RLK-YOLOv8: multi-stage detection of strawberry fruits throughout the full growth cycle in greenhouses based on large kernel convolutions and improved YOLOv8
IntroductionIn the context of intelligent strawberry cultivation, achieving multi-stage detection and yield estimation for strawberry fruits throughout their full growth cycle is essential for advancing intelligent management of greenhouse strawberries. Addressing the high rates of missed and false...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-03-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2025.1552553/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850099113386835968 |
|---|---|
| author | Lei He Lei He Lei He Dasheng Wu Dasheng Wu Dasheng Wu Xinyu Zheng Xinyu Zheng Xinyu Zheng Fengya Xu Fengya Xu Fengya Xu Shangqin Lin Shangqin Lin Shangqin Lin Siyang Wang Siyang Wang Siyang Wang Fuchuan Ni Fang Zheng |
| author_facet | Lei He Lei He Lei He Dasheng Wu Dasheng Wu Dasheng Wu Xinyu Zheng Xinyu Zheng Xinyu Zheng Fengya Xu Fengya Xu Fengya Xu Shangqin Lin Shangqin Lin Shangqin Lin Siyang Wang Siyang Wang Siyang Wang Fuchuan Ni Fang Zheng |
| author_sort | Lei He |
| collection | DOAJ |
| description | IntroductionIn the context of intelligent strawberry cultivation, achieving multi-stage detection and yield estimation for strawberry fruits throughout their full growth cycle is essential for advancing intelligent management of greenhouse strawberries. Addressing the high rates of missed and false detections in existing object detection algorithms under complex backgrounds and dense multi-target scenarios, this paper proposes an improved multi-stage detection algorithm RLK-YOLOv8 for greenhouse strawberries. The proposed algorithm, an enhancement of YOLOv8, leverages the benefits of large kernel convolutions alongside a multi-stage detection approach.MethodRLK-YOLOv8 incorporates several improvements based on the original YOLOv8 model. Firstly, it utilizes the large kernel convolution network RepLKNet as the backbone to enhance the extraction of features from targets and complex backgrounds. Secondly, RepNCSPELAN4 is introduced as the neck network to achieve bidirectional multi-scale feature fusion, thereby improving detection capability in dense target scenarios. DynamicHead is also employed to dynamically adjust the weight distribution in target detection, further enhancing the model’s accuracy in recognizing strawberries at different growth stages. Finally, PolyLoss is adopted as the loss function, which effectively improve the localization accuracy of bounding boxes and accelerating model convergence.ResultsThe experimental results indicate that RLK-YOLOv8 achieved a mAP of 95.4% in the strawberry full growth cycle detection task, with a precision and F1-score of 95.4% and 0.903, respectively. Compared to the baseline YOLOv8, the proposed algorithm demonstrates a 3.3% improvement in detection accuracy under complex backgrounds and dense multi-target scenarios.DiscussionThe RLK-YOLOv8 exhibits outstanding performance in strawberry multi-stage detection and yield estimation tasks, validating the effectiveness of integrating large kernel convolutions and multi-scale feature fusion strategies. The proposed algorithm has demonstrated significant improvements in detection performance across various environments and scenarios. |
| format | Article |
| id | doaj-art-2a8a4efec59441f599139a661d6086a3 |
| institution | DOAJ |
| issn | 1664-462X |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj-art-2a8a4efec59441f599139a661d6086a32025-08-20T02:40:33ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-03-011610.3389/fpls.2025.15525531552553RLK-YOLOv8: multi-stage detection of strawberry fruits throughout the full growth cycle in greenhouses based on large kernel convolutions and improved YOLOv8Lei He0Lei He1Lei He2Dasheng Wu3Dasheng Wu4Dasheng Wu5Xinyu Zheng6Xinyu Zheng7Xinyu Zheng8Fengya Xu9Fengya Xu10Fengya Xu11Shangqin Lin12Shangqin Lin13Shangqin Lin14Siyang Wang15Siyang Wang16Siyang Wang17Fuchuan Ni18Fang Zheng19College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaKey Laboratory of State Forestry and Grassland Administration on Forestry Sensing Technology and Intelligent Equipment, Hangzhou, ChinaKey Laboratory of Forestry Intelligent Monitoring and Information Technology of Zhejiang Province, Hangzhou, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaKey Laboratory of State Forestry and Grassland Administration on Forestry Sensing Technology and Intelligent Equipment, Hangzhou, ChinaKey Laboratory of Forestry Intelligent Monitoring and Information Technology of Zhejiang Province, Hangzhou, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaKey Laboratory of State Forestry and Grassland Administration on Forestry Sensing Technology and Intelligent Equipment, Hangzhou, ChinaKey Laboratory of Forestry Intelligent Monitoring and Information Technology of Zhejiang Province, Hangzhou, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaKey Laboratory of State Forestry and Grassland Administration on Forestry Sensing Technology and Intelligent Equipment, Hangzhou, ChinaKey Laboratory of Forestry Intelligent Monitoring and Information Technology of Zhejiang Province, Hangzhou, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaKey Laboratory of State Forestry and Grassland Administration on Forestry Sensing Technology and Intelligent Equipment, Hangzhou, ChinaKey Laboratory of Forestry Intelligent Monitoring and Information Technology of Zhejiang Province, Hangzhou, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, ChinaKey Laboratory of State Forestry and Grassland Administration on Forestry Sensing Technology and Intelligent Equipment, Hangzhou, ChinaKey Laboratory of Forestry