A Lightweight Citrus Object Detection Method in Complex Environments
Aiming at the limitations of current citrus detection methods in complex orchard environments, especially the problems of poor model adaptability and high computational complexity under different lighting, multiple occlusions, and dense fruit conditions, this study proposes an improved citrus detect...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/10/1046 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849327673591988224 |
|---|---|
| author | Qiurong Lv Fuchun Sun Yuechao Bian Haorong Wu Xiaoxiao Li Xin Li Jie Zhou |
| author_facet | Qiurong Lv Fuchun Sun Yuechao Bian Haorong Wu Xiaoxiao Li Xin Li Jie Zhou |
| author_sort | Qiurong Lv |
| collection | DOAJ |
| description | Aiming at the limitations of current citrus detection methods in complex orchard environments, especially the problems of poor model adaptability and high computational complexity under different lighting, multiple occlusions, and dense fruit conditions, this study proposes an improved citrus detection model, YOLO-PBGM, based on You Only Look Once v7 (YOLOv7). First, to tackle the large size of the YOLOv7 network model and its deployment challenges, the PC-ELAN module is constructed by introducing Partial Convolution (PConv) for lightweight improvement, which reduces the model’s demand for computing resources and parameters. At the same time, the Bi-Former attention module is embedded to enhance the perception and processing of citrus fruit information. Secondly, a lightweight neck network is constructed using Grouped Shuffle Convolution (GSConv) to simplify computational complexity. Finally, the minimum-point-distance-based IoU (MPDIoU) loss function is utilized to optimize the boundary return mechanism, which speeds up model convergence and reduces the redundancy of bounding box regression. Experimental results indicate that for the citrus dataset collected in a natural environment, the improved model reduces Params and GFLOPs by 15.4% and 23.7%, respectively, while improving precision, recall, and mAP by 0.3%, 4%, and 3.5%, respectively, thereby outperforming other detection networks. Additionally, an analysis of citrus object detection under varying lighting and occlusion conditions reveals that the YOLO-PBGM network model demonstrates good adaptability, effectively coping with variations in lighting and occlusions while exhibiting high robustness. This model can provide a technical reference for uncrewed intelligent picking of citrus. |
| format | Article |
| id | doaj-art-e22eb86ed5044432bd1bc2d5947f685c |
| institution | Kabale University |
| issn | 2077-0472 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-e22eb86ed5044432bd1bc2d5947f685c2025-08-20T03:47:48ZengMDPI AGAgriculture2077-04722025-05-011510104610.3390/agriculture15101046A Lightweight Citrus Object Detection Method in Complex EnvironmentsQiurong Lv0Fuchun Sun1Yuechao Bian2Haorong Wu3Xiaoxiao Li4Xin Li5Jie Zhou6School of Mechanical Engineering, Chengdu University, Chengdu 610106, ChinaSchool of Mechanical Engineering, Chengdu University, Chengdu 610106, ChinaSchool of Mechanical Engineering, Chengdu University, Chengdu 610106, ChinaSchool of Electronic Information and Electrical Engineering, Chengdu University, Chengdu 610106, ChinaSchool of Mechanical Engineering, Chengdu University, Chengdu 610106, ChinaShengzhong Water Conservancy Project Operation and Management Center of Sichuan Province, Nanchong 623300, ChinaSchool of Mechanical Engineering, Chengdu University, Chengdu 610106, ChinaAiming at the limitations of current citrus detection methods in complex orchard environments, especially the problems of poor model adaptability and high computational complexity under different lighting, multiple occlusions, and dense fruit conditions, this study proposes an improved citrus detection model, YOLO-PBGM, based on You Only Look Once v7 (YOLOv7). First, to tackle the large size of the YOLOv7 network model and its deployment challenges, the PC-ELAN module is constructed by introducing Partial Convolution (PConv) for lightweight improvement, which reduces the model’s demand for computing resources and parameters. At the same time, the Bi-Former attention module is embedded to enhance the perception and processing of citrus fruit information. Secondly, a lightweight neck network is constructed using Grouped Shuffle Convolution (GSConv) to simplify computational complexity. Finally, the minimum-point-distance-based IoU (MPDIoU) loss function is utilized to optimize the boundary return mechanism, which speeds up model convergence and reduces the redundancy of bounding box regression. Experimental results indicate that for the citrus dataset collected in a natural environment, the improved model reduces Params and GFLOPs by 15.4% and 23.7%, respectively, while improving precision, recall, and mAP by 0.3%, 4%, and 3.5%, respectively, thereby outperforming other detection networks. Additionally, an analysis of citrus object detection under varying lighting and occlusion conditions reveals that the YOLO-PBGM network model demonstrates good adaptability, effectively coping with variations in lighting and occlusions while exhibiting high robustness. This model can provide a technical reference for uncrewed intelligent picking of citrus.https://www.mdpi.com/2077-0472/15/10/1046citrusattention mechanismmachine visionYOLOv7deep learning |
| spellingShingle | Qiurong Lv Fuchun Sun Yuechao Bian Haorong Wu Xiaoxiao Li Xin Li Jie Zhou A Lightweight Citrus Object Detection Method in Complex Environments Agriculture citrus attention mechanism machine vision YOLOv7 deep learning |
| title | A Lightweight Citrus Object Detection Method in Complex Environments |
| title_full | A Lightweight Citrus Object Detection Method in Complex Environments |
| title_fullStr | A Lightweight Citrus Object Detection Method in Complex Environments |
| title_full_unstemmed | A Lightweight Citrus Object Detection Method in Complex Environments |
| title_short | A Lightweight Citrus Object Detection Method in Complex Environments |
| title_sort | lightweight citrus object detection method in complex environments |
| topic | citrus attention mechanism machine vision YOLOv7 deep learning |
| url | https://www.mdpi.com/2077-0472/15/10/1046 |
| work_keys_str_mv | AT qiuronglv alightweightcitrusobjectdetectionmethodincomplexenvironments AT fuchunsun alightweightcitrusobjectdetectionmethodincomplexenvironments AT yuechaobian alightweightcitrusobjectdetectionmethodincomplexenvironments AT haorongwu alightweightcitrusobjectdetectionmethodincomplexenvironments AT xiaoxiaoli alightweightcitrusobjectdetectionmethodincomplexenvironments AT xinli alightweightcitrusobjectdetectionmethodincomplexenvironments AT jiezhou alightweightcitrusobjectdetectionmethodincomplexenvironments AT qiuronglv lightweightcitrusobjectdetectionmethodincomplexenvironments AT fuchunsun lightweightcitrusobjectdetectionmethodincomplexenvironments AT yuechaobian lightweightcitrusobjectdetectionmethodincomplexenvironments AT haorongwu lightweightcitrusobjectdetectionmethodincomplexenvironments AT xiaoxiaoli lightweightcitrusobjectdetectionmethodincomplexenvironments AT xinli lightweightcitrusobjectdetectionmethodincomplexenvironments AT jiezhou lightweightcitrusobjectdetectionmethodincomplexenvironments |