A method of identification and localization of tea buds based on lightweight improved YOLOV5
The low degree of intelligence and standardization of tea bud picking, as well as laborious and time-consuming manual harvesting, bring significant challenges to the sustainable development of the high-quality tea industry. There is an urgent need to investigate the critical technologies of intellig...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-11-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2024.1488185/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850266063218933760 |
|---|---|
| author | Yuanhong Wang Yuanhong Wang Jinzhu Lu Jinzhu Lu Qi Wang Qi Wang Zongmei Gao |
| author_facet | Yuanhong Wang Yuanhong Wang Jinzhu Lu Jinzhu Lu Qi Wang Qi Wang Zongmei Gao |
| author_sort | Yuanhong Wang |
| collection | DOAJ |
| description | The low degree of intelligence and standardization of tea bud picking, as well as laborious and time-consuming manual harvesting, bring significant challenges to the sustainable development of the high-quality tea industry. There is an urgent need to investigate the critical technologies of intelligent picking robots for tea. The complexity of the model requires high hardware computing resources, which limits the deployment of the tea bud detection model in tea-picking robots. Therefore, in this study, we propose the YOLOV5M-SBSD tea bud lightweight detection model to address the above issues. The Fuding white tea bud image dataset was established by collecting Fuding white tea images; then the lightweight network ShuffleNetV2 was used to replace the YOLOV5 backbone network; the up-sampling algorithm of YOLOV5 was optimized by using CARAFE modular structure, which increases the sensory field of the network while maintaining the lightweight; then BiFPN was used to achieve more efficient multi-scale feature fusion; and the introduction of the parameter-free attention SimAm to enhance the feature extraction ability of the model while not adding extra computation. The improved model was denoted as YOLOV5M-SBSD and compared and analyzed with other mainstream target detection models. Then, the YOLOV5M-SBSD recognition model is experimented on with the tea bud dataset, and the tea buds are recognized using YOLOV5M-SBSD. The experimental results show that the recognition accuracy of tea buds is 88.7%, the recall rate is 86.9%, and the average accuracy is 93.1%, which is 0.5% higher than the original YOLOV5M algorithm’s accuracy, the average accuracy is 0.2% higher, the Size is reduced by 82.89%, and the Params, and GFlops are reduced by 83.7% and 85.6%, respectively. The improved algorithm has higher detection accuracy while reducing the amount of computation and parameters. Also, it reduces the dependence on hardware, provides a reference for deploying the tea bud target detection model in the natural environment of the tea garden, and has specific theoretical and practical significance for the identification and localization of the intelligent picking robot of tea buds. |
| format | Article |
| id | doaj-art-7c436002d6c64a2eb0b3604c0167984d |
| institution | OA Journals |
| issn | 1664-462X |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj-art-7c436002d6c64a2eb0b3604c0167984d2025-08-20T01:54:16ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2024-11-011510.3389/fpls.2024.14881851488185A method of identification and localization of tea buds based on lightweight improved YOLOV5Yuanhong Wang0Yuanhong Wang1Jinzhu Lu2Jinzhu Lu3Qi Wang4Qi Wang5Zongmei Gao6Modern Agricultural Equipment Research Institute, Xihua University, Chengdu, ChinaSchool of Mechanical Engineering, Xihua University, Chengdu, ChinaModern Agricultural Equipment Research Institute, Xihua University, Chengdu, ChinaSchool of Mechanical Engineering, Xihua University, Chengdu, ChinaModern Agricultural Equipment Research Institute, Xihua University, Chengdu, ChinaSchool of Mechanical Engineering, Xihua University, Chengdu, ChinaDepartment of Biological Systems Engineering, Washington State University, Prosser, WA, United StatesThe low degree of intelligence and standardization of tea bud picking, as well as laborious and time-consuming manual harvesting, bring significant challenges to the sustainable development of the high-quality tea industry. There is an urgent need to investigate the critical technologies of intelligent picking robots for tea. The