基于改进YOLOv4模型的番茄成熟度检测方法  

Research on tomato maturity detection method based on improved YOLOv4 model

作　　者：吕金锐[1] 付燕[2] 倪美玉 曹为刚 杜子涛[4] LU Jinrui;FU Yan;NI Meiyu;CAO Weigang;DU Zitao(Taiyuan City Vocational College,Taiyuan,Shanxi 030027,China;Xi'an University of Science and Technology,Xi'an,Shaanxi 710054,China;Zhejiang Jinhua Technology&Trade Polytechnic,Jinhua,Zhejiang 321019,China;Hebei University of Technology,Tianjin 300401,China)

机构地区：[1]太原城市职业技术学院,山西太原030027 [2]西安科技大学,陕西西安710054 [3]浙江金华科贸职业技术学院,浙江金华321019 [4]河北工业大学,天津300401

出　　处：《食品与机械》2023年第9期134-139,共6页Food and Machinery

基　　金：山西省重点研发计划项目(编号:201903D121171);山西省优秀博士科研资助项目(编号:2022LJ042);教育部职业院校信息化教学指导委员会数字化转型行动研究课题(编号:KT22302)。

摘　　要：目的:解决现有番茄成熟度检测方法存在的检测精度低和模型参数量多等问题。方法:基于番茄图像采集系统,提出了一种改进的YOLOv4模型用于番茄成熟度自动检测。将轻量级网络MobileNetv3网络引入模型替换CSPDarkNet53网络,降低模型复杂度。在SPP模块中采用平均池化替代最大池化,提高算法对小目标的检测精度。在上采样过程中引入注意力机制CBAM增强深浅层特征融合能力,并通过试验验证所提模型的可行性。结果:与常规方法相比,试验方法在番茄成熟度检测中具有较高的检测mAP值和运行效率,且模型参数量较少,mAP值为92.50%,检测速度为37.1 FPS,模型参数量为48 M。结论:该番茄成熟度检测方法能有效降低模型参数和检测时间,具有较高的检测mAP值。Objective:To solve the problems of low detection accuracy and large number of model parameters in existing tomato maturity detection methods.Methods:Based on the tomato image acquisition system,an improved YOLOv4 model was proposed for automatic detection of tomato maturity.Introducing the lightweight network MobileNetv3 network into the model to replace the CSPParkNet53 network,reducing model complexity.Using average pooling instead of maximum pooling in the SPP module improved the algorithm's detection accuracy for small targets.Introduced attention mechanism CBAM in the upsampling process to enhance the fusion ability of deep and shallow features,and verified the feasibility of the proposed model through experiments.Results:Compared with conventional methods,the experimental method had higher detection mAP values and operational efficiency in tomato maturity detection,and the model parameter quantity was relatively small,the mAP value was 92.50%,the detection speed was 37.1 FPS,and the model parameter quantity was 48 M.Conclusion:This tomato maturity detection method can effectively reduce model parameters and detection time,and has a high detection mAP value.

关 键 词：番茄 成熟度 YOLOv4模型 MobileNetv3网络 注意力机制CBAM 平均池化 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] S641.2[自动化与计算机技术—计算机科学与技术]