针对光照不均匀和水表表盘雾化的指针式水表在读数检测时出现漏检、误检等问题,提出一种基于改进YOLOv5s的指针式水表读数检测方法。首先,采用Mosaic、Mixup等数据增强方法,提高模型的泛化能力;其次,引入加权双向特征金字塔网络(bilater...针对光照不均匀和水表表盘雾化的指针式水表在读数检测时出现漏检、误检等问题,提出一种基于改进YOLOv5s的指针式水表读数检测方法。首先,采用Mosaic、Mixup等数据增强方法,提高模型的泛化能力;其次,引入加权双向特征金字塔网络(bilateral feature pyramid network, BiFPN)实现更高层次的特征融合使得水表图像的深层特征图和浅层特征图充分融合,提高网络的表达能力;然后,嵌入卷积注意力机制(convolutional block attention module, CBAM),在通道和空间双重维度上强化指针式水表子表盘示数特征;最后将完全交并比损失函数(complete intersection over union loss, CIoU-Loss)替换为SIoU_Loss(scylla intersection over union loss),提升边界框的回归精度。改进算法的mAP@0.5达到97.8%,比YOLOv5s原始网络提升了3.2%。实验结果表明:该算法能有效提高指针式水表的读数检测精度。展开更多
在多数目标检测公开数据集中,小目标检测是一个研究热点。针对检测器在多尺寸检测场景下对小目标检测精度不足的问题,文中提出基于YOLOv5s(You Only Look Once version 5s)的小目标检测改进模型。模型在检测器的特征提取网络中加入卷积...在多数目标检测公开数据集中,小目标检测是一个研究热点。针对检测器在多尺寸检测场景下对小目标检测精度不足的问题,文中提出基于YOLOv5s(You Only Look Once version 5s)的小目标检测改进模型。模型在检测器的特征提取网络中加入卷积自注意力聚合残差块来提升特征提取能力,同时从浅层网络中引入新的特征图增强小目标的特征信息,改进特征融合网络结构,以便充分利用新引入的浅层特征。引入SIOU Loss替换原GIOU Loss矩形框损失函数,提升检测精度和训练速度。实验结果表明,在PASCAL VOC的2007和2012数据集上,改进模型检测精度比YOLOv5s提高0.012,小目标检测精度比YOLOv5s提高0.023;在MS COCO数据集上改进模型比YOLOv5s的检测精度提高0.001,小目标检测精度比YOLOv5s提高0.009。展开更多
The rapid pace of urban development has resulted in the widespread presence of construction equipment andincreasingly complex conditions in transmission corridors. These conditions pose a serious threat to the safeope...The rapid pace of urban development has resulted in the widespread presence of construction equipment andincreasingly complex conditions in transmission corridors. These conditions pose a serious threat to the safeoperation of the power grid.Machine vision technology, particularly object recognition technology, has beenwidelyemployed to identify foreign objects in transmission line images. Despite its wide application, the technique faceslimitations due to the complex environmental background and other auxiliary factors. To address these challenges,this study introduces an improved YOLOv8n. The traditional stepwise convolution and pooling layers are replacedwith a spatial-depth convolution (SPD-Conv) module, aiming to improve the algorithm’s efficacy in recognizinglow-resolution and small-size objects. The algorithm’s feature extraction network is improved by using a LargeSelective Kernel (LSK) attention mechanism, which enhances the ability to extract relevant features. Additionally,the SIoU Loss function is used instead of the Complete Intersection over Union (CIoU) Loss to facilitate fasterconvergence of the algorithm. Through experimental verification, the improved YOLOv8n model achieves adetection accuracy of 88.8% on the test set. The recognition accuracy of cranes is improved by 2.9%, which isa significant enhancement compared to the unimproved algorithm. This improvement effectively enhances theaccuracy of recognizing foreign objects on transmission lines and proves the effectiveness of the new algorithm.展开更多
文摘针对光照不均匀和水表表盘雾化的指针式水表在读数检测时出现漏检、误检等问题,提出一种基于改进YOLOv5s的指针式水表读数检测方法。首先,采用Mosaic、Mixup等数据增强方法,提高模型的泛化能力;其次,引入加权双向特征金字塔网络(bilateral feature pyramid network, BiFPN)实现更高层次的特征融合使得水表图像的深层特征图和浅层特征图充分融合,提高网络的表达能力;然后,嵌入卷积注意力机制(convolutional block attention module, CBAM),在通道和空间双重维度上强化指针式水表子表盘示数特征;最后将完全交并比损失函数(complete intersection over union loss, CIoU-Loss)替换为SIoU_Loss(scylla intersection over union loss),提升边界框的回归精度。改进算法的mAP@0.5达到97.8%,比YOLOv5s原始网络提升了3.2%。实验结果表明:该算法能有效提高指针式水表的读数检测精度。
文摘在多数目标检测公开数据集中,小目标检测是一个研究热点。针对检测器在多尺寸检测场景下对小目标检测精度不足的问题,文中提出基于YOLOv5s(You Only Look Once version 5s)的小目标检测改进模型。模型在检测器的特征提取网络中加入卷积自注意力聚合残差块来提升特征提取能力,同时从浅层网络中引入新的特征图增强小目标的特征信息,改进特征融合网络结构,以便充分利用新引入的浅层特征。引入SIOU Loss替换原GIOU Loss矩形框损失函数,提升检测精度和训练速度。实验结果表明,在PASCAL VOC的2007和2012数据集上,改进模型检测精度比YOLOv5s提高0.012,小目标检测精度比YOLOv5s提高0.023;在MS COCO数据集上改进模型比YOLOv5s的检测精度提高0.001,小目标检测精度比YOLOv5s提高0.009。
基金the Natural Science Foundation of Shandong Province(ZR2021QE289)State Key Laboratory of Electrical Insulation and Power Equipment(EIPE22201).
文摘The rapid pace of urban development has resulted in the widespread presence of construction equipment andincreasingly complex conditions in transmission corridors. These conditions pose a serious threat to the safeoperation of the power grid.Machine vision technology, particularly object recognition technology, has beenwidelyemployed to identify foreign objects in transmission line images. Despite its wide application, the technique faceslimitations due to the complex environmental background and other auxiliary factors. To address these challenges,this study introduces an improved YOLOv8n. The traditional stepwise convolution and pooling layers are replacedwith a spatial-depth convolution (SPD-Conv) module, aiming to improve the algorithm’s efficacy in recognizinglow-resolution and small-size objects. The algorithm’s feature extraction network is improved by using a LargeSelective Kernel (LSK) attention mechanism, which enhances the ability to extract relevant features. Additionally,the SIoU Loss function is used instead of the Complete Intersection over Union (CIoU) Loss to facilitate fasterconvergence of the algorithm. Through experimental verification, the improved YOLOv8n model achieves adetection accuracy of 88.8% on the test set. The recognition accuracy of cranes is improved by 2.9%, which isa significant enhancement compared to the unimproved algorithm. This improvement effectively enhances theaccuracy of recognizing foreign objects on transmission lines and proves the effectiveness of the new algorithm.