针对传统目测法检测贴片二极管表面缺陷效率低下和基于手工特征的目标检测算法模型较浅,以及语义性不高等问题,提出了改进YOLO-V4的贴片二极管表面缺陷检测方法。首先考虑到随着网络加深使梯度消失,以及减少网络中的特征冗余和参数量的...针对传统目测法检测贴片二极管表面缺陷效率低下和基于手工特征的目标检测算法模型较浅,以及语义性不高等问题,提出了改进YOLO-V4的贴片二极管表面缺陷检测方法。首先考虑到随着网络加深使梯度消失,以及减少网络中的特征冗余和参数量的情况,CSP1模块采用DenseNet替换原网络中的ResNet;其次,为了实现特征信息的跨维度交互,让网络更加关注重要信息,在CSP1模块后引入了三分支注意力机制模块,同时使用FPN+PANet对特征进行融合;并且用CSP2替换CBL×5模块,降低了网络的运算量,提高了算法检测速度;最后优化了Focal Loss函数,对正负样本添加权重,以解决正负样本不平衡的问题。本文算法相较于YOLO-V4的检测精度(precision,P)、召回率(recall,R)和多分类平均精度(mean average precision,mAP),分别高出2.98%,2.65%,2.92%,表明改进YOLO-V4可以有效检测贴片二极管表面缺陷问题。展开更多
Traditional maize ear harvesters mainly rely on manual identification of fallen maize ears,which cannot realize real-time detection of ear falling.The improved You Only Look Once-V4(YOLO-V4)algorithm is combined with ...Traditional maize ear harvesters mainly rely on manual identification of fallen maize ears,which cannot realize real-time detection of ear falling.The improved You Only Look Once-V4(YOLO-V4)algorithm is combined with the channel pruning algorithm to detect the dropped ears of maize harvesters.K-means clustering algorithm is used to obtain a prior box matching the size of the dropped ears,which improves the Intersection Over Union(IOU).Compare the effect of different activation functions on the accuracy of the YOLO-V4 model,and use the Mish activation function as the activation function of this model.Improve the calculation of the regression positioning loss function,and use the CEIOU loss function to balance the accuracy of each category.Use improved Adam optimization function and multi-stage learning optimization technology to improve the accuracy of the YOLO-V4 model.The channel pruning algorithm is used to compress the model and distillation technology is used in the fine-tuning of the model.The final model size was only 10.77%before compression,and the test set mean Average Precision(mAP)was 93.14%.The detection speed was 112 fps,which can meet the need for real-time detection of maize harvester ears in the field.This study can provide technical reference for the detection of the ear loss rate of intelligent maize harvesters.展开更多
鱼类目标检测对渔业精准养殖、生产自动化、资源调查及鱼行为的研究等具有重要的意义。为了能快速准确地得到鱼类目标的位置和所属类别,提出了一种改进YOLO v4模型的鱼类目标检测方法,在CIoU(Complete Intersection over Union)损失函...鱼类目标检测对渔业精准养殖、生产自动化、资源调查及鱼行为的研究等具有重要的意义。为了能快速准确地得到鱼类目标的位置和所属类别,提出了一种改进YOLO v4模型的鱼类目标检测方法,在CIoU(Complete Intersection over Union)损失函数基础上构建了新的损失项,改进的损失函数使真实框与相交框呈相同宽高比进行回归,同时通过设置多锚点框模式,增强在特定尺寸面积上的检测效果。结果显示:改进YOLO v4模型的mAP(mean Average Precision)比原模型有较大提升,在自建数据集、Fish4Knowledge数据集和NCFM数据集上的mAP分别达到了94.22%、99.52%、92.16%。研究表明,改进YOLO v4模型可以快速准确地检测到鱼的位置和类别,检测速度满足实时的要求,可以为渔业精准养殖等提供参考。展开更多
文摘针对传统目测法检测贴片二极管表面缺陷效率低下和基于手工特征的目标检测算法模型较浅,以及语义性不高等问题,提出了改进YOLO-V4的贴片二极管表面缺陷检测方法。首先考虑到随着网络加深使梯度消失,以及减少网络中的特征冗余和参数量的情况,CSP1模块采用DenseNet替换原网络中的ResNet;其次,为了实现特征信息的跨维度交互,让网络更加关注重要信息,在CSP1模块后引入了三分支注意力机制模块,同时使用FPN+PANet对特征进行融合;并且用CSP2替换CBL×5模块,降低了网络的运算量,提高了算法检测速度;最后优化了Focal Loss函数,对正负样本添加权重,以解决正负样本不平衡的问题。本文算法相较于YOLO-V4的检测精度(precision,P)、召回率(recall,R)和多分类平均精度(mean average precision,mAP),分别高出2.98%,2.65%,2.92%,表明改进YOLO-V4可以有效检测贴片二极管表面缺陷问题。
基金This work was funded and supported by the Shandong Provincial Key Science and Technology Innovation Engineering Project(Grant No.2018CXGC0217)the 13th Five-Year National Key Research and Development Program(Grant No.2018YFD0300606).
文摘Traditional maize ear harvesters mainly rely on manual identification of fallen maize ears,which cannot realize real-time detection of ear falling.The improved You Only Look Once-V4(YOLO-V4)algorithm is combined with the channel pruning algorithm to detect the dropped ears of maize harvesters.K-means clustering algorithm is used to obtain a prior box matching the size of the dropped ears,which improves the Intersection Over Union(IOU).Compare the effect of different activation functions on the accuracy of the YOLO-V4 model,and use the Mish activation function as the activation function of this model.Improve the calculation of the regression positioning loss function,and use the CEIOU loss function to balance the accuracy of each category.Use improved Adam optimization function and multi-stage learning optimization technology to improve the accuracy of the YOLO-V4 model.The channel pruning algorithm is used to compress the model and distillation technology is used in the fine-tuning of the model.The final model size was only 10.77%before compression,and the test set mean Average Precision(mAP)was 93.14%.The detection speed was 112 fps,which can meet the need for real-time detection of maize harvester ears in the field.This study can provide technical reference for the detection of the ear loss rate of intelligent maize harvesters.
文摘鱼类目标检测对渔业精准养殖、生产自动化、资源调查及鱼行为的研究等具有重要的意义。为了能快速准确地得到鱼类目标的位置和所属类别,提出了一种改进YOLO v4模型的鱼类目标检测方法,在CIoU(Complete Intersection over Union)损失函数基础上构建了新的损失项,改进的损失函数使真实框与相交框呈相同宽高比进行回归,同时通过设置多锚点框模式,增强在特定尺寸面积上的检测效果。结果显示:改进YOLO v4模型的mAP(mean Average Precision)比原模型有较大提升,在自建数据集、Fish4Knowledge数据集和NCFM数据集上的mAP分别达到了94.22%、99.52%、92.16%。研究表明,改进YOLO v4模型可以快速准确地检测到鱼的位置和类别,检测速度满足实时的要求,可以为渔业精准养殖等提供参考。
