YOLOv7-DWS: tea bud recognition and detection network in multi-density environment via improved YOLOv7
IntroductionAccurate detection and recognition of tea bud images can drive advances in intelligent harvesting machinery for tea gardens and technology for tea bud pests and diseases. In order to realize the recognition and grading of tea buds in a complex multi-density tea garden environment.Methods...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2024.1503033/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841556745656205312 |
|---|---|
| author | Xiaoming Wang Xiaoming Wang Zhenlong Wu Guannan Xiao Guannan Xiao Chongyang Han Cheng Fang |
| author_facet | Xiaoming Wang Xiaoming Wang Zhenlong Wu Guannan Xiao Guannan Xiao Chongyang Han Cheng Fang |
| author_sort | Xiaoming Wang |
| collection | DOAJ |
| description | IntroductionAccurate detection and recognition of tea bud images can drive advances in intelligent harvesting machinery for tea gardens and technology for tea bud pests and diseases. In order to realize the recognition and grading of tea buds in a complex multi-density tea garden environment.MethodsThis paper proposes an improved YOLOv7 object detection algorithm, called YOLOv7-DWS, which focuses on improving the accuracy of tea recognition. First, we make a series of improvements to the YOLOv7 algorithm, including decouple head to replace the head of YOLOv7, to enhance the feature extraction ability of the model and optimize the class decision logic. The problem of simultaneous detection and classification of one-bud-one-leaf and one-bud-two-leaves of tea was solved. Secondly, a new loss function WiseIoU is proposed for the loss function in YOLOv7, which improves the accuracy of the model. Finally, we evaluate different attention mechanisms to enhance the model’s focus on key features.Results and discussionThe experimental results show that the improved YOLOv7 algorithm has significantly improved over the original algorithm in all evaluation indexes, especially in the RTea(+6.2%) and mAP@0.5 (+7.7%). From the results, the algorithm in this paper helps to provide a new perspective and possibility for the field of tea image recognition. |
| format | Article |
| id | doaj-art-c04edef50238432e9ab0b6bd9910da49 |
| institution | Kabale University |
| issn | 1664-462X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj-art-c04edef50238432e9ab0b6bd9910da492025-01-07T06:41:04ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-01-011510.3389/fpls.2024.15030331503033YOLOv7-DWS: tea bud recognition and detection network in multi-density environment via improved YOLOv7Xiaoming Wang0Xiaoming Wang1Zhenlong Wu2Guannan Xiao3Guannan Xiao4Chongyang Han5Cheng Fang6Chengdu Polytechnic, Innovation and Practice Base for Postdoctors, Chengdu, Sichuan, ChinaSichuan Provincial Engineering Research Center of Thermoelectric Materials and Devices, Chengdu, Sichuan, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaChengdu Polytechnic, Innovation and Practice Base for Postdoctors, Chengdu, Sichuan, ChinaSichuan Provincial Engineering Research Center of Thermoelectric Materials and Devices, Chengdu, Sichuan, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaIntroductionAccurate detection and recognition of tea bud images can drive advances in intelligent harvesting machinery for tea gardens and technology for tea bud pests and diseases. In order to realize the recognition and grading of tea buds in a complex multi-density tea garden environment.MethodsThis paper proposes an improved YOLOv7 object detection algorithm, called YOLOv7-DWS, which focuses on improving the accuracy of tea recognition. First, we make a series of improvements to the YOLOv7 algorithm, including decouple head to replace the head of YOLOv7, to enhance the feature extraction ability of the model and optimize the class decision logic. The problem of simultaneous detection and classification of one-bud-one-leaf and one-bud-two-leaves of tea was solved. Secondly, a new loss function WiseIoU is proposed for the loss function in YOLOv7, which improves the accuracy of the model. Finally, we evaluate different attention mechanisms to enhance the model’s focus on key features.Results and discussionThe experimental results show that the improved YOLOv7 algorithm has significantly improved over the original algorithm in all evaluation indexes, especially in the RTea(+6.2%) and mAP@0.5 (+7.7%). From the results, the algorithm in this paper helps to provide a new perspective and possibility for the field of tea image recognition.https://www.frontiersin.org/articles/10.3389/fpls.2024.1503033/fulltea budsimages recognitionmulti-densityobject detectionYOLOv7deep learning |
| spellingShingle | Xiaoming Wang Xiaoming Wang Zhenlong Wu Guannan Xiao Guannan Xiao Chongyang Han Cheng Fang YOLOv7-DWS: tea bud recognition and detection network in multi-density environment via improved YOLOv7 Frontiers in Plant Science tea buds images recognition multi-density object detection YOLOv7 deep learning |
| title | YOLOv7-DWS: tea bud recognition and detection network in multi-density environment via improved YOLOv7 |
| title_full | YOLOv7-DWS: tea bud recognition and detection network in multi-density environment via improved YOLOv7 |
| title_fullStr | YOLOv7-DWS: tea bud recognition and detection network in multi-density environment via improved YOLOv7 |
| title_full_unstemmed | YOLOv7-DWS: tea bud recognition and detection network in multi-density environment via improved YOLOv7 |
| title_short | YOLOv7-DWS: tea bud recognition and detection network in multi-density environment via improved YOLOv7 |
| title_sort | yolov7 dws tea bud recognition and detection network in multi density environment via improved yolov7 |
| topic | tea buds images recognition multi-density object detection YOLOv7 deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2024.1503033/full |
| work_keys_str_mv | AT xiaomingwang yolov7dwsteabudrecognitionanddetectionnetworkinmultidensityenvironmentviaimprovedyolov7 AT xiaomingwang yolov7dwsteabudrecognitionanddetectionnetworkinmultidensityenvironmentviaimprovedyolov7 AT zhenlongwu yolov7dwsteabudrecognitionanddetectionnetworkinmultidensityenvironmentviaimprovedyolov7 AT guannanxiao yolov7dwsteabudrecognitionanddetectionnetworkinmultidensityenvironmentviaimprovedyolov7 AT guannanxiao yolov7dwsteabudrecognitionanddetectionnetworkinmultidensityenvironmentviaimprovedyolov7 AT chongyanghan yolov7dwsteabudrecognitionanddetectionnetworkinmultidensityenvironmentviaimprovedyolov7 AT chengfang yolov7dwsteabudrecognitionanddetectionnetworkinmultidensityenvironmentviaimprovedyolov7 |