Fruits hidden by green: an improved YOLOV8n for detection of young citrus in lush citrus trees
In order to address the challenges of inefficiency and insufficient accuracy in the manual identification of young citrus fruits during thinning processes, this study proposes a detection methodology using the you only look once for complex backgrounds of young citrus fruits (YCCB-YOLO) approach. Th...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-04-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2024.1375118/full |
| _version_ | 1827288750233747456 |
|---|---|
| author | Gao Ang Gao Ang Tian Zhiwei Ma Wei Song Yuepeng Ren Longlong Feng Yuliang Qian Jianping Xu Lijia |
| author_facet | Gao Ang Gao Ang Tian Zhiwei Ma Wei Song Yuepeng Ren Longlong Feng Yuliang Qian Jianping Xu Lijia |
| author_sort | Gao Ang |
| collection | DOAJ |
| description | In order to address the challenges of inefficiency and insufficient accuracy in the manual identification of young citrus fruits during thinning processes, this study proposes a detection methodology using the you only look once for complex backgrounds of young citrus fruits (YCCB-YOLO) approach. The method first constructs a dataset containing images of young citrus fruits in a real orchard environment. To improve the detection accuracy while maintaining the computational efficiency, the study reconstructs the detection head and backbone network using pointwise convolution (PWonv) lightweight network, which reduces the complexity of the model without affecting the performance. In addition, the ability of the model to accurately detect young citrus fruits in complex backgrounds is enhanced by integrating the fusion attention mechanism. Meanwhile, the simplified spatial pyramid pooling fast-large kernel separated attention (SimSPPF-LSKA) feature pyramid was introduced to further enhance the multi-feature extraction capability of the model. Finally, the Adam optimization function was used to strengthen the nonlinear representation and feature extraction ability of the model. The experimental results show that the model achieves 91.79% precision (P), 92.75% recall (R), and 97.32% mean average precision (mAP)on the test set, which were improved by 1.33%, 2.24%, and 1.73%, respectively, compared with the original model, and the size of the model is only 5.4 MB. This study could meet the performance requirements for citrus fruit identification, which provides technical support for fruit thinning. |
| first_indexed | 2024-04-24T11:35:56Z |
| format | Article |
| id | doaj.art-1ab990242f1648619972ec5d22e1195e |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-04-24T11:35:56Z |
| publishDate | 2024-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-1ab990242f1648619972ec5d22e1195e2024-04-10T05:05:03ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2024-04-011510.3389/fpls.2024.13751181375118Fruits hidden by green: an improved YOLOV8n for detection of young citrus in lush citrus treesGao Ang0Gao Ang1Tian Zhiwei2Ma Wei3Song Yuepeng4Ren Longlong5Feng Yuliang6Qian Jianping7Xu Lijia8College of Mechanical and Electronic Engineering, Shandong Agricultural University, Tai’an, Shandong, ChinaInstitute of Urban Agriculture, Chinese Academy of Agricultural Sciences, Chengdu, ChinaInstitute of Urban Agriculture, Chinese Academy of Agricultural Sciences, Chengdu, ChinaInstitute of Urban Agriculture, Chinese Academy of Agricultural Sciences, Chengdu, ChinaCollege of Mechanical and Electronic Engineering, Shandong Agricultural University, Tai’an, Shandong, ChinaCollege of Mechanical and Electronic Engineering, Shandong Agricultural University, Tai’an, Shandong, ChinaCollege of Engineering, China Agricultural University, Beijing, ChinaInstitute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing, ChinaCollege of Mechanical and Electrical Engineering, Sichuan Agriculture University, Ya’an, ChinaIn order to address the challenges of inefficiency and insufficient accuracy in the manual identification of young citrus fruits during thinning processes, this study proposes a detection methodology using the you only look once for complex backgrounds of young citrus fruits (YCCB-YOLO) approach. The method first constructs a dataset containing images of young citrus fruits in a real orchard environment. To improve the detection accuracy while maintaining the computational efficiency, the study reconstructs the detection head and backbone network using pointwise convolution (PWonv) lightweight network, which reduces the complexity of the model without affecting the performance. In addition, the ability of the model to accurately detect young citrus fruits in complex backgrounds is enhanced by integrating the fusion attention mechanism. Meanwhile, the simplified spatial pyramid pooling fast-large kernel separated attention (SimSPPF-LSKA) feature pyramid was introduced to further enhance the multi-feature extraction capability of the model. Finally, the Adam optimization function was used to strengthen the nonlinear representation and feature extraction ability of the model. The experimental results show that the model achieves 91.79% precision (P), 92.75% recall (R), and 97.32% mean average precision (mAP)on the test set, which were improved by 1.33%, 2.24%, and 1.73%, respectively, compared with the original model, and the size of the model is only 5.4 MB. This study could meet the performance requirements for citrus fruit identification, which provides technical support for fruit thinning.https://www.frontiersin.org/articles/10.3389/fpls.2024.1375118/fullYOLO V8young citrus fruitdeep learningtarget detectionlightweight network |
| spellingShingle | Gao Ang Gao Ang Tian Zhiwei Ma Wei Song Yuepeng Ren Longlong Feng Yuliang Qian Jianping Xu Lijia Fruits hidden by green: an improved YOLOV8n for detection of young citrus in lush citrus trees Frontiers in Plant Science YOLO V8 young citrus fruit deep learning target detection lightweight network |
| title | Fruits hidden by green: an improved YOLOV8n for detection of young citrus in lush citrus trees |
| title_full | Fruits hidden by green: an improved YOLOV8n for detection of young citrus in lush citrus trees |
| title_fullStr | Fruits hidden by green: an improved YOLOV8n for detection of young citrus in lush citrus trees |
| title_full_unstemmed | Fruits hidden by green: an improved YOLOV8n for detection of young citrus in lush citrus trees |
| title_short | Fruits hidden by green: an improved YOLOV8n for detection of young citrus in lush citrus trees |
| title_sort | fruits hidden by green an improved yolov8n for detection of young citrus in lush citrus trees |
| topic | YOLO V8 young citrus fruit deep learning target detection lightweight network |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2024.1375118/full |
| work_keys_str_mv | AT gaoang fruitshiddenbygreenanimprovedyolov8nfordetectionofyoungcitrusinlushcitrustrees AT gaoang fruitshiddenbygreenanimprovedyolov8nfordetectionofyoungcitrusinlushcitrustrees AT tianzhiwei fruitshiddenbygreenanimprovedyolov8nfordetectionofyoungcitrusinlushcitrustrees AT mawei fruitshiddenbygreenanimprovedyolov8nfordetectionofyoungcitrusinlushcitrustrees AT songyuepeng fruitshiddenbygreenanimprovedyolov8nfordetectionofyoungcitrusinlushcitrustrees AT renlonglong fruitshiddenbygreenanimprovedyolov8nfordetectionofyoungcitrusinlushcitrustrees AT fengyuliang fruitshiddenbygreenanimprovedyolov8nfordetectionofyoungcitrusinlushcitrustrees AT qianjianping fruitshiddenbygreenanimprovedyolov8nfordetectionofyoungcitrusinlushcitrustrees AT xulijia fruitshiddenbygreenanimprovedyolov8nfordetectionofyoungcitrusinlushcitrustrees |