T‐YOLO: a lightweight and efficient detection model for nutrient buds in complex tea‐plantation environments

Abstract

BackgroundQuick and accurate detection of nutrient buds is critical for yield prediction and field management in tea plantations. However, the complexity of tea plantation environments and the similarity in color between nutrient buds and older leaves make locating tea nutrient buds challenging.ResultsThis research presents a lightweight and efficient detection T‐YOLO model for accurately detecting tea nutrient buds in unstructured environments. First, a lightweight module C2fG2 and an efficient feature extraction module DBS are introduced into the backbone and neck of the YOLOv5 baseline model. Second, the head network of the model is pruned to further achieve lightweighting. Finally, the dynamic detection head is integrated to mitigate the feature loss caused by lightweighting. The experimental data show that T‐YOLO achieves a mean average precision (mAP) of 84.1%, the parameters are 11.26 M, and the floating‐point operations per second (FLOPs) are 17.2 G. Compared to the baseline YOLOv5 model, T‐YOLO reduces parameters by 47% and lowers FLOPs by 65%. Additionally, T‐YOLO outperforms the existing optimal detection YOLOv8 model by 7.5% in terms of mAP.ConclusionThe T‐YOLO model proposed in this study performs well in detecting small tea nutrient buds. It provides a decision‐making basis for tea farmers to realize the fine management of smart tea gardens. Additionally, the T‐YOLO model outperforms mainstream detection models on the public dataset GWHD, which offers a reference for the detection of other small target crops.This article is protected by copyright. All rights reserved.