基于深度学习的白纹伊蚊卵粒识别模型初步研究  

PRELIMINARY STUDY ON EGG RECOGNITION MODEL OF AEDES ALBOPICTUS BASED ON DEEP LEARNING

作　　者：朱敏慧[1] 董琳娟 王墩家 蔡逸舟 张兆文 刘曜[2] 何世鹏 周毅彬 ZHU Min-hui;DONG Lin-juan;WANG Dun-jia;CAI Yi-zhou;ZHANG Zhao-wen;LIU Yao;HE Shi-peng;ZHOU Yi-bin(Minhang District Center for Disease Control and Prevention,Shanghai 201100,China;Shanghai Municipal Center for Disease Control and Prevention,Shanghai 200336,China)

机构地区：[1]上海市闵行区疾病预防控制中心,上海201100 [2]上海市疾病预防控制中心,上海200336

出　　处：《寄生虫与医学昆虫学报》2024年第1期12-18,共7页Acta Parasitologica et Medica Entomologica Sinica

基　　金：上海市闵行区自然科学研究课题(2023MHZ002);上海市闵行区公共卫生重点学科(MGWXK2023-09)。

摘　　要：目的构建白纹伊蚊Aedes albopictus卵粒图片数据库,并基于深度学习和瓦片重叠法建立白纹伊蚊卵粒自动识别和计数模型,为伊蚊监测和防治提供技术方法。方法在上海市3个区收集野外和实验室品系的白纹伊蚊卵粒图片449张,使用Python环境labelimg库进行人工标定蚊卵,采用快速区域卷积神经网络(faster regional convolution neural network,Faster R-CNN)模型建立白纹伊蚊卵粒识别模型,并使用瓦片重叠法智能识别和计数。使用精确率、召回率和调和平均值(F-measure)进行模型效果评价。结果经过15次模型迭代训练,损失值随着训练次数增加逐渐下降至0.000119,平均精度均值(Mean Aaccuracy,mAP)从0.968增加至0.980,最终模型精确率为0.90,召回率为0.97,调和平均值为0.93。结论本模型具有较高的白纹伊蚊卵粒识别能力,初步达到了辅助开展诱蚊诱卵器监测中卵粒鉴别和计数的功能。在不断的优化模型、细化分类识别能力后可成为简便高效的监测辅助工具。Objective In this study,a pictorial database of Aedes albopictus eggs was built to establish a model for the automatic recognition and counting of eggs of this mosquito species.Methods In total,449 images of Ae.albopictus eggs from field strains in three districts of Shanghai and laboratory strains were collected.The eggs were manually calibrated using the Python environment labeling library,and the faster region-based convolution neural network(Faster R-CNN)was used to train the model with the tile overlap method.Results The results of model validation evaluation using accuracy,recall,and F-measure showed that after 15 training sessions,the loss gradually decreased with increasing training frequency and ultimately decreased to 0.000119.The mean accuracy(mAP)increased from 0.968 to 0.980 with increasing training frequency.The final model had an accuracy of up to 0.90,a recall rate of 0.97,and an F-measure of 0.93.Conclusion The established model achieved its function of assisting in egg identification and counting.With further optimization of the model and refining of its classification and recognition capabilities,it will serve as a simple and efficient auxiliary monitoring tool.

关 键 词：深度学习 诱蚊诱卵器 白纹伊蚊 卵粒 

分 类 号：R384.1[医药卫生—医学寄生虫学] TP391.41[医药卫生—基础医学]