliding-window searches and shallow learning techniques,struggle with computational inefficiency and robustness under dynamic conditions.To address these limitations,this study proposes a six-stage hierarchical framework integrating radiometric calibration,deep learning,and classical feature engineering.The workflow begins with radiometric calibration to normalize pixel intensities and mitigate sensor noise,followed by Conditional Random Field(CRF)segmentation to isolate vehicles.YOLOv9,equipped with a bi-directional feature pyramid network(BiFPN),ensures precise multi-scale object detection.Hybrid feature extraction employs Maximally Stable Extremal Regions(MSER)for stable contour detection,Binary Robust Independent Elementary Features(BRIEF)for texture encoding,and Affine-SIFT(ASIFT)for viewpoint invariance.Quadratic Discriminant Analysis(QDA)enhances feature discrimination,while a Probabilistic Neural Network(PNN)performs Bayesian probability-based classification.Tested on the Roundabout Aerial Imagery(15,474 images,985K instances)and AU-AIR(32,823 instances,7 classes)datasets,the model achieves state-of-the-art accuracy of 95.54%and 94.14%,respectively.Its superior performance in detecting small-scale vehicles and resolving occlusions highlights its potential for intelligent traffic systems.Future work will extend testing to nighttime and adverse weather conditions while optimizing real-time UAV inference.展开更多
交通视频图像目标提取精度低和提取效率低,为此,提出一种基于物联网技术的智能化交通视频图像目标提取方法。采用物联网技术采集交通视频图像,结合对称性检测和灰度验证,识别视频图像前景区域的种子点,根据方向相似性和灰度值连接前景...交通视频图像目标提取精度低和提取效率低,为此,提出一种基于物联网技术的智能化交通视频图像目标提取方法。采用物联网技术采集交通视频图像,结合对称性检测和灰度验证,识别视频图像前景区域的种子点,根据方向相似性和灰度值连接前景种子点,获得视频图像的前景区域,采用模板去噪方法消除前景区域中的噪声;采用YOLOv3(you only look once version 3)模型提取交通视频图像中的目标,引入卡尔曼滤波器跟踪目标,并通过匈牙利匹配提高目标提取精度。实验结果表明,所提方法具有良好的图像处理能力、目标提取精度高、提取效率高。展开更多
基金funded by Anhui NARI ZT Electric Co.,Ltd.,entitled“Research on the Shared Operation and Maintenance Service Model for Metering Equipment and Platform Development for the Modern Industrial Chain”(Grant No.524636250005).
文摘With the rapid adoption of artificial intelligence(AI)in domains such as power,transportation,and finance,the number of machine learning and deep learning models has grown exponentially.However,challenges such as delayed retraining,inconsistent version management,insufficient drift monitoring,and limited data security still hinder efficient and reliable model operations.To address these issues,this paper proposes the Intelligent Model Lifecycle Management Algorithm(IMLMA).The algorithm employs a dual-trigger mechanism based on both data volume thresholds and time intervals to automate retraining,and applies Bayesian optimization for adaptive hyperparameter tuning to improve performance.A multi-metric replacement strategy,incorporating MSE,MAE,and R2,ensures that new models replace existing ones only when performance improvements are guaranteed.A versioning and traceability database supports comparison and visualization,while real-time monitoring with stability analysis enables early warnings of latency and drift.Finally,hash-based integrity checks secure both model files and datasets.Experimental validation in a power metering operation scenario demonstrates that IMLMA reduces model update delays,enhances predictive accuracy and stability,and maintains low latency under high concurrency.This work provides a practical,reusable,and scalable solution for intelligent model lifecycle management,with broad applicability to complex systems such as smart grids.
文摘针对基于You Only Look Once v2算法的目标检测存在精度低及稳健性差的问题,提出一种车辆目标实时检测的You Only Look Once v2优化算法;该算法以You Only Look Once v2算法为基础,通过增加网络深度,增强特征提取能力,同时,通过添加残差模块,解决网络深度增加带来的梯度消失或弥散问题;该方法将网络结构中低层特征与高层特征进行融合,提升对小目标车辆的检测精度。结果表明,通过在KITTI数据集上进行测试,优化后的算法在检测速度不变的情况下,提高了车辆目标检测精度,平均精度达到0.94,同时提升了小目标检测的准确性。
基金Special Project for Key Mechatronic Equipment of Zhejiang Province,China (No.2006Cl1067)Science & Technology Project of Zhejiang Province,China (No. 2005E10049)
文摘To avoid suffering gouge and transient overshooting in high speed cutting machining, a novel parametefized curve interpolator model with velocity look-ahead algorithm is proposed. Based on a prearrangement step interpolation algorithm for parameterized curves and considering high curvature points, parameterized curve tool path is divided into acceleration segments and deceleration segments by look-ahead algorithm. Under condition of characteristics of acceleration and deceleration stored in control system, deceleration before high curvature points and acceleration after high curvature points are realized in real-time in high speed cutting machining. Based on new parameterized curve interpolator model with velocity look-ahead algorithm, a real cubic spline is machined simulativly. The simulation results show that velocity look-ahead algorithm improves velocity changing more smoothly.
