Edge Device Detection of Tea Leaves with One Bud and Two Leaves Based on ShuffleNetv2-YOLOv5-Lite-E
In order to solve the problem of an accurate recognition of tea picking through tea picking robots, an edge device detection method is proposed in this paper based on ShuffleNetv2-YOLOv5-Lite-E for tea with one bud and two leaves. This replaces the original feature extraction network by removing the...
Main Authors: | , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-02-01
|
Series: | Agronomy |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4395/13/2/577 |
_version_ | 1797622834030182400 |
---|---|
author | Shihao Zhang Hekai Yang Chunhua Yang Wenxia Yuan Xinghui Li Xinghua Wang Yinsong Zhang Xiaobo Cai Yubo Sheng Xiujuan Deng Wei Huang Lei Li Junjie He Baijuan Wang |
author_facet | Shihao Zhang Hekai Yang Chunhua Yang Wenxia Yuan Xinghui Li Xinghua Wang Yinsong Zhang Xiaobo Cai Yubo Sheng Xiujuan Deng Wei Huang Lei Li Junjie He Baijuan Wang |
author_sort | Shihao Zhang |
collection | DOAJ |
description | In order to solve the problem of an accurate recognition of tea picking through tea picking robots, an edge device detection method is proposed in this paper based on ShuffleNetv2-YOLOv5-Lite-E for tea with one bud and two leaves. This replaces the original feature extraction network by removing the Focus layer and using the ShuffleNetv2 algorithm, followed by a channel pruning of YOLOv5 at the neck layer head, thus achieving the purpose of reducing the model size. The results show that the size of the improved generated weight file is 27% of that of the original YOLOv5 model, and the mAP value of ShuffleNetv2-YOLOv5-Lite-E is 97.43% and 94.52% on the pc and edge device respectively, which are 1.32% and 1.75% lower compared to that of the original YOLOv5 model. The detection speeds of ShuffleNetv2-YOLOv5-Lite-E, YOLOv5, YOLOv4, and YOLOv3 were 8.6 fps, 2.7 fps, 3.2 fps, and 3.4 fps respectively after importing the models into an edge device, and the improved YOLOv5 detection speed was 3.2 times faster than that of the original YOLOv5 model. Through the detection method, the size of the original YOLOv5 model is effectively reduced while essentially ensuring recognition accuracy. The detection speed is also significantly improved, which is conducive to the realization of intelligent and accurate picking for future tea gardens, laying a solid foundation for the realization of tea picking robots. |
first_indexed | 2024-03-11T09:16:50Z |
format | Article |
id | doaj.art-429f1f93ef6c4a5ab55f341df82e0192 |
institution | Directory Open Access Journal |
issn | 2073-4395 |
language | English |
last_indexed | 2024-03-11T09:16:50Z |
publishDate | 2023-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Agronomy |
spelling | doaj.art-429f1f93ef6c4a5ab55f341df82e01922023-11-16T18:36:38ZengMDPI AGAgronomy2073-43952023-02-0113257710.3390/agronomy13020577Edge Device Detection of Tea Leaves with One Bud and Two Leaves Based on ShuffleNetv2-YOLOv5-Lite-EShihao Zhang0Hekai Yang1Chunhua Yang2Wenxia Yuan3Xinghui Li4Xinghua Wang5Yinsong Zhang6Xiaobo Cai7Yubo Sheng8Xiujuan Deng9Wei Huang10Lei Li11Junjie He12Baijuan Wang13College of Mechanical and Electrical Engineering, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Mechanical and Electrical Engineering, Yunnan Agricultural University, Kunming 650201, ChinaYunnan Organic Tea Industry Intelligent Engineering Research Center, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Tea Science, Yunnan Agricultural University, Kunming 650201, ChinaInternational Institute of Tea Industry Innovation for “The Belt and Road”, Nanjing Agricultural University, Nanjing 210095, ChinaCollege of Tea Science, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Foreign Languages, Yunnan Agricultural University, Kunming 650201, ChinaYunnan Organic Tea Industry Intelligent Engineering Research Center, Yunnan Agricultural University, Kunming 650201, ChinaChina Tea (Yunnan) Co., Ltd., Kunming 650201, ChinaCollege of Tea Science, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Tea Science, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Tea Science, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Tea Science, Yunnan Agricultural