Pest recognition in microstates state : an improvement of YOLOv7 based on Spatial and Channel Reconstruction Convolution for feature redundancy and vision transformer with Bi-Level Routing Attention
Copyright © 2024 He, Zhang, Yang, Wang, Gao, Huang, Wang, Wang, Yuan, Wu, Li, Xu, Wang, Zhang and Wang..
Introduction: In order to solve the problem of precise identification and counting of tea pests, this study has proposed a novel tea pest identification method based on improved YOLOv7 network.
Methods: This method used MPDIoU to optimize the original loss function, which improved the convergence speed of the model and simplifies the calculation process. Replace part of the network structure of the original model using Spatial and Channel reconstruction Convolution to reduce redundant features, lower the complexity of the model, and reduce computational costs. The Vision Transformer with Bi-Level Routing Attention has been incorporated to enhance the flexibility of model calculation allocation and content perception.
Results: The experimental results revealed that the enhanced YOLOv7 model significantly boosted Precision, Recall, F1, and mAP by 5.68%, 5.14%, 5.41%, and 2.58% respectively, compared to the original YOLOv7. Furthermore, when compared to deep learning networks such as SSD, Faster Region-based Convolutional Neural Network (RCNN), and the original YOLOv7, this method proves to be superior while being externally validated. It exhibited a noticeable improvement in the FPS rates, with increments of 5.75 HZ, 34.42 HZ, and 25.44 HZ respectively. Moreover, the mAP for actual detection experiences significant enhancements, with respective increases of 2.49%, 12.26%, and 7.26%. Additionally, the parameter size is reduced by 1.39 G relative to the original model.
Discussion: The improved model can not only identify and count tea pests efficiently and accurately, but also has the characteristics of high recognition rate, low parameters and high detection speed. It is of great significance to achieve realize the intelligent and precise prevention and control of tea pests.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:15 |
---|---|
Enthalten in: |
Frontiers in plant science - 15(2024) vom: 15., Seite 1327237 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
He, Junjie [VerfasserIn] |
---|
Links: |
---|
Themen: |
Improved Yolov7 |
---|
Anmerkungen: |
Date Revised 22.02.2024 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.3389/fpls.2024.1327237 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM368699617 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM368699617 | ||
003 | DE-627 | ||
005 | 20240222232834.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240222s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.3389/fpls.2024.1327237 |2 doi | |
028 | 5 | 2 | |a pubmed24n1302.xml |
035 | |a (DE-627)NLM368699617 | ||
035 | |a (NLM)38379942 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a He, Junjie |e verfasserin |4 aut | |
245 | 1 | 0 | |a Pest recognition in microstates state |b an improvement of YOLOv7 based on Spatial and Channel Reconstruction Convolution for feature redundancy and vision transformer with Bi-Level Routing Attention |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 22.02.2024 | ||
500 | |a published: Electronic-eCollection | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a Copyright © 2024 He, Zhang, Yang, Wang, Gao, Huang, Wang, Wang, Yuan, Wu, Li, Xu, Wang, Zhang and Wang. | ||
520 | |a Introduction: In order to solve the problem of precise identification and counting of tea pests, this study has proposed a novel tea pest identification method based on improved YOLOv7 network | ||
520 | |a Methods: This method used MPDIoU to optimize the original loss function, which improved the convergence speed of the model and simplifies the calculation process. Replace part of the network structure of the original model using Spatial and Channel reconstruction Convolution to reduce redundant features, lower the complexity of the model, and reduce computational costs. The Vision Transformer with Bi-Level Routing Attention has been incorporated to enhance the flexibility of model calculation allocation and content perception | ||
520 | |a Results: The experimental results revealed that the enhanced YOLOv7 model significantly boosted Precision, Recall, F1, and mAP by 5.68%, 5.14%, 5.41%, and 2.58% respectively, compared to the original YOLOv7. Furthermore, when compared to deep learning networks such as SSD, Faster Region-based Convolutional Neural Network (RCNN), and the original YOLOv7, this method proves to be superior while being externally validated. It exhibited a noticeable improvement in the FPS rates, with increments of 5.75 HZ, 34.42 HZ, and 25.44 HZ respectively. Moreover, the mAP for actual detection experiences significant enhancements, with respective increases of 2.49%, 12.26%, and 7.26%. Additionally, the parameter size is reduced by 1.39 G relative to the original model | ||
520 | |a Discussion: The improved model can not only identify and count tea pests efficiently and accurately, but also has the characteristics of high recognition rate, low parameters and high detection speed. It is of great significance to achieve realize the intelligent and precise prevention and control of tea pests | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a MPDIou | |
650 | 4 | |a Spatial and Channel Reconstruction Convolution | |
650 | 4 | |a improved Yolov7 | |
650 | 4 | |a pest identification | |
650 | 4 | |a vision transformer with Bi-Level Routing Attention | |
700 | 1 | |a Zhang, Shihao |e verfasserin |4 aut | |
700 | 1 | |a Yang, Chunhua |e verfasserin |4 aut | |
700 | 1 | |a Wang, Houqiao |e verfasserin |4 aut | |
700 | 1 | |a Gao, Jun |e verfasserin |4 aut | |
700 | 1 | |a Huang, Wei |e verfasserin |4 aut | |
700 | 1 | |a Wang, Qiaomei |e verfasserin |4 aut | |
700 | 1 | |a Wang, Xinghua |e verfasserin |4 aut | |
700 | 1 | |a Yuan, Wenxia |e verfasserin |4 aut | |
700 | 1 | |a Wu, Yamin |e verfasserin |4 aut | |
700 | 1 | |a Li, Lei |e verfasserin |4 aut | |
700 | 1 | |a Xu, Jiayi |e verfasserin |4 aut | |
700 | 1 | |a Wang, Zejun |e verfasserin |4 aut | |
700 | 1 | |a Zhang, Rukui |e verfasserin |4 aut | |
700 | 1 | |a Wang, Baijuan |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Frontiers in plant science |d 2010 |g 15(2024) vom: 15., Seite 1327237 |w (DE-627)NLM218083777 |x 1664-462X |7 nnns |
773 | 1 | 8 | |g volume:15 |g year:2024 |g day:15 |g pages:1327237 |
856 | 4 | 0 | |u http://dx.doi.org/10.3389/fpls.2024.1327237 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 15 |j 2024 |b 15 |h 1327237 |