Intelligent Monitoring and Information Technology of Zhejiang Province, Hangzhou, ChinaEngineering Research Center of Intelligent Technology for Agriculture, Ministry of Education, Wuhan, ChinaEngineering Research Center of Intelligent Technology for Agriculture, Ministry of Education, Wuhan, ChinaIntroductionIn the context of intelligent strawberry cultivation, achieving multi-stage detection and yield estimation for strawberry fruits throughout their full growth cycle is essential for advancing intelligent management of greenhouse strawberries. Addressing the high rates of missed and false detections in existing object detection algorithms under complex backgrounds and dense multi-target scenarios, this paper proposes an improved multi-stage detection algorithm RLK-YOLOv8 for greenhouse strawberries. The proposed algorithm, an enhancement of YOLOv8, leverages the benefits of large kernel convolutions alongside a multi-stage detection approach.MethodRLK-YOLOv8 incorporates several improvements based on the original YOLOv8 model. Firstly, it utilizes the large kernel convolution network RepLKNet as the backbone to enhance the extraction of features from targets and complex backgrounds. Secondly, RepNCSPELAN4 is introduced as the neck network to achieve bidirectional multi-scale feature fusion, thereby improving detection capability in dense target scenarios. DynamicHead is also employed to dynamically adjust the weight distribution in target detection, further enhancing the model’s accuracy in recognizing strawberries at different growth stages. Finally, PolyLoss is adopted as the loss function, which effectively improve the localization accuracy of bounding boxes and accelerating model convergence.ResultsThe experimental results indicate that RLK-YOLOv8 achieved a mAP of 95.4% in the strawberry full growth cycle detection task, with a precision and F1-score of 95.4% and 0.903, respectively. Compared to the baseline YOLOv8, the proposed algorithm demonstrates a 3.3% improvement in detection accuracy under complex backgrounds and dense multi-target scenarios.DiscussionThe RLK-YOLOv8 exhibits outstanding performance in strawberry multi-stage detection and yield estimation tasks, validating the effectiveness of integrating large kernel convolutions and multi-scale feature fusion strategies. The proposed algorithm has demonstrated significant improvements in detection performance across various environments and scenarios.https://www.frontiersin.org/articles/10.3389/fpls.2025.1552553/fullYOLOv8RepLKNetRepNCSPELAN4DynamicHeadPolyLossfull growth cycle of strawberry fruits |
| spellingShingle | Lei He Lei He Lei He Dasheng Wu Dasheng Wu Dasheng Wu Xinyu Zheng Xinyu Zheng Xinyu Zheng Fengya Xu Fengya Xu Fengya Xu Shangqin Lin Shangqin Lin Shangqin Lin Siyang Wang Siyang Wang Siyang Wang Fuchuan Ni Fang Zheng RLK-YOLOv8: multi-stage detection of strawberry fruits throughout the full growth cycle in greenhouses based on large kernel convolutions and improved YOLOv8 Frontiers in Plant Science YOLOv8 RepLKNet RepNCSPELAN4 DynamicHead PolyLoss full growth cycle of strawberry fruits |
| title | RLK-YOLOv8: multi-stage detection of strawberry fruits throughout the full growth cycle in greenhouses based on large kernel convolutions and improved YOLOv8 |
| title_full | RLK-YOLOv8: multi-stage detection of strawberry fruits throughout the full growth cycle in greenhouses based on large kernel convolutions and improved YOLOv8 |
| title_fullStr | RLK-YOLOv8: multi-stage detection of strawberry fruits throughout the full growth cycle in greenhouses based on large kernel convolutions and improved YOLOv8 |
| title_full_unstemmed | RLK-YOLOv8: multi-stage detection of strawberry fruits throughout the full growth cycle in greenhouses based on large kernel convolutions and improved YOLOv8 |
| title_short | RLK-YOLOv8: multi-stage detection of strawberry fruits throughout the full growth cycle in greenhouses based on large kernel convolutions and improved YOLOv8 |
| title_sort | rlk yolov8 multi stage detection of strawberry fruits throughout the full growth cycle in greenhouses based on large kernel convolutions and improved yolov8 |
| topic | YOLOv8 RepLKNet RepNCSPELAN4 DynamicHead PolyLoss full growth cycle of strawberry fruits |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2025.1552553/full |
| work_keys_str_mv | AT leihe rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT leihe rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT leihe rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT dashengwu rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT dashengwu rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT dashengwu rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT xinyuzheng rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT xinyuzheng rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT xinyuzheng rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT fengyaxu rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT fengyaxu rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT fengyaxu rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT shangqinlin rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT shangqinlin rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT shangqinlin rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT siyangwang rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT siyangwang rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT siyangwang rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT fuchuanni rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 AT fangzheng rlkyolov8multistagedetectionofstrawberryfruitsthroughoutthefullgrowthcycleingreenhousesbasedonlargekernelconvolutionsandimprovedyolov8 |