基金financially supported by the National Natural Science Foundation of China(11202081,11272124,and 11472109)the State Key Lab of Subtropical Building Science,South China University of Technology(2014ZC17)
文摘Global look-up table strategy proposed recently has been proven to be an efficient method to accelerate the interpolation, which is the most time-consuming part in the iterative sub-pixel digital image correlation （DIC） algorithms. In this paper, a global look-up table strategy with cubic B-spline interpolation is developed for the DIC method based on the inverse compositional Gauss-Newton （IC-GN） algorithm. The performance of this strategy, including accuracy, precision, and computation efficiency, is evaluated through a theoretical and experimental study, using the one with widely employed bicubic interpolation as a benchmark. The global look-up table strategy with cubic B-spline interpolation improves significantly the accuracy of the IC-GN algorithm-based DIC method compared with the one using the bicubic interpolation, at a trivial price of computation efficiency.
文摘The new version of“Dreamlike Lijiang”is now on stage with a brand-new appearance in Guilin,Guangxi,China. The show has been performing successfully over four years so far! As a leading role in the local show market,“Dreamlike Lijiang”has become a successful quintessence during the last four years,with its popularity and the applause from the audiences.As a famous brand in show industry,“
文摘针对交通路口图像复杂,小目标难测且目标之间易遮挡以及天气和光照变化引发的颜色失真、噪声和模糊等问题,提出一种基于YOLOv9(You Only Look Once version 9)的交通路口图像的多目标检测算法ITD-YOLOv9(Intersection Target Detection-YOLOv9)。首先,设计CoT-CAFRNet(Chain-of-Thought prompted Content-Aware Feature Reassembly Network)图像增强网络,以提升图像质量,并优化输入特征;其次,加入通道自适应特征融合(iCAFF)模块,以增强小目标及重叠遮挡目标的提取能力;再次,提出特征融合金字塔结构BiHS-FPN(Bi-directional High-level Screening Feature Pyramid Network),以增强多尺度特征的融合能力;最后,设计IF-MPDIoU(Inner-Focaler-Minimum Point Distance based Intersection over Union)损失函数,以通过调整变量因子,聚焦关键样本,并增强泛化能力。实验结果表明,在自制数据集和SODA10M数据集上,ITD-YOLOv9算法的检测精度分别为83.8%和56.3%,检测帧率分别为64.8 frame/s和57.4 frame/s。与YOLOv9算法相比,ITD-YOLOv9算法的检测精度分别提升了3.9和2.7个百分点。可见,所提算法有效实现了交通路口的多目标检测。
文摘针对目前传统安检方法对于车辆底盘表面藏匿的违禁物品的检测效率低、漏检率高、便携性差等不足,设计了一个基于云端的移动式智能车底藏匿物检测系统,通过机器人、网络通信、图像处理及目标检测等技术,实现藏匿物智能化检测。基于SIFT(Scale-Invariant Feature Transform)算法提取图像特征信息并获取车底局部全景图像,使用YOLOv5(You Only Look Once version 5)深度神经网络模型检测4种车底藏匿物,搭建云数据库存储车辆信息,轮式机器人、上位机、云数据库之间通过TCP/IP(Transmission Control Protocol/Internet Protocol)协议进行通信。经测试,该系统能在特定场景下完成车底藏匿物检测,图像拼接成功率达81.7%,目标检测准确率达83.7%,在车底安检领域具有一定的实用价值。
文摘针对传统课堂质量评价手段主要依靠人工观察,存在效率低和精度差等问题,提出了一种基于改进YOLOv5s(You Only Look Once version 5 small)的轻量化课堂评价模型。通过采用该模型和层次分析法建立完善的课堂评价体系。该模型在颈部网络中融入CBAM(Convolutional Block Attention Module)注意力机制,提高了模型的识别精度;通过在骨干网络中融合Ghost模块,显著降低了模型的复杂度;通过采用Focal Loss损失函数,有效地缓解了类别不平衡的问题。实验结果表明,与YOLOv5s模型相比,改进后的模型平均精度提升了7.3%,参数量减少了42.0%,计算量减少33.1%,检测速度提升了4%。最后结合层次分析法和熵权法建立课堂质量评价体系,动态显示当前课堂质量的评分,可满足实际课堂需求。
文摘为推动输电线路智能化巡检模式,本文针对人机协同巡检模式下的图像差异大及干扰因素多等问题,提出一种轻量化改进型YOLOv8(you only look once version 8)的多类别绝缘子缺陷检测算法。首先在特征提取网络中融合可变形大核注意力的同时进行轻量化,提升网络对不同目标轮廓与尺寸的适用性;其次引入渐进的特征融合策略以改善不同层次特征间的语义差距,提高网络的检测精度;并设计轻量化非对称检测头,进一步减少参数冗余;最后改进边框损失函数有效降低由密集遮挡造成的漏检和误检数量。实验结果表明,本文算法相较于原算法检测精度提升了7.7%,参数量和计算量分别减少了26.4%和30.2%,并在密集、遮挡、多类别目标缺陷检测中的评价指标均领先于当前主流的几类目标检测算法,显著提高了复杂环境下的多类别绝缘子缺陷检测,实现了检测精度和速度的双重提升。
