棉田虫害的快速检测与准确识别是预防棉田虫害、提高棉花品质的重要前提。针对真实棉田环境下昆虫相似度高、背景干扰严重的问题,该研究提出一种ECSF-YOLOv7棉田虫害检测模型。首先,采用EfficientFormerV2作为特征提取网络,以加强网络...棉田虫害的快速检测与准确识别是预防棉田虫害、提高棉花品质的重要前提。针对真实棉田环境下昆虫相似度高、背景干扰严重的问题,该研究提出一种ECSF-YOLOv7棉田虫害检测模型。首先,采用EfficientFormerV2作为特征提取网络,以加强网络的特征提取能力并减少模型参数量;同时,将卷积注意力模块(convolution block attention module,CBAM)嵌入到模型的主干输出端,以增强模型对小目标的特征提取能力并削弱背景干扰;其次,使用GSConv卷积搭建Slim-Neck颈部网络结构,在减少模型参数量的同时保持模型的识别精度;最后,采用Focal-EIOU(focal and efficient IOU loss,Focal-EIOU)作为边界框回归损失函数,加速网络收敛并提高模型的检测准确率。结果表明,改进的ECSF-YOLOv7模型在棉田虫害测试集上的平均精度均值(mean average precision,mAP)为95.71%,检测速度为69.47帧/s。与主流的目标检测模型YOLOv7、SSD、YOLOv5l和YOLOX-m相比,ECSF-YOLOv7模型的mAP分别高出1.43、9.08、1.94、1.52个百分点,并且改进模型具有参数量更小、检测速度更快的优势,可为棉田虫害快速准确检测提供技术支持。展开更多
【目的】针对城市复杂环境下的车辆难识别问题,提出了基于YOLOv8n(you only look once version 8n)的改进模型DB-YOLOv8n(deformable block YOLOv8n)。【方法】首先在颈部网络融合通道注意力机制(efficient channel attention,ECA)和改...【目的】针对城市复杂环境下的车辆难识别问题,提出了基于YOLOv8n(you only look once version 8n)的改进模型DB-YOLOv8n(deformable block YOLOv8n)。【方法】首先在颈部网络融合通道注意力机制(efficient channel attention,ECA)和改进加权双向特征金字塔网络(bidirectional feature pyramid network,BiFPN),以增强在昏暗光线下的车辆检测性能及对多尺度图像的处理能力,特别是对远处或部分遮挡的车辆;其次在主干网络引入可变型卷积(deformable convolutional networks,DCN),以增强模型对不同尺寸车辆的适应性;最后使用精确边界框回归的高效交并比损失函数(focal and efficient intersection over union loss,Focal-EIOU loss)替换高效交并比(efficient intersection over union,EIOU),进一步提升模型的稳定性。【结果】DB-YOLOv8n在自制车辆数据集上相比YOLOv8n,平均精度、精度和召回率分别提高了3.2%、3%和2%。【结论】本研究结果能为提高车辆检测的精确度提供理论参考。展开更多
针对YOLO v5l(you only look once version 5 large)算法对于小目标、少样本且背景复杂的排水管道缺陷图像检测的精度低、误检和漏检率较高等问题,提出了一种基于YOLO v5l-Im算法的排水管道缺陷检测改进方法。做了三点改进:首先提出了Fo...针对YOLO v5l(you only look once version 5 large)算法对于小目标、少样本且背景复杂的排水管道缺陷图像检测的精度低、误检和漏检率较高等问题,提出了一种基于YOLO v5l-Im算法的排水管道缺陷检测改进方法。做了三点改进:首先提出了Focal-EIoU(focal embedding intersection over union)损失函数,有效提升了检测模型的性能;其次为增强检测模型对小目标缺陷的检测效果,减少缺陷误检和漏检的概率,将骨干网络中浅层特征图融合到双向特征金字塔网络(bidirectional feature pyramid network,BiFPN)中,增加针对小目标的预测层;最后在YOLO v5l中引入坐标注意力机制(coordinate attention,CA),提高模型对图像中感兴趣区域的敏感程度,减少冗余背景信息的干扰。3种改进对平均检测准确率(mean average precision,mAP)的提升分别为2.0、2.9、5.9个百分点。将三种有效改进融合到一起,检测结果表明:本文提出的YOLO v5l-Im模型的mAP达到了92.1%,较原模型的85.5%提升了6.5个百分点。由此可见,所做的改进有效增强了YOLO v5l对排水管道缺陷的检测能力。展开更多
Electrolysis tanks are used to smeltmetals based on electrochemical principles,and the short-circuiting of the pole plates in the tanks in the production process will lead to high temperatures,thus affecting normal pr...Electrolysis tanks are used to smeltmetals based on electrochemical principles,and the short-circuiting of the pole plates in the tanks in the production process will lead to high temperatures,thus affecting normal production.Aiming at the problems of time-consuming and poor accuracy of existing infrared methods for high-temperature detection of dense pole plates in electrolysis tanks,an infrared dense pole plate anomalous target detection network YOLOv5-RMF based on You Only Look Once version 5(YOLOv5)is proposed.Firstly,we modified the Real-Time Enhanced Super-Resolution Generative Adversarial Network(Real-ESRGAN)by changing the U-shaped network(U-Net)to Attention U-Net,to preprocess the images;secondly,we propose a new Focus module that introduces the Marr operator,which can provide more boundary information for the network;again,because Complete Intersection over