Dense strawberry maturity recognition neural network based on multichannel attention mechanism
Keywords:
Object detection, Feature fusion, Maturity testing, Deep learningAbstract
Color is an important indicator of strawberry maturity; therefore, identifying color changes during harvesting and delivery is important. The soft skin of strawberries can easily cause mechanical damage during harvesting and manual selection. While scholars have made significant progress in using machine vision technology for crop detection, detecting strawberries that are densely placed, differently sized, and in different growth states remains challenging. This study proposes a YOLOv8s-based dense strawberry maturity recognition convolutional neural network that integrates multiscale feature attention. The proposed model addresses several issues, including the overlapping of adjacent fruit features, fuzzy maturity criteria, and difficulty distinguishing individual fruits when they are densely placed. It utilizes a multichannel attention mechanism to fuse semantic features of strawberries at different scales, enhancing the independent summarization ability of image information of individual strawberries in dense and randomly placed environments. It also introduces wavelet down sampling convolution as the backbone of network layers to enhance the ability to capture detailed features of small strawberries. Furthermore, with the integration of the weighted intersection over union loss function, it optimizes the convergence effect and inference accuracy of network training. On a custom strawberry dataset, model accuracy, recall rate, mAP@0.5, and mAP@0.5:0.95 increased by 1.1%, 1.8%, 1.2%, and 0.8%, respectively, compared to the original YOLOv8s model, showing good recognition accuracy and stability when facing dense strawberry arrays with multiple sizes and arbitrary placement. The proposed model can quickly detect the maturity of individual strawberry fruits in random environments, improve sorting efficiency, and reduce post-harvest losses. This study provides new ideas and technical references for the application of machine vision technology in the field of dense crop maturity recognition.
Keywords: object detection, feature fusion, maturity testing, deep learning
DOI: 10.25165/j.ijabe.20261901.9931
Citation: Cao Z R, Wang C W, Xin X J, Chen X Y, Cai J H. Dense strawberry maturity recognition neural network based on multichannel attention mechanism. Int J Agric & Biol Eng, 2026; 19(1): 295–301.
References
[1] Xu C, Zhang X Y, Liang J, Fu Y J, Wang J, Jiang M, et al. Cell wall and reactive oxygen metabolism responses of strawberry fruit during storage to low voltage electrostatic field treatment. Postharvest Biol Technol, 2022; 192: 112017.
[2] Zhang Y T, Li S L, Deng M Y, Gui R, Liu Y Q, Chen X P, et al. Blue light combined with salicylic acid treatment maintained the postharvest quality of strawberry fruit during refrigerated storage. Food Chem X, 2022; 15: 100384.
[3] Wang L, Luo Z S, Yang M Y, Liang Z, Qi M, Dong Y Y, et al. The action of RED light: Specific elevation of pelargonidin-based anthocyanin through ABA-related pathway in strawberry. Postharvest Biol Technol, 2022; 186: 111835.
[4] De Preter A, Anthonis J, De Baerdemaeker J. Development of a robot for harvesting strawberries. IFAC-PapersOnLine, 2018; 51（17）: 14–19.
[5] Wang C L, Wang H M, Han Q Y, Zhang Z G, Kong D D, Zou X J. Strawberry detection and ripeness classification using YOLOv8+ model and image processing method. Agriculture, 2024; 14（5）: 751.
[6] Yamamoto S, Hayashi S, Saito S, Ochiai Y, Yamashita T, Sugano S. Development of robotic strawberry harvester to approach target fruit from hanging bench side. IFAC Proceedings Volumes, 2010; 43（26）: 95–100.
[7] Yu Y, Zhang K L, Liu H, Yang L, Zhang D X. Real-time visual localization of the picking points for a ridge-planting strawberry harvesting robot. IEEE Access, 2020; 8: 116556–116568.
[8] Yu Y, Zhang K L, Yang L, Zhang D X. Fruit detection for strawberry harvesting robot in non-structural environment based on Mask-RCNN. Comput Electron Agric, 2019; 163: 104846.
[9] Zhao Y S, Liang G, Huang Y X, Liu C L. A review of key techniques of vision-based control for harvesting robot. Comput Electron Agric, 2016; 127: 311–323.
[10] An Q L, Wang K, Li Z Y, Song C Y, Tang X Y, Song J. Real-time monitoring method of strawberry fruit growth state based on YOLO improved model. IEEE Access, 2022; 10: 124363–124372.
[11] Du X Q, Cheng H C, Ma Z H, Lu W W, Wang M X, Meng Z C, et al. DSW-YOLO: A detection method for ground-planted strawberry fruits under different occlusion levels. Comput Electron Agric, 2023; 214: 108304.
[12] Wang Y, Yan G, Meng Q L, Yao T, Han J F, Zhang B. DSE-YOLO: Detail semantics enhancement YOLO for multi-stage strawberry detection. Comput Electron Agric, 2022; 198: 107057.
