YOLOv5-ASFF: A Multistage Strawberry Detection Algorithm Based on Improved YOLOv5

被引:18
作者
Li, Yaodi [1 ]
Xue, Jianxin [1 ]
Zhang, Mingyue [1 ]
Yin, Junyi [1 ]
Liu, Yang [1 ]
Qiao, Xindan [1 ]
Zheng, Decong [1 ]
Li, Zezhen [2 ]
机构
[1] Shanxi Agr Univ, Coll Agr Engn, Jinzhong 030801, Peoples R China
[2] Shanxi Agr Univ, Coll Food Sci & Engn, Jinzhong 030801, Peoples R China
来源
AGRONOMY-BASEL | 2023年 / 13卷 / 07期
基金
中国国家自然科学基金;
关键词
strawberry; YOLOv5; intelligent monitoring; automatic picking;
D O I
10.3390/agronomy13071901
中图分类号
S3 [农学(农艺学)];
学科分类号
0901 ;
摘要
The smart farm is currently a hot topic in the agricultural industry. Due to the complex field environment, the intelligent monitoring model applicable to this environment requires high hardware performance, and there are difficulties in realizing real-time detection of ripe strawberries on a small automatic picking robot, etc. This research proposes a real-time multistage strawberry detection algorithm YOLOv5-ASFF based on improved YOLOv5. Through the introduction of the ASFF (adaptive spatial feature fusion) module into YOLOv5, the network can adaptively learn the fused spatial weights of strawberry feature maps at each scale as a way to fully obtain the image feature information of strawberries. To verify the superiority and availability of YOLOv5-ASFF, a strawberry dataset containing a variety of complex scenarios, including leaf shading, overlapping fruit, and dense fruit, was constructed in this experiment. The method achieved 91.86% and 88.03% for mAP and F1, respectively, and 98.77% for AP of mature-stage strawberries, showing strong robustness and generalization ability, better than SSD, YOLOv3, YOLOv4, and YOLOv5s. The YOLOv5-ASFF algorithm can overcome the influence of complex field environments and improve the detection of strawberries under dense distribution and shading conditions, and the method can provide technical support for monitoring yield estimation and harvest planning in intelligent strawberry field management.
引用
收藏
页数:15
相关论文
共 36 条
[1]   Antioxidant and anticancer properties of berries [J].
Baby, Bincy ;
Antony, Priya ;
Vijayan, Ranjit .
CRITICAL REVIEWS IN FOOD SCIENCE AND NUTRITION, 2018, 58 (15) :2491-2507
[2]  
Bochkovskiy A, 2020, Arxiv, DOI arXiv:2004.10934
[3]   Lightweight Detection Network for Arbitrary-Oriented Vehicles in UAV Imagery via Global Attentive Relation and Multi-Path Fusion [J].
Feng, Jiangfan ;
Yi, Chengjie .
DRONES, 2022, 6 (05)
[4]   Fast and accurate detection of kiwifruit in orchard using improved YOLOv3-tiny model [J].
Fu, Longsheng ;
Feng, Yali ;
Wu, Jingzhu ;
Liu, Zhihao ;
Gao, Fangfang ;
Majeed, Yaqoob ;
Al-Mallahi, Ahmad ;
Zhang, Qin ;
Li, Rui ;
Cui, Yongjie .
PRECISION AGRICULTURE, 2021, 22 (03) :754-776
[5]   A Dynamic Detection Method for Phenotyping Pods in a Soybean Population Based on an Improved YOLO-v5 Network [J].
Fu, Xiaoming ;
Li, Aokang ;
Meng, Zhijun ;
Yin, Xiaohui ;
Zhang, Chi ;
Zhang, Wei ;
Qi, Liqiang .
AGRONOMY-BASEL, 2022, 12 (12)
[6]  
[郭希岳 Guo Xiyue], 2022, [农业工程学报, Transactions of the Chinese Society of Agricultural Engineering], V38, P186
[7]   GCS-YOLOV4-Tiny: A lightweight group convolution network for multi-stage fruit detection [J].
Huang, Mei-Ling ;
Wu, Yi-Shan .
MATHEMATICAL BIOSCIENCES AND ENGINEERING, 2023, 20 (01) :241-268
[8]   Fusion of the YOLOv4 network model and visual attention mechanism to detect low-quality young apples in a complex environment [J].
Jiang, Mei ;
Song, Lei ;
Wang, Yunfei ;
Li, Zhenyu ;
Song, Huaibo .
PRECISION AGRICULTURE, 2022, 23 (02) :559-577
[9]   Deep learning in agriculture: A survey [J].
Kamilaris, Andreas ;
Prenafeta-Boldu, Francesc X. .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2018, 147 :70-90
[10]   Deep learning for real-time fruit detection and orchard fruit load estimation: benchmarking of 'MangoYOLO' [J].
Koirala, A. ;
Walsh, K. B. ;
Wang, Z. ;
McCarthy, C. .
PRECISION AGRICULTURE, 2019, 20 (06) :1107-1135