Union(CIOU)cannot accommodate target borders that are increasing and decreasing,replace CIOU with Extended Intersection over Union(EIOU),while the loss function is changed to Focal and Efficient IOU(Focal-EIOU)due to the different difficulty of sample detection.On the homemade dataset,the precision of our method is 94%,the recall is 70.8%,and the map@.5 is 83.6%,which is an improvement of 1.3%in precision,9.7%in recall,and 7%in map@.5 over the original network.The algorithm can meet the needs of electrolysis tank pole plate abnormal temperature detection,which can lay a technical foundation for improving production efficiency and reducing production waste.展开更多
Detection of floating garbage in inland rivers is crucial for water environmental protection,as it effectively reduces ecological damage and ensures the safety of water resources.To address the inefficiency of traditi...Detection of floating garbage in inland rivers is crucial for water environmental protection,as it effectively reduces ecological damage and ensures the safety of water resources.To address the inefficiency of traditional cleanup methods and the challenges in detecting small targets,an improved YOLOv5 object detection model was proposed in this study.In order to enhance the model’s sensitivity to small targets and mitigate the impact of redundant information on detection performance,a bi-level routing attention mechanism was introduced and embedded into the backbone network.Additionally,a multi-scale detection head was incorporated into the model,allowing for more comprehensive coverage of floating garbage of various sizes through multi-scale feature extraction and detection.The Focal-EIoU loss function was also employed to optimize the model parameters,improving localization accuracy.Experimental results on the publicly available FloW_Img dataset demonstrated that the improved YOLOv5 model outperforms the original YOLOv5 model in terms of precision and recall,achieving a mAP(mean average precision)of 86.12%,with significant improvements and faster convergence.展开更多
文摘棉田虫害的快速检测与准确识别是预防棉田虫害、提高棉花品质的重要前提。针对真实棉田环境下昆虫相似度高、背景干扰严重的问题,该研究提出一种ECSF-YOLOv7棉田虫害检测模型。首先,采用EfficientFormerV2作为特征提取网络,以加强网络的特征提取能力并减少模型参数量;同时,将卷积注意力模块(convolution block attention module,CBAM)嵌入到模型的主干输出端,以增强模型对小目标的特征提取能力并削弱背景干扰;其次,使用GSConv卷积搭建Slim-Neck颈部网络结构,在减少模型参数量的同时保持模型的识别精度;最后,采用Focal-EIOU(focal and efficient IOU loss,Focal-EIOU)作为边界框回归损失函数,加速网络收敛并提高模型的检测准确率。结果表明,改进的ECSF-YOLOv7模型在棉田虫害测试集上的平均精度均值(mean average precision,mAP)为95.71%,检测速度为69.47帧/s。与主流的目标检测模型YOLOv7、SSD、YOLOv5l和YOLOX-m相比,ECSF-YOLOv7模型的mAP分别高出1.43、9.08、1.94、1.52个百分点,并且改进模型具有参数量更小、检测速度更快的优势,可为棉田虫害快速准确检测提供技术支持。
文摘【目的】针对城市复杂环境下的车辆难识别问题,提出了基于YOLOv8n(you only look once version 8n)的改进模型DB-YOLOv8n(deformable block YOLOv8n)。【方法】首先在颈部网络融合通道注意力机制(efficient channel attention,ECA)和改进加权双向特征金字塔网络(bidirectional feature pyramid network,BiFPN),以增强在昏暗光线下的车辆检测性能及对多尺度图像的处理能力,特别是对远处或部分遮挡的车辆;其次在主干网络引入可变型卷积(deformable convolutional networks,DCN),以增强模型对不同尺寸车辆的适应性;最后使用精确边界框回归的高效交并比损失函数(focal and efficient intersection over union loss,Focal-EIOU loss)替换高效交并比(efficient intersection over union,EIOU),进一步提升模型的稳定性。【结果】DB-YOLOv8n在自制车辆数据集上相比YOLOv8n,平均精度、精度和召回率分别提高了3.2%、3%和2%。【结论】本研究结果能为提高车辆检测的精确度提供理论参考。
