TDDet: A novel lightweight and efficient tea disease detector

• 全文链接

TDDet：一种新型轻便高效的茶叶病害检测仪

关键词：

来源：

Computers and Electronics in Agriculture 期刊

全文链接：

//agri.nais.net.cn/topic/downloadFile/d3cc4271-042b-4048-9a1e-59ed40aaf857

来源地址：

https://www.sciencedirect.com/science/article/pii/S0168169925005873

资源所属：

茶学研究专题

类型：

学术文献

语种：

英语

原文发布日期：

2025-05-16

摘要：

This paper proposes a lightweight and efficient detector called TDDet to quickly and accurately detect tea diseases.  TDDet is mainly composed of two key innovations: feature extraction and feature aggregation.  For feature extraction, we use lightweight depthwise separable convolution to reduce the computational load and enhance the ability to extract key local features in images of tea diseases.  In addition, attention mechanisms including channel-, spatial-, and self-attentions, are employed to enable the model to focus on the most important parts of tea diseases, thereby improving the performance of the model.  For feature aggregation, we propose a novel Cross-scale Feature Fusion (CFF) module to focus on tea disease areas, boosting the model’s sensitivity to feature details.  Based on CFF, TDDet repeatedly fuses multiscale features of different levels in a top-down and bottom-up manner, enhancing feature representation capability.  Besides, a lightweight and efficient upsampling module, called Dysample, is used to reduce computational costs and improve model performance by dynamically adjusting the sampling rate of feature maps.  Experimental results demonstrate that TDDet with fewer parameters outperforms other state-of-the-art object detection models, enabling fast and accurate identification of tea diseases.