University, Kunming 650201, ChinaYunnan Organic Tea Industry Intelligent Engineering Research Center, Yunnan Agricultural University, Kunming 650201, ChinaIn order to solve the problem of an accurate recognition of tea picking through tea picking robots, an edge device detection method is proposed in this paper based on ShuffleNetv2-YOLOv5-Lite-E for tea with one bud and two leaves. This replaces the original feature extraction network by removing the Focus layer and using the ShuffleNetv2 algorithm, followed by a channel pruning of YOLOv5 at the neck layer head, thus achieving the purpose of reducing the model size. The results show that the size of the improved generated weight file is 27% of that of the original YOLOv5 model, and the mAP value of ShuffleNetv2-YOLOv5-Lite-E is 97.43% and 94.52% on the pc and edge device respectively, which are 1.32% and 1.75% lower compared to that of the original YOLOv5 model. The detection speeds of ShuffleNetv2-YOLOv5-Lite-E, YOLOv5, YOLOv4, and YOLOv3 were 8.6 fps, 2.7 fps, 3.2 fps, and 3.4 fps respectively after importing the models into an edge device, and the improved YOLOv5 detection speed was 3.2 times faster than that of the original YOLOv5 model. Through the detection method, the size of the original YOLOv5 model is effectively reduced while essentially ensuring recognition accuracy. The detection speed is also significantly improved, which is conducive to the realization of intelligent and accurate picking for future tea gardens, laying a solid foundation for the realization of tea picking robots.https://www.mdpi.com/2073-4395/13/2/577ShuffleNetv2-YOLOv5-Lite-Emodel sizeone bud and two leavesedge device |
spellingShingle | Shihao Zhang Hekai Yang Chunhua Yang Wenxia Yuan Xinghui Li Xinghua Wang Yinsong Zhang Xiaobo Cai Yubo Sheng Xiujuan Deng Wei Huang Lei Li Junjie He Baijuan Wang Edge Device Detection of Tea Leaves with One Bud and Two Leaves Based on ShuffleNetv2-YOLOv5-Lite-E Agronomy ShuffleNetv2-YOLOv5-Lite-E model size one bud and two leaves edge device |
title | Edge Device Detection of Tea Leaves with One Bud and Two Leaves Based on ShuffleNetv2-YOLOv5-Lite-E |
title_full | Edge Device Detection of Tea Leaves with One Bud and Two Leaves Based on ShuffleNetv2-YOLOv5-Lite-E |
title_fullStr | Edge Device Detection of Tea Leaves with One Bud and Two Leaves Based on ShuffleNetv2-YOLOv5-Lite-E |
title_full_unstemmed | Edge Device Detection of Tea Leaves with One Bud and Two Leaves Based on ShuffleNetv2-YOLOv5-Lite-E |
title_short | Edge Device Detection of Tea Leaves with One Bud and Two Leaves Based on ShuffleNetv2-YOLOv5-Lite-E |
title_sort | edge device detection of tea leaves with one bud and two leaves based on shufflenetv2 yolov5 lite e |
topic | ShuffleNetv2-YOLOv5-Lite-E model size one bud and two leaves edge device |
url | https://www.mdpi.com/2073-4395/13/2/577 |
work_keys_str_mv | AT shihaozhang edgedevicedetectionoftealeaveswithonebudandtwoleavesbasedonshufflenetv2yolov5litee AT hekaiyang edgedevicedetectionoftealeaveswithonebudandtwoleavesbasedonshufflenetv2yolov5litee AT chunhuayang edgedevicedetectionoftealeaveswithonebudandtwoleavesbasedonshufflenetv2yolov5litee AT wenxiayuan edgedevicedetectionoftealeaveswithonebudandtwoleavesbasedonshufflenetv2yolov5litee AT xinghuili edgedevicedetectionoftealeaveswithonebudandtwoleavesbasedonshufflenetv2yolov5litee AT xinghuawang edgedevicedetectionoftealeaveswithonebudandtwoleavesbasedonshufflenetv2yolov5litee AT yinsongzhang edgedevicedetectionoftealeaveswithonebudandtwoleavesbasedonshufflenetv2yolov5litee AT xiaobocai edgedevicedetectionoftealeaveswithonebudandtwoleavesbasedonshufflenetv2yolov5litee AT yubosheng edgedevicedetectionoftealeaveswithonebudandtwoleavesbasedonshufflenetv2yolov5litee AT xiujuandeng edgedevicedetectionoftealeaveswithonebudandtwoleavesbasedonshufflenetv2yolov5litee AT weihuang edgedevicedetectionoftealeaveswithonebudandtwoleavesbasedonshufflenetv2yolov5litee AT leili edgedevicedetectionoftealeaveswithonebudandtwoleavesbasedonshufflenetv2yolov5litee AT junjiehe edgedevicedetectionoftealeaveswithonebudandtwoleavesbasedonshufflenetv2yolov5litee AT baijuanwang edgedevicedetectionoftealeaveswithonebudandtwoleavesbasedonshufflenetv2yolov5litee |