摘要
为了实现复杂自然背景下虫咬紫金蝉茶的快速、准确识别,提出了一种基于YOLOv5s-SE和通道剪枝的虫咬紫金蝉茶检测方法。首先在YOLOv5s的主干网络中添加SE注意力机制以增强模型特征提取的能力,降低复杂背景对茶叶特征提取时的干扰;然后采用通道剪枝算法对模型进行剪枝并进行微调,实现虫咬紫金蝉茶叶片的快速、准确检测。结果表明,修剪后的模型相比原YOLOv5s模型,参数量减少60.1%,帧率提升18.6%,运算量减少29.7%,平均精度均值(mAP)为81.3%。
In order to achieve rapid and accurate identification of insect‑bitten Zijin tea leaves in complex nature backgrounds,a detection method for Zijin tea based on YOLOv5s‑SE and channel pruning was proposed.Firstly,SE modules were added to the backbone network of YOLOv5s to enhance the model’s feature extraction capability and reduce interference from complex backgrounds during tea leaf feature extraction.Then,a channel pruning algorithm was used to prune the model and fine‑tuning was conducted,enabling fast and accurate detection of insect‑bitten Zijin tea leaves.Compared to YOLOv5s,the test results showed that the pruned model reduced parameters by 60.1%,improved FPS by 18.6%,reduced GFLOPs by 29.7%,and achieved mAP of 81.3%.
作者
戴佳兵
宋春芳
凌彩金
李臻锋
孙崇高
DAI Jiabing;SONG Chunfang;LING Caijin;LI Zhenfeng;SUN Chonggao(College of Mechanical Engineering,Jiangnan University/Jiangsu Key Laboratory of Advanced Food Manufacturing Equipment&Technology,Wuxi 214122,China;Tea Research Institute,Guangdong Academy of Agricultural Sciences/Guangdong Key Laboratory of Tea Plant Resources Innovation&Utilization,Guangzhou 510640,China;Shandong Bihai Packaging Materials Co.,Ltd.,Linyi 276600,China)
出处
《河南农业科学》
北大核心
2024年第5期157-163,共7页
Journal of Henan Agricultural Sciences
基金
农产品为单元的广东省现代农业产业技术体系创新团队建设项目(茶叶)(2023KJ120)
河源市科技计划项目(河科2021030)
2024紫金县科技计划项目。
