针对YOLOv5(you only look once version five)模型在农作物害虫密集目标上的检测效果无法满足实际需求,以及训练过程中模型收敛速度较慢等问题,该研究提出了融入全局响应归一化(global response normalization,GRN)注意力机制的YOLOv5...针对YOLOv5(you only look once version five)模型在农作物害虫密集目标上的检测效果无法满足实际需求,以及训练过程中模型收敛速度较慢等问题,该研究提出了融入全局响应归一化(global response normalization,GRN)注意力机制的YOLOv5农作物害虫识别模型(YOLOv5-GRNS)。设计了融入GRN注意力机制的编码器(convolution three,C3)模块,提高对密集目标的识别精度;利用形状交并比(shape intersection over union,SIoU)损失函数提高模型收敛速度和识别精度;在公开数据集IP102(insect pests 102)的基础上,筛选出危害陕西省主要农作物的8种害虫类型,构建了新数据集IP8-CW(insect pests eight for corn and wheat)。改进后的模型在新IP8-CW和完整的IP102两种数据集上进行了全面验证。对于IP8-CW,全类别平均准确率(mean average precision,mAP)mAP@.5和mAP@.5:.95分别达到了72.3%和47.0%。该研究还对YOLOv5-GRNS模型进行了类激活图分析,不仅从识别精度,而且从可解释性的角度,验证了对农作物害虫、尤其是密集目标的优秀识别效果。此外,模型还兼具参数量少、运算量低的优势,具有良好的嵌入式设备应用前景。展开更多
Biology provides many examples of complex systems whose properties allow organisms to develop in a highly reproducible,or robust,manner.One such system is the growth and development of flat leaves in Arabidopsis thali...Biology provides many examples of complex systems whose properties allow organisms to develop in a highly reproducible,or robust,manner.One such system is the growth and development of flat leaves in Arabidopsis thaliana.This mechanistically challenging process results from multiple inputs including gene interactions,cellular geometry,growth rates,and coordinated cell divisions.To better understand how this complex genetic and cellular information controls leaf growth,we developed a mathematical model of flat leaf production.This two-dimensional model describes the gene interactions in a vertex network of cells which grow and divide according to physical forces and genetic information.Interestingly,the model predicts the presence of an unknown additional factor required for the formation of biologically realistic gene expression domains and iterative cell division.This two-dimensional model will form the basis for future studies into robustness of adaxial-abaxial patterning.展开更多
文摘针对YOLOv5(you only look once version five)模型在农作物害虫密集目标上的检测效果无法满足实际需求,以及训练过程中模型收敛速度较慢等问题,该研究提出了融入全局响应归一化(global response normalization,GRN)注意力机制的YOLOv5农作物害虫识别模型(YOLOv5-GRNS)。设计了融入GRN注意力机制的编码器(convolution three,C3)模块,提高对密集目标的识别精度;利用形状交并比(shape intersection over union,SIoU)损失函数提高模型收敛速度和识别精度;在公开数据集IP102(insect pests 102)的基础上,筛选出危害陕西省主要农作物的8种害虫类型,构建了新数据集IP8-CW(insect pests eight for corn and wheat)。改进后的模型在新IP8-CW和完整的IP102两种数据集上进行了全面验证。对于IP8-CW,全类别平均准确率(mean average precision,mAP)mAP@.5和mAP@.5:.95分别达到了72.3%和47.0%。该研究还对YOLOv5-GRNS模型进行了类激活图分析,不仅从识别精度,而且从可解释性的角度,验证了对农作物害虫、尤其是密集目标的优秀识别效果。此外,模型还兼具参数量少、运算量低的优势,具有良好的嵌入式设备应用前景。
基金supported by the NSF#2039489 to A.Y.H and the NSF#1813071 to C.-S.C.
文摘Biology provides many examples of complex systems whose properties allow organisms to develop in a highly reproducible,or robust,manner.One such system is the growth and development of flat leaves in Arabidopsis thaliana.This mechanistically challenging process results from multiple inputs including gene interactions,cellular geometry,growth rates,and coordinated cell divisions.To better understand how this complex genetic and cellular information controls leaf growth,we developed a mathematical model of flat leaf production.This two-dimensional model describes the gene interactions in a vertex network of cells which grow and divide according to physical forces and genetic information.Interestingly,the model predicts the presence of an unknown additional factor required for the formation of biologically realistic gene expression domains and iterative cell division.This two-dimensional model will form the basis for future studies into robustness of adaxial-abaxial patterning.
