GLS-YOLO: A Lightweight Tea Bud Detection Model in Complex Scenarios
The efficiency of tea bud harvesting has been greatly enhanced, and human labor intensity significantly reduced, through the mechanization and intelligent management of tea plantations. A key challenge for harvesting machinery is ensuring both the freshness of tea buds and the integrity of the tea p...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/14/12/2939 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850036662826958848 |
|---|---|
| author | Shanshan Li Zhe Zhang Shijun Li |
| author_facet | Shanshan Li Zhe Zhang Shijun Li |
| author_sort | Shanshan Li |
| collection | DOAJ |
| description | The efficiency of tea bud harvesting has been greatly enhanced, and human labor intensity significantly reduced, through the mechanization and intelligent management of tea plantations. A key challenge for harvesting machinery is ensuring both the freshness of tea buds and the integrity of the tea plants. However, achieving precise harvesting requires complex computational models, which can limit practical deployment. To address the demand for high-precision yet lightweight tea bud detection, this study proposes the GLS-YOLO detection model, based on YOLOv8. The model leverages GhostNetV2 as its backbone network, replacing standard convolutions with depthwise separable convolutions, resulting in substantial reductions in computational load and memory consumption. Additionally, the C2f-LC module is integrated into the improved model, combining cross-covariance fusion with a lightweight contextual attention mechanism to enhance feature recognition and extraction quality. To tackle the challenges posed by varying poses and occlusions of tea buds, Shape-IoU was employed as the loss function to improve the scoring of similarly shaped objects, reducing false positives and false negatives while improving the detection of non-rectangular or irregularly shaped objects. Experimental results demonstrate the model’s superior performance, achieving an AP@0.5 of 90.55%. Compared to the original YOLOv8, the model size was reduced by 38.85%, and the number of parameters decreased by 39.95%. This study presents innovative advances in agricultural robotics by significantly improving the accuracy and efficiency of tea bud harvesting, simplifying the configuration process for harvesting systems, and effectively lowering the technological barriers for real-world applications. |
| format | Article |
| id | doaj-art-0c849c9064cb49e7ab48cf464a58fa8c |
| institution | DOAJ |
| issn | 2073-4395 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj-art-0c849c9064cb49e7ab48cf464a58fa8c2025-08-20T02:57:05ZengMDPI AGAgronomy2073-43952024-12-011412293910.3390/agronomy14122939GLS-YOLO: A Lightweight Tea Bud Detection Model in Complex ScenariosShanshan Li0Zhe Zhang1Shijun Li2Institute for the Smart Agriculture, Jilin Agricultural University, Changchun 130118, ChinaInstitute for the Smart Agriculture, Jilin Agricultural University, Changchun 130118, ChinaSchool of Electronics and Information Engineering, Wuzhou University, Wuzhou 543002, ChinaThe efficiency of tea bud harvesting has been greatly enhanced, and human labor intensity significantly reduced, through the mechanization and intelligent management of tea plantations. A key challenge for harvesting machinery is ensuring both the freshness of tea buds and the integrity of the tea plants. However, achieving precise harvesting requires complex computational models, which can limit practical deployment. To address the demand for high-precision yet lightweight tea bud detection, this study proposes the GLS-YOLO detection model, based on YOLOv8. The model leverages GhostNetV2 as its backbone network, replacing standard convolutions with depthwise separable convolutions, resulting in substantial reductions in computational load and memory consumption. Additionally, the C2f-LC module is integrated into the improved model, combining cross-covariance fusion with a lightweight contextual attention mechanism to enhance feature recognition and extraction quality. To tackle the challenges posed by varying poses and occlusions of tea buds, Shape-IoU was employed as the loss function to improve the scoring of similarly shaped objects, reducing false positives and false negatives while improving the detection of non-rectangular or irregularly shaped objects. Experimental results demonstrate the model’s superior performance, achieving an AP@0.5 of 90.55%. Compared to the original YOLOv8, the model size was reduced by 38.85%, and the number of parameters decreased by 39.95%. This study presents innovative advances in agricultural robotics by significantly improving the accuracy and efficiency of tea bud harvesting, simplifying the configuration process for harvesting systems, and effectively lowering the technological barriers for real-world applications.https://www.mdpi.com/2073-4395/14/12/2939tea bud pickingtea bud target detectioncomputer visiondeep neural networkYOLOv8smart agriculture |
| spellingShingle | Shanshan Li Zhe Zhang Shijun Li GLS-YOLO: A Lightweight Tea Bud Detection Model in Complex Scenarios Agronomy tea bud picking tea bud target detection computer vision deep neural network YOLOv8 smart agriculture |
| title | GLS-YOLO: A Lightweight Tea Bud Detection Model in Complex Scenarios |
| title_full | GLS-YOLO: A Lightweight Tea Bud Detection Model in Complex Scenarios |
| title_fullStr | GLS-YOLO: A Lightweight Tea Bud Detection Model in Complex Scenarios |
| title_full_unstemmed | GLS-YOLO: A Lightweight Tea Bud Detection Model in Complex Scenarios |
| title_short | GLS-YOLO: A Lightweight Tea Bud Detection Model in Complex Scenarios |
| title_sort | gls yolo a lightweight tea bud detection model in complex scenarios |
| topic | tea bud picking tea bud target detection computer vision deep neural network YOLOv8 smart agriculture |
| url | https://www.mdpi.com/2073-4395/14/12/2939 |
| work_keys_str_mv | AT shanshanli glsyoloalightweightteabuddetectionmodelincomplexscenarios AT zhezhang glsyoloalightweightteabuddetectionmodelincomplexscenarios AT shijunli glsyoloalightweightteabuddetectionmodelincomplexscenarios |