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

doi:10.1002/jsfa.13396

CSpace

	T-YOLO: a lightweight and efficient detection model for nutrient buds in complex tea-plantation environments
	Bai, Bingyi 1,2; Wang, Junshu 3; Li, Jianlong 4,5; Yu, Long 1; Wen, Jiangtao 6; Han, Yuxing 7
	2024-03-04
发表期刊	JOURNAL OF THE SCIENCE OF FOOD AND AGRICULTURE
ISSN	0022-5142
摘要	BACKGROUND: Quick and accurate detection of nutrient buds is essential 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 the location of tea nutrient buds challenging. RESULTS: This research presents a lightweight and efficient detection model, T-YOLO, for the accurate detection of 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 achieve further 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 total number of parameters for model training (Params) is 11.26 million (M), and the number of floating-point operations (FLOPs) is 17.2 Giga (G). Compared with the baseline YOLOv5 model, T-YOLO reduces Params by 47% and lowers FLOPs by 65%. T-YOLO also outperforms the existing optimal detection YOLOv8 model by 7.5% in terms of mAP. CONCLUSION: The 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 manage smart tea gardens. The T-YOLO model outperforms mainstream detection models on the public dataset, Global Wheat Head Detection (GWHD), which offers a reference for the construction of lightweight and efficient detection models for other small target crops. (c) 2024 Society of Chemical Industry.
关键词	tea nutrient buds deep learning small object detection lightweight model
其他关键词	SYSTEM
DOI	10.1002/jsfa.13396
收录类别	SCIE
语种	英语
WOS研究方向	Agriculture ; Chemistry ; Food Science & Technology
WOS类目	Agriculture, Multidisciplinary ; Chemistry, Applied ; Food Science & Technology
WOS记录号	WOS:001179076600001
出版者	WILEY
原始文献类型	Article ; Early Access
EISSN	1097-0010
引用统计	被引频次：7[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.library.ouchn.edu.cn/handle/39V7QQFX/169795
专题	国家开放大学
通讯作者	Han, Yuxing
作者单位	1.South China Agr Univ, Coll Elect Engn, Guangzhou, Peoples R China; 2.South China Agr Univ, Guangdong Lab Lingnan Modern Agr, Guangzhou, Peoples R China; 3.Guangdong Open Univ, Sch Robot, Guangzhou, Peoples R China; 4.Guangdong Acad Agr Sci, Tea Res Inst, Guangzhou, Peoples R China; 5.Guangdong Prov Key Lab Tea Plant Resources Innovat, Guangzhou, Peoples R China; 6.Eastern Inst Technol, Ningbo Inst Digital Twin, Ningbo, Peoples R China; 7.Tsinghua Univ, Shenzhen Int Grad Sch, Shenzhen, Peoples R China
推荐引用方式 GB/T 7714	Bai, Bingyi,Wang, Junshu,Li, Jianlong,et al. T-YOLO: a lightweight and efficient detection model for nutrient buds in complex tea-plantation environments[J]. JOURNAL OF THE SCIENCE OF FOOD AND AGRICULTURE,2024.
APA	Bai, Bingyi,Wang, Junshu,Li, Jianlong,Yu, Long,Wen, Jiangtao,&Han, Yuxing.(2024).T-YOLO: a lightweight and efficient detection model for nutrient buds in complex tea-plantation environments.JOURNAL OF THE SCIENCE OF FOOD AND AGRICULTURE.
MLA	Bai, Bingyi,et al."T-YOLO: a lightweight and efficient detection model for nutrient buds in complex tea-plantation environments".JOURNAL OF THE SCIENCE OF FOOD AND AGRICULTURE (2024).