complexity of the model requires high hardware computing resources, which limits the deployment of the tea bud detection model in tea-picking robots. Therefore, in this study, we propose the YOLOV5M-SBSD tea bud lightweight detection model to address the above issues. The Fuding white tea bud image dataset was established by collecting Fuding white tea images; then the lightweight network ShuffleNetV2 was used to replace the YOLOV5 backbone network; the up-sampling algorithm of YOLOV5 was optimized by using CARAFE modular structure, which increases the sensory field of the network while maintaining the lightweight; then BiFPN was used to achieve more efficient multi-scale feature fusion; and the introduction of the parameter-free attention SimAm to enhance the feature extraction ability of the model while not adding extra computation. The improved model was denoted as YOLOV5M-SBSD and compared and analyzed with other mainstream target detection models. Then, the YOLOV5M-SBSD recognition model is experimented on with the tea bud dataset, and the tea buds are recognized using YOLOV5M-SBSD. The experimental results show that the recognition accuracy of tea buds is 88.7%, the recall rate is 86.9%, and the average accuracy is 93.1%, which is 0.5% higher than the original YOLOV5M algorithm’s accuracy, the average accuracy is 0.2% higher, the Size is reduced by 82.89%, and the Params, and GFlops are reduced by 83.7% and 85.6%, respectively. The improved algorithm has higher detection accuracy while reducing the amount of computation and parameters. Also, it reduces the dependence on hardware, provides a reference for deploying the tea bud target detection model in the natural environment of the tea garden, and has specific theoretical and practical significance for the identification and localization of the intelligent picking robot of tea buds.https://www.frontiersin.org/articles/10.3389/fpls.2024.1488185/fulltea budstarget detectionYOLOV5M-SBSDlightweight modelingdeep learning |
| spellingShingle | Yuanhong Wang Yuanhong Wang Jinzhu Lu Jinzhu Lu Qi Wang Qi Wang Zongmei Gao A method of identification and localization of tea buds based on lightweight improved YOLOV5 Frontiers in Plant Science tea buds target detection YOLOV5M-SBSD lightweight modeling deep learning |
| title | A method of identification and localization of tea buds based on lightweight improved YOLOV5 |
| title_full | A method of identification and localization of tea buds based on lightweight improved YOLOV5 |
| title_fullStr | A method of identification and localization of tea buds based on lightweight improved YOLOV5 |
| title_full_unstemmed | A method of identification and localization of tea buds based on lightweight improved YOLOV5 |
| title_short | A method of identification and localization of tea buds based on lightweight improved YOLOV5 |
| title_sort | method of identification and localization of tea buds based on lightweight improved yolov5 |
| topic | tea buds target detection YOLOV5M-SBSD lightweight modeling deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2024.1488185/full |
| work_keys_str_mv | AT yuanhongwang amethodofidentificationandlocalizationofteabudsbasedonlightweightimprovedyolov5 AT yuanhongwang amethodofidentificationandlocalizationofteabudsbasedonlightweightimprovedyolov5 AT jinzhulu amethodofidentificationandlocalizationofteabudsbasedonlightweightimprovedyolov5 AT jinzhulu amethodofidentificationandlocalizationofteabudsbasedonlightweightimprovedyolov5 AT qiwang amethodofidentificationandlocalizationofteabudsbasedonlightweightimprovedyolov5 AT qiwang amethodofidentificationandlocalizationofteabudsbasedonlightweightimprovedyolov5 AT zongmeigao amethodofidentificationandlocalizationofteabudsbasedonlightweightimprovedyolov5 AT yuanhongwang methodofidentificationandlocalizationofteabudsbasedonlightweightimprovedyolov5 AT yuanhongwang methodofidentificationandlocalizationofteabudsbasedonlightweightimprovedyolov5 AT jinzhulu methodofidentificationandlocalizationofteabudsbasedonlightweightimprovedyolov5 AT jinzhulu methodofidentificationandlocalizationofteabudsbasedonlightweightimprovedyolov5 AT qiwang methodofidentificationandlocalizationofteabudsbasedonlightweightimprovedyolov5 AT qiwang methodofidentificationandlocalizationofteabudsbasedonlightweightimprovedyolov5 AT zongmeigao methodofidentificationandlocalizationofteabudsbasedonlightweightimprovedyolov5 |