文摘前视合成孔径雷达(Synthetic Aperture Radar,SAR)在舰船成像方面展现出了巨大潜力,特别是在SAR导引头的应用上,弹载雷达通常在末制导阶段要求雷达正对着舰船运动,以实现精准打击。针对前视条件下传统SAR成像方法所面临的挑战,本文提出了一种基于极坐标格式算法(Polar Format Algorithm,PFA)的前视SAR舰船目标立面成像方法。该方法巧妙利用了舰船的三维特性,即使雷达工作在前视模式下,虽然在方位向上无法有效分辨目标,但在俯仰向上仍然存在多普勒频率的变化,因此可以在距离向和俯仰向上实现对舰船的二维高分辨率成像。此外,这种成像方法能够提供更为直观的舰船立面图像,这对于识别舰船类型、判断潜在威胁以及对其进行精准打击具有重大意义。最后,通过仿真实验对该方法进行了验证,利用PFA获得了清晰的舰船立面图像。
文摘针对小尺度目标在检测时精确率低且易出现漏检和误检等问题,提出一种改进的YOLOv3(You Only Look Once version 3)小目标检测算法。在网络结构方面,为提高基础网络的特征提取能力,使用DenseNet-121密集连接网络替换原Darknet-53网络作为其基础网络,同时修改卷积核尺寸,进一步降低特征图信息的损耗,并且为增强检测模型对小尺度目标的鲁棒性,额外增加第4个尺寸为104×104像素的特征检测层;在对特征图融合操作方面,使用双线性插值法进行上采样操作代替原最近邻插值法上采样操作,解决大部分检测算法中存在的特征严重损失问题;在损失函数方面,使用广义交并比(GIoU)代替交并比(IoU)来计算边界框的损失值,同时引入Focal Loss焦点损失函数作为边界框的置信度损失函数。实验结果表明,改进算法在VisDrone2019数据集上的均值平均精度(mAP)为63.3%,较原始YOLOv3检测模型提高了13.2百分点,并且在GTX 1080 Ti设备上可实现52帧/s的检测速度,对小目标有着较好的检测性能。
基金supported through Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R508)Princess Nourah bint Abdulrahman University,Riyadh,Saudi ArabiaThe research team thanks the Deanship of Graduate Studies and Scientific Research at Najran University for supporting the research project through the Nama’a program,with the project code NU/GP/SERC/13/18-5.
文摘Unmanned Aerial Vehicles(UAVs)are increasingly employed in traffic surveillance,urban planning,and infrastructure monitoring due to their cost-effectiveness,flexibility,and high-resolution imaging.However,vehicle detection and classification in aerial imagery remain challenging due to scale variations from fluctuating UAV altitudes,frequent occlusions in dense traffic,and environmental noise,such as shadows and lighting inconsistencies.Traditional methods,including sliding-window searches and shallow learning techniques,struggle with computational inefficiency and robustness under dynamic conditions.To address these limitations,this study proposes a six-stage hierarchical framework integrating radiometric calibration,deep learning,and classical feature engineering.The workflow begins with radiometric calibration to normalize pixel intensities and mitigate sensor noise,followed by Conditional Random Field(CRF)segmentation to isolate vehicles.YOLOv9,equipped with a bi-directional feature pyramid network(BiFPN),ensures precise multi-scale object detection.Hybrid feature extraction employs Maximally Stable Extremal Regions(MSER)for stable contour detection,Binary Robust Independent Elementary Features(BRIEF)for texture encoding,and Affine-SIFT(ASIFT)for viewpoint invariance.Quadratic Discriminant Analysis(QDA)enhances feature discrimination,while a Probabilistic Neural Network(PNN)performs Bayesian probability-based classification.Tested on the Roundabout Aerial Imagery(15,474 images,985K instances)and AU-AIR(32,823 instances,7 classes)datasets,the model achieves state-of-the-art accuracy of 95.54%and 94.14%,respectively.Its superior performance in detecting small-scale vehicles and resolving occlusions highlights its potential for intelligent traffic systems.Future work will extend testing to nighttime and adverse weather conditions while optimizing real-time UAV inference.
文摘交通视频图像目标提取精度低和提取效率低,为此,提出一种基于物联网技术的智能化交通视频图像目标提取方法。采用物联网技术采集交通视频图像,结合对称性检测和灰度验证,识别视频图像前景区域的种子点,根据方向相似性和灰度值连接前景种子点,获得视频图像的前景区域,采用模板去噪方法消除前景区域中的噪声;采用YOLOv3(you only look once version 3)模型提取交通视频图像中的目标,引入卡尔曼滤波器跟踪目标,并通过匈牙利匹配提高目标提取精度。实验结果表明,所提方法具有良好的图像处理能力、目标提取精度高、提取效率高。
