TBD-Y: Automatic tea bud detection with synergistic object-spatial attention and global-local attention guided feature fusion

Automatic Tea Bud Detection (TBD) is a critical technology in intelligent tea-picking systems. Nevertheless, challenges, such as complex environments and the high visual similarity between tea buds and backgrounds, frequently result in false detection and missed detection, especially for small tea b...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhongyuan Liu, Li Zhuo, Chunwang Dong, Jiafeng Li, Yang Li
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375525002990
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850128705165197312
author Zhongyuan Liu
Li Zhuo
Chunwang Dong
Jiafeng Li
Yang Li
author_facet Zhongyuan Liu
Li Zhuo
Chunwang Dong
Jiafeng Li
Yang Li
author_sort Zhongyuan Liu
collection DOAJ
description Automatic Tea Bud Detection (TBD) is a critical technology in intelligent tea-picking systems. Nevertheless, challenges, such as complex environments and the high visual similarity between tea buds and backgrounds, frequently result in false detection and missed detection, especially for small tea buds. To address these issues, in this paper, an automatic TBD method is proposed, which is built upon the YOLOv11 object detection framework, named TBD-Y. Firstly, a Synergistic Object-Spatial Attention (SOSA) mechanism is proposed, which incorporates the proposed Local Context Attention (LCA) mechanism to enhance the features in both spatial and regional dimensions. It enables the network to focus more on the tea bud regions, and suppress the interference from background noise. Secondly, a Global-local Attention Guided Feature Fusion (GAGFF) strategy is designed. It consists of two branches: one branch enhances low-resolution, high-level features containing rich global semantic information, while the other branch strengthens high-resolution features that preserve low-level visual details. The fusion of these two branches improves the representation capability of the features. The SOSA and GAGFF are integrated into the YOLOv11 framework, constructing three variants of the TBD model with different parameter scales, named TBD-Y-L, TBD-Y-M, and TBD-Y-S. Experimental results on the self-built TBD dataset and the publicly available Global Wheat Head Dataset 2021 (GWHD_2021) demonstrate that the proposed TBD-Y-L outperforms the existing methods, achieving superior detection accuracy. Furthermore, the TBD-Y-S model exhibits improved detection accuracy compared to YOLOv11-L, while maintaining lower model parameters and computational complexity.
format Article
id doaj-art-5d7b5f7a4cd14e2bada610d3bc579450
institution OA Journals
issn 2772-3755
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-5d7b5f7a4cd14e2bada610d3bc5794502025-08-20T02:33:12ZengElsevierSmart Agricultural Technology2772-37552025-12-011210106610.1016/j.atech.2025.101066TBD-Y: Automatic tea bud detection with synergistic object-spatial attention and global-local attention guided feature fusionZhongyuan Liu0Li Zhuo1Chunwang Dong2Jiafeng Li3Yang Li4Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing 100124, China; Faculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaBeijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing 100124, China; Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China; Corresponding authors.Tea Research Institute, Shandong Academy of Agricultural Sciences, Jinan 250100, China; Corresponding authors.Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing 100124, China; Faculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaKey Laboratory of Tea Quality and Safety Control, Ministry of Agriculture and Rural Affairs, Tea Research Institute, Chinese Academy of Agricultural Sciences, Hangzhou, ChinaAutomatic Tea Bud Detection (TBD) is a critical technology in intelligent tea-picking systems. Nevertheless, challenges, such as complex environments and the high visual similarity between tea buds and backgrounds, frequently result in false detection and missed detection, especially for small tea buds. To address these issues, in this paper, an automatic TBD method is proposed, which is built upon the YOLOv11 object detection framework, named TBD-Y. Firstly, a Synergistic Object-Spatial Attention (SOSA) mechanism is proposed, which incorporates the proposed Local Context Attention (LCA) mechanism to enhance the features in both spatial and regional dimensions. It enables the network to focus more on the tea bud regions, and suppress the interference from background noise. Secondly, a Global-local Attention Guided Feature Fusion (GAGFF) strategy is designed. It consists of two branches: one branch enhances low-resolution, high-level features containing rich global semantic information, while the other branch strengthens high-resolution features that preserve low-level visual details. The fusion of these two branches improves the representation capability of the features. The SOSA and GAGFF are integrated into the YOLOv11 framework, constructing three variants of the TBD model with different parameter scales, named TBD-Y-L, TBD-Y-M, and TBD-Y-S. Experimental results on the self-built TBD dataset and the publicly available Global Wheat Head Dataset 2021 (GWHD_2021) demonstrate that the proposed TBD-Y-L outperforms the existing methods, achieving superior detection accuracy. Furthermore, the TBD-Y-S model exhibits improved detection accuracy compared to YOLOv11-L, while maintaining lower model parameters and computational complexity.http://www.sciencedirect.com/science/article/pii/S2772375525002990Tea bud detectionYOLOv11Synergistic object-spatial attentionLocal context attentionGlobal-local attention guided feature fusion
spellingShingle Zhongyuan Liu
Li Zhuo
Chunwang Dong
Jiafeng Li
Yang Li
TBD-Y: Automatic tea bud detection with synergistic object-spatial attention and global-local attention guided feature fusion
Smart Agricultural Technology
Tea bud detection
YOLOv11
Synergistic object-spatial attention
Local context attention
Global-local attention guided feature fusion
title TBD-Y: Automatic tea bud detection with synergistic object-spatial attention and global-local attention guided feature fusion
title_full TBD-Y: Automatic tea bud detection with synergistic object-spatial attention and global-local attention guided feature fusion
title_fullStr TBD-Y: Automatic tea bud detection with synergistic object-spatial attention and global-local attention guided feature fusion
title_full_unstemmed TBD-Y: Automatic tea bud detection with synergistic object-spatial attention and global-local attention guided feature fusion
title_short TBD-Y: Automatic tea bud detection with synergistic object-spatial attention and global-local attention guided feature fusion
title_sort tbd y automatic tea bud detection with synergistic object spatial attention and global local attention guided feature fusion
topic Tea bud detection
YOLOv11
Synergistic object-spatial attention
Local context attention
Global-local attention guided feature fusion
url http://www.sciencedirect.com/science/article/pii/S2772375525002990
work_keys_str_mv AT zhongyuanliu tbdyautomaticteabuddetectionwithsynergisticobjectspatialattentionandgloballocalattentionguidedfeaturefusion
AT lizhuo tbdyautomaticteabuddetectionwithsynergisticobjectspatialattentionandgloballocalattentionguidedfeaturefusion
AT chunwangdong tbdyautomaticteabuddetectionwithsynergisticobjectspatialattentionandgloballocalattentionguidedfeaturefusion
AT jiafengli tbdyautomaticteabuddetectionwithsynergisticobjectspatialattentionandgloballocalattentionguidedfeaturefusion
AT yangli tbdyautomaticteabuddetectionwithsynergisticobjectspatialattentionandgloballocalattentionguidedfeaturefusion