[13] Shen S, Duan F M, Tian Z W, Han C X. A novel deep learning method for detecting strawberry fruit. Applied Sciences, 2024; 14: 4213.
[14] He Y L, Peng Y F, Wei C Y, Zheng Y D, Yang C C, Zou T Y. Automatic disease detection from strawberry leaf based on improved YOLOv8. Plants, 2024; 13: 2556.
[15] Li C L, Wu H N, Zhang T, Lu J H, Li J H. Lightweight network of multi-stage strawberry detection based on improved YOLOv7-Tiny. Agriculture, 2024; 14: 1132.
[16] Li Y H, Zhang M Y, Zhang C Y, Liang H, Li P, Zhang W W. YOLO-CCS: Vehicle detection algorithm based on coordinate attention mechanism. Digital Signal Processing: A Review Journal, 2024; 153: 104632.
[17] Shan W, Yue Y R. Apple defect detection in complex environments. Electronics, 2024; 13: 4844.
[18] Xiao L S, Li W Z, Yao S, Liu H T, Ren D H. High-precision and lightweight small-target detection algorithm for low-cost edge intelligence. Sci Rep, 2024; 14: 23542.
[19] Chen J J, Zhu J N, Li Z, Yang X B. YOLOv7-WFD a novel convolutional neural network model for helmet detection in high-risk workplaces. IEEE Access, 2023; 11: 113580–113592.
[20] Huang X H, Zhu J H, Huo Y. SSA-YOLO: An improved YOLO for hot-rolled strip steel surface defect detection. IEEE Trans Instrum Meas, 2024; 73: 5040017.
[21] Gao W W, Zong C L, Wang M Y, Zhang H F, Fang Y. Intelligent identification of rice leaf disease based on YOLO V5-EFFICIENT. Crop Protection, 2024; 183: 106758.
[22] Hu X Y, Kong D F, Liu X Y, Zhang J W, Zhang D D. FM-STDNet: High-speed detector for fast-moving small targets based on deep first-order network architecture. Electronics, 2023; 12: 1829.
[23] Wang Q H, Liu Y K, Zheng Q, Tao R, Liu Y. SMC-YOLO: A high-precision maize insect pest-detection method. Agronomy, 2025; 15: 195.
[24] Cao X M, Zhong P, Huang Y H, Huang M T, Huang Z Y, Zou T L, et al. Research on lightweight algorithm model for precise recognition and detection of outdoor strawberries based on improved YOLOv5n. Agriculture, 2025; 15（1）: 90.
[25] Chen S L, Liao Y H, Lin F, Huang B. An improved lightweight YOLOv5 algorithm for detecting strawberry diseases. IEEE Access, 2023; 11: 54080–54092.
[26] Weng S Z, Yu S, Guo B Q, Tang P P, Liang D. Non-destructive detection of strawberry quality using multi-features of hyperspectral imaging and multivariate methods. Sensors, 2020; 20: 3074.
[27] Guo R Q, Ji P Y, Zhang Y P, Hu J Q, Liu W L, Li X J, et al. Steel surface defect detection based on improved GCHS-YOLO algorithm. IEEE Access, 2024; 12: 190865–190875.
[28] Su Y, Tan W X, Dong Y F, Xu W, Huang P P, Zhang J X, Zhang D K. Enhancing concealed object detection in active millimeter wave images using wavelet transform. Signal Processing, 2024; 216: 109303.
[29] Xu G P, Liao W T, Zhang X, Li C, He X W, Wu X L. Haar wavelet downsampling: A simple but effective downsampling module for semantic segmentation. Pattern Recognition, 2023; 143: 109819.
[30] Wu H T, Mo X T, Wen S J, Wu K L, Ye Y, Wang Y M, et al. DNE-YOLO: A method for apple fruit detection in diverse natural environments. Journal of King Saud University- Computer and Information Sciences, 2024; 36: 102220.
[31] Xiang S, Wang S Y, Xu M, Wang W Y, Liu W G. YOLO POD: A fast and accurate multi-task model for dense soybean pod counting. Plant Methods, 2023; 19: 8.
[32] Zhao S Y, Liu J Z, Wu S. Multiple disease detection method for greenhouse-cultivated strawberry based on multiscale feature fusion Faster R_CNN. Comput Electron Agric, 2022; 199: 107176.
[33] Lu M, Sheng W Q, Zou Y, Chen Y T, Chen Z G. WSS-YOLO: An improved industrial defect detection network for steel surface defects. Measurement, 2024; 236: 115060.
[34] Malik M H, Zhang T, Li H, Zhang M, Shabbir S, Saeed A. Mature tomato fruit detection algorithm based on improved HSV and watershed algorithm. IFAC-PapersOnLine, 2018; 51（17）: 431–436.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Agricultural and Biological Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
IJABE is an international peer reviewed, open access journal, adopting Creative Commons Copyright Notices as follows.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