文摘针对YOLO v5l(you only look once version 5 large)算法对于小目标、少样本且背景复杂的排水管道缺陷图像检测的精度低、误检和漏检率较高等问题,提出了一种基于YOLO v5l-Im算法的排水管道缺陷检测改进方法。做了三点改进:首先提出了Focal-EIoU(focal embedding intersection over union)损失函数,有效提升了检测模型的性能;其次为增强检测模型对小目标缺陷的检测效果,减少缺陷误检和漏检的概率,将骨干网络中浅层特征图融合到双向特征金字塔网络(bidirectional feature pyramid network,BiFPN)中,增加针对小目标的预测层;最后在YOLO v5l中引入坐标注意力机制(coordinate attention,CA),提高模型对图像中感兴趣区域的敏感程度,减少冗余背景信息的干扰。3种改进对平均检测准确率(mean average precision,mAP)的提升分别为2.0、2.9、5.9个百分点。将三种有效改进融合到一起,检测结果表明:本文提出的YOLO v5l-Im模型的mAP达到了92.1%,较原模型的85.5%提升了6.5个百分点。由此可见,所做的改进有效增强了YOLO v5l对排水管道缺陷的检测能力。
文摘Electrolysis tanks are used to smeltmetals based on electrochemical principles,and the short-circuiting of the pole plates in the tanks in the production process will lead to high temperatures,thus affecting normal production.Aiming at the problems of time-consuming and poor accuracy of existing infrared methods for high-temperature detection of dense pole plates in electrolysis tanks,an infrared dense pole plate anomalous target detection network YOLOv5-RMF based on You Only Look Once version 5(YOLOv5)is proposed.Firstly,we modified the Real-Time Enhanced Super-Resolution Generative Adversarial Network(Real-ESRGAN)by changing the U-shaped network(U-Net)to Attention U-Net,to preprocess the images;secondly,we propose a new Focus module that introduces the Marr operator,which can provide more boundary information for the network;again,because Complete Intersection over Union(CIOU)cannot accommodate target borders that are increasing and decreasing,replace CIOU with Extended Intersection over Union(EIOU),while the loss function is changed to Focal and Efficient IOU(Focal-EIOU)due to the different difficulty of sample detection.On the homemade dataset,the precision of our method is 94%,the recall is 70.8%,and the map@.5 is 83.6%,which is an improvement of 1.3%in precision,9.7%in recall,and 7%in map@.5 over the original network.The algorithm can meet the needs of electrolysis tank pole plate abnormal temperature detection,which can lay a technical foundation for improving production efficiency and reducing production waste.
文摘Detection of floating garbage in inland rivers is crucial for water environmental protection,as it effectively reduces ecological damage and ensures the safety of water resources.To address the inefficiency of traditional cleanup methods and the challenges in detecting small targets,an improved YOLOv5 object detection model was proposed in this study.In order to enhance the model’s sensitivity to small targets and mitigate the impact of redundant information on detection performance,a bi-level routing attention mechanism was introduced and embedded into the backbone network.Additionally,a multi-scale detection head was incorporated into the model,allowing for more comprehensive coverage of floating garbage of various sizes through multi-scale feature extraction and detection.The Focal-EIoU loss function was also employed to optimize the model parameters,improving localization accuracy.Experimental results on the publicly available FloW_Img dataset demonstrated that the improved YOLOv5 model outperforms the original YOLOv5 model in terms of precision and recall,achieving a mAP(mean average precision)of 86.12%,with significant improvements and faster convergence.
