针对传统跳频网台分选技术在低信噪比条件下检测效果不佳且实时性差的问题,本文提出一种基于YOLOv8(You Only Look Once version 8)的跳频信号分选算法.首先,对接收到的混叠信号进行短时傅里叶变换生成灰度时频图作为YOLOv8网络模型的输...针对传统跳频网台分选技术在低信噪比条件下检测效果不佳且实时性差的问题,本文提出一种基于YOLOv8(You Only Look Once version 8)的跳频信号分选算法.首先,对接收到的混叠信号进行短时傅里叶变换生成灰度时频图作为YOLOv8网络模型的输入.其次,针对混叠信号中扫频、定频信号以及跳频信号之间发生频率碰撞对检测精度的影响,在C2f层中引入可变形卷积核(Deformable Convolutional Net-works v2,DCNv2)提高网络特征提取的泛化能力.再次,在Backbone层中加入SimAM注意力机制,解决低信噪比下背景噪声易与跳频信号混淆影响检测精度的问题.最后,将Detect检测头的卷积核替换为局部卷积核(Partial Convolution,PConv),在mAP@0.5精度损失不超过0.37%的情况下使网络计算复杂度降低32.18%,提高网络模型的推理速度.实验结果表明,本文所提算法在信噪比为-5 dB时分选率达到97.68%,且模型收敛快,鲁棒性强.展开更多
Accurate vehicle detection is essential for autonomous driving,traffic monitoring,and intelligent transportation systems.This paper presents an enhanced YOLOv8n model that incorporates the Ghost Module,Convolutional B...Accurate vehicle detection is essential for autonomous driving,traffic monitoring,and intelligent transportation systems.This paper presents an enhanced YOLOv8n model that incorporates the Ghost Module,Convolutional Block Attention Module(CBAM),and Deformable Convolutional Networks v2(DCNv2).The Ghost Module streamlines feature generation to reduce redundancy,CBAM applies channel and spatial attention to improve feature focus,and DCNv2 enables adaptability to geometric variations in vehicle shapes.These components work together to improve both accuracy and computational efficiency.Evaluated on the KITTI dataset,the proposed model achieves 95.4%mAP@0.5—an 8.97% gain over standard YOLOv8n—along with 96.2% precision,93.7% recall,and a 94.93%F1-score.Comparative analysis with seven state-of-the-art detectors demonstrates consistent superiority in key performance metrics.An ablation study is also conducted to quantify the individual and combined contributions of GhostModule,CBAM,and DCNv2,highlighting their effectiveness in improving detection performance.By addressing feature redundancy,attention refinement,and spatial adaptability,the proposed model offers a robust and scalable solution for vehicle detection across diverse traffic scenarios.展开更多
针对目前绝缘子缺陷目标检测算法中存在的误检、漏检和检测精度低等问题,提出一种改进的YOLOv8绝缘子及其自爆缺陷目标检测算法。在YOLOv8模型原有的结构上添加了一个小目标检测头,使得网络模型对小目标物体更加专注。使用可变形卷积(De...针对目前绝缘子缺陷目标检测算法中存在的误检、漏检和检测精度低等问题,提出一种改进的YOLOv8绝缘子及其自爆缺陷目标检测算法。在YOLOv8模型原有的结构上添加了一个小目标检测头,使得网络模型对小目标物体更加专注。使用可变形卷积(Deformable ConvNets v2,DCNv2)替换了C2f模块中的普通卷积,使得模型可以更好地捕捉和感知被检测目标的特征。在主干网络中引入反向残差注意力模块(Inverted Residual Mobile Block,iRMB),使模型能够捕捉局部特征和复杂空间之间的关系,从而更加专注于检测目标的特征信息。使用Wise Intersection over Union(WIoU)作为损失函数,使得模型在训练时能够取得更好的效果,从而提高检测精度。在输电线路绝缘子数据集上,该算法的平均检测精度(mean Average Precision,mAP)提高至98.0%,相比于原始算法提高了2.9%,精确率和召回率分别提高至92.8%和94.8%。改进后的算法相比原始算法,特别是针对小目标缺陷的检测有明显提升,证明了算法改进后的可行性。展开更多
文摘针对传统跳频网台分选技术在低信噪比条件下检测效果不佳且实时性差的问题,本文提出一种基于YOLOv8(You Only Look Once version 8)的跳频信号分选算法.首先,对接收到的混叠信号进行短时傅里叶变换生成灰度时频图作为YOLOv8网络模型的输入.其次,针对混叠信号中扫频、定频信号以及跳频信号之间发生频率碰撞对检测精度的影响,在C2f层中引入可变形卷积核(Deformable Convolutional Net-works v2,DCNv2)提高网络特征提取的泛化能力.再次,在Backbone层中加入SimAM注意力机制,解决低信噪比下背景噪声易与跳频信号混淆影响检测精度的问题.最后,将Detect检测头的卷积核替换为局部卷积核(Partial Convolution,PConv),在mAP@0.5精度损失不超过0.37%的情况下使网络计算复杂度降低32.18%,提高网络模型的推理速度.实验结果表明,本文所提算法在信噪比为-5 dB时分选率达到97.68%,且模型收敛快,鲁棒性强.
文摘Accurate vehicle detection is essential for autonomous driving,traffic monitoring,and intelligent transportation systems.This paper presents an enhanced YOLOv8n model that incorporates the Ghost Module,Convolutional Block Attention Module(CBAM),and Deformable Convolutional Networks v2(DCNv2).The Ghost Module streamlines feature generation to reduce redundancy,CBAM applies channel and spatial attention to improve feature focus,and DCNv2 enables adaptability to geometric variations in vehicle shapes.These components work together to improve both accuracy and computational efficiency.Evaluated on the KITTI dataset,the proposed model achieves 95.4%mAP@0.5—an 8.97% gain over standard YOLOv8n—along with 96.2% precision,93.7% recall,and a 94.93%F1-score.Comparative analysis with seven state-of-the-art detectors demonstrates consistent superiority in key performance metrics.An ablation study is also conducted to quantify the individual and combined contributions of GhostModule,CBAM,and DCNv2,highlighting their effectiveness in improving detection performance.By addressing feature redundancy,attention refinement,and spatial adaptability,the proposed model offers a robust and scalable solution for vehicle detection across diverse traffic scenarios.
文摘针对目前绝缘子缺陷目标检测算法中存在的误检、漏检和检测精度低等问题,提出一种改进的YOLOv8绝缘子及其自爆缺陷目标检测算法。在YOLOv8模型原有的结构上添加了一个小目标检测头,使得网络模型对小目标物体更加专注。使用可变形卷积(Deformable ConvNets v2,DCNv2)替换了C2f模块中的普通卷积,使得模型可以更好地捕捉和感知被检测目标的特征。在主干网络中引入反向残差注意力模块(Inverted Residual Mobile Block,iRMB),使模型能够捕捉局部特征和复杂空间之间的关系,从而更加专注于检测目标的特征信息。使用Wise Intersection over Union(WIoU)作为损失函数,使得模型在训练时能够取得更好的效果,从而提高检测精度。在输电线路绝缘子数据集上,该算法的平均检测精度(mean Average Precision,mAP)提高至98.0%,相比于原始算法提高了2.9%,精确率和召回率分别提高至92.8%和94.8%。改进后的算法相比原始算法,特别是针对小目标缺陷的检测有明显提升,证明了算法改进后的可行性。
