期刊论文

Wolfberry pest detection based on improved YOLOv5

中文

浙江大学学报.工学版

1008-973X

2024

58

10

1992-2000

10.3785/j.issn.1008-973X.2024.10.002

湖北省社会科学基金资助项目（21ZD072）；

本校为第一机构

为了检测复杂环境下枸杞的虫害情况,提出基于改进YOLOv5m的模型.以下一代视觉转换器(Next-ViT)作为骨干网络,提高模型的特征提取能力,使模型更加关注关键目标特征.在模型颈部增加自适应融合的上下文增强模块,增强模...展开更多 为了检测复杂环境下枸杞的虫害情况,提出基于改进YOLOv5m的模型.以下一代视觉转换器(Next-ViT)作为骨干网络,提高模型的特征提取能力,使模型更加关注关键目标特征.在模型颈部增加自适应融合的上下文增强模块,增强模型对上下文信息的理解与处理能力,提高模型对小目标(蚜虫)的检测精度.将颈部网络中的C3模块替换为C3_Faster模块,减少模型占用量并进一步提高模型检测精度.实...

A model based on improved YOLOv5m was proposed for wolfberry pest detection in a complex environment.The next generation vision transformer(Next-ViT)was used as the backbone network to improve the feature extraction ability of the model,and the key target features were ...MORE A model based on improved YOLOv5m was proposed for wolfberry pest detection in a complex environment.The next generation vision transformer(Next-ViT)was used as the backbone network to improve the feature extraction ability of the model,and the key target features were gi...