[目的]针对苹果无损检测过程中表面缺陷检测精度低的问题,提出一种基于DSCS-YOLO的苹果表面缺陷检测方法。[方法]首先为提高网络对表面缺陷细节特征的提取能力,设计一种基于Dense模块以及SE模块的深浅特征选择模块DSCS(deep and shallow...[目的]针对苹果无损检测过程中表面缺陷检测精度低的问题,提出一种基于DSCS-YOLO的苹果表面缺陷检测方法。[方法]首先为提高网络对表面缺陷细节特征的提取能力,设计一种基于Dense模块以及SE模块的深浅特征选择模块DSCS(deep and shallow feature selection module),采用DSCS替换Backbone中的C3模块,在保留表面缺陷浅层信息的基础上强化对重要特征的学习,并起到削弱冗余特征的作用;针对Backbone与Neck部分输出信息过多导致的参数耦合问题,利用解耦头原理对Head层部分进行分层预测。其次采用ELU激活函数改进原有解耦头,简化末端结构,使网络训练更加容易。最后针对表面缺陷标注困难的问题,采用Wise-IoU损失函数代替CIoU损失函数,为不同质量的标注提供非线性增益,实现网络的动态聚焦学习。[结果]DSCS-YOLO提高了对小目标的检测能力,在苹果表面缺陷测试集上平均精度均值达到90.9%,相较于YOLOv3-tiny、YOLOv5s、YOLOX-s以及SSD分别提高了4.5%、1.9%、6.3%、16.3%,检测效果最优。同时模型参数量为9.54 M,推理时间仅为2.8 ms,检测速度快,满足实际应用需求。[结论]改进后的DSCS-YOLO提高了YOLOv5s算法的精度,实现了苹果表面缺陷的精准识别。展开更多
The effect of soil nutrient content on fruit yield and fruit quality is very important.To explore the effect of soil nutrients on apple quality we investigated 200 fruit samples from 40 orchards in Feng County,Jiangsu...The effect of soil nutrient content on fruit yield and fruit quality is very important.To explore the effect of soil nutrients on apple quality we investigated 200 fruit samples from 40 orchards in Feng County,Jiangsu Province.Soil mineral elements and fruit quality were measured.The effect of soil nutrient content on fruit quality was analyzed by artificial neural network(ANN)model.The results showed that the prediction accuracy was highest(R2=0.851,0.847,0.885,0.678 and 0.746)in mass per fruit(MPF),hardness(HB),soluble solids concentrations(SSC),titratable acid concentration(TA)and solid-acid ratio(SSC/TA),respectively.The sensitivity analysis of the prediction model showed that soil available P,K,Ca and Mg contents had the greatest impact on the quality of apple fruit.Response surface method(RSM)was performed to determine the optimum range of the available P,K,Ca,and Mg contents in orchards In Feng County,which were 10∼20 mg⋅kg^(−1),170∼200 mg⋅kg^(−1),1000∼1500 mg⋅kg^(−1),and 80∼200 mg⋅kg^(−1),respectively.The research also concluded that improving the content of available P and available Ca in orchard soil was crucial to improve apple fruit quality in Feng County,Jiangsu Province.展开更多
基金supported by the National Key Research and Development Program of China(2019YFD1000103)National Natural Science Foundation of China(31872076)+1 种基金supported by the National Key Research and Development Program of China(2019YFD1000103)National Natural Science Foundation of China(31872076).
文摘The effect of soil nutrient content on fruit yield and fruit quality is very important.To explore the effect of soil nutrients on apple quality we investigated 200 fruit samples from 40 orchards in Feng County,Jiangsu Province.Soil mineral elements and fruit quality were measured.The effect of soil nutrient content on fruit quality was analyzed by artificial neural network(ANN)model.The results showed that the prediction accuracy was highest(R2=0.851,0.847,0.885,0.678 and 0.746)in mass per fruit(MPF),hardness(HB),soluble solids concentrations(SSC),titratable acid concentration(TA)and solid-acid ratio(SSC/TA),respectively.The sensitivity analysis of the prediction model showed that soil available P,K,Ca and Mg contents had the greatest impact on the quality of apple fruit.Response surface method(RSM)was performed to determine the optimum range of the available P,K,Ca,and Mg contents in orchards In Feng County,which were 10∼20 mg⋅kg^(−1),170∼200 mg⋅kg^(−1),1000∼1500 mg⋅kg^(−1),and 80∼200 mg⋅kg^(−1),respectively.The research also concluded that improving the content of available P and available Ca in orchard soil was crucial to improve apple fruit quality in Feng County,Jiangsu Province.
