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
A novel model of fuzzy clustering, i.e. an allied fuzzy c means （AFCM） model is proposed based on the combination of advantages of fuzzy c means （FCM） and possibilistic c means （PCM） clustering. PCM is sensitive...A novel model of fuzzy clustering, i.e. an allied fuzzy c means （AFCM） model is proposed based on the combination of advantages of fuzzy c means （FCM） and possibilistic c means （PCM） clustering. PCM is sensitive to initializations and often generates coincident clusters. AFCM overcomes this shortcoming and it is an ex tension of PCM. Membership and typicality values can be simultaneously produced in AFCM. Experimental re- suits show that noise data can be well processed, coincident clusters are avoided and clustering accuracy is better.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A novel model of fuzzy clustering, i.e. an allied fuzzy c means （AFCM） model is proposed based on the combination of advantages of fuzzy c means （FCM） and possibilistic c means （PCM） clustering. PCM is sensitive to initializations and often generates coincident clusters. AFCM overcomes this shortcoming and it is an ex tension of PCM. Membership and typicality values can be simultaneously produced in AFCM. Experimental re- suits show that noise data can be well processed, coincident clusters are avoided and clustering accuracy is better.
