ORIGINAL RESEARCH article
Front. Plant Sci.
Sec. Plant Bioinformatics
Volume 16 - 2025 | doi: 10.3389/fpls.2025.1579335
WCS-YOLOv8s: improved YOLOv8s model for target identification and localisation throughout the strawberry growth process
Provisionally accepted
- 1Qingdao University of Technology, Qingdao, China
- 2Henan Agricultural University, Zhengzhou, Henan Province, China
- 3Huazhong Agricultural University, Wuhan, Hubei Province, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
To enhance the quality and yield of strawberries, it is essential to effectively supervise the entire growing process. Currently, the monitoring of strawberry growth primarily relies on manual identification and positioning methods. This approach presents several challenges, including low efficiency, high labor intensity, time consumption, elevated costs, and a lack of standardized monitoring protocols. On the basis of this, there was an urgent need in the market to automate the whole process of target recognition and localisation in strawberry. Aiming at the above problems, based on the YOLOv8s benchmark model, this paper innovatively constructed a model for target recognition and localisation of strawberries-WCS-YOLOv8s model. In this paper, the whole growth process of strawberry was divided into four stages, namely: bud stage, flower stage, fruit under-ripening stage and fruit ripening stage, and a total of 1957 images of these four stages were captured with a binocular depth camera. Using the constructed WCS-YOLOv8s model to process the images, the target recognition and localisation of the whole growth process of strawberry was accomplished. This model proposes a data enhancement strategy based on the Warmup learning rate to stabilize the initial training process. The self-developed SE-MSDWA module is integrated into the backbone network to improve the model's feature extraction capability while suppressing redundant information, thereby achieving efficient feature extraction.Additionally, the neck network is enhanced by incorporating the CGFM module, which employs a multihead self-attention mechanism to fuse diverse feature information and improve the network's feature fusion performance. The model's Precision(P), Recall(R),
Keywords: strawberry, deep learning, target recognition and localisation, WCS-YOLOv8s model, binocular vision
Received: 13 Mar 2025; Accepted: 06 Jun 2025.
Copyright: © 2025 Gao, Cui and Wang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Sheng Gao, Qingdao University of Technology, Qingdao, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.