Cargando…

Global Context-Aware-Based Deformable Residual Network Module for Precise Pest Recognition and Detection

An accurate and robust pest detection and recognition scheme is an important step to enable the high quality and yield of agricultural products according to integrated pest management (IPM). Due to pose-variant, serious overlap, dense distribution, and interclass similarity of agricultural pests, th...

Descripción completa

Detalles Bibliográficos
Autores principales: Jiao, Lin, Li, Gaoqiang, Chen, Peng, Wang, Rujing, Du, Jianming, Liu, Haiyun, Dong, Shifeng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9201688/
https://www.ncbi.nlm.nih.gov/pubmed/35720529
http://dx.doi.org/10.3389/fpls.2022.895944
_version_ 1784728369163665408
author Jiao, Lin
Li, Gaoqiang
Chen, Peng
Wang, Rujing
Du, Jianming
Liu, Haiyun
Dong, Shifeng
author_facet Jiao, Lin
Li, Gaoqiang
Chen, Peng
Wang, Rujing
Du, Jianming
Liu, Haiyun
Dong, Shifeng
author_sort Jiao, Lin
collection PubMed
description An accurate and robust pest detection and recognition scheme is an important step to enable the high quality and yield of agricultural products according to integrated pest management (IPM). Due to pose-variant, serious overlap, dense distribution, and interclass similarity of agricultural pests, the precise detection of multi-classes pest faces great challenges. In this study, an end-to-end pest detection algorithm has been proposed on the basis of deep convolutional neural networks. The detection method adopts a deformable residual network to extract pest features and a global context-aware module for obtaining region-of-interests of agricultural pests. The detection results of the proposed method are compared with the detection results of other state-of-the-art methods, for example, RetinaNet, YOLO, SSD, FPN, and Cascade RCNN modules. The experimental results show that our method can achieve an average accuracy of 77.8% on 21 categories of agricultural pests. The proposed detection algorithm can achieve 20.9 frames per second, which can satisfy real-time pest detection.
format Online
Article
Text
id pubmed-9201688
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-92016882022-06-17 Global Context-Aware-Based Deformable Residual Network Module for Precise Pest Recognition and Detection Jiao, Lin Li, Gaoqiang Chen, Peng Wang, Rujing Du, Jianming Liu, Haiyun Dong, Shifeng Front Plant Sci Plant Science An accurate and robust pest detection and recognition scheme is an important step to enable the high quality and yield of agricultural products according to integrated pest management (IPM). Due to pose-variant, serious overlap, dense distribution, and interclass similarity of agricultural pests, the precise detection of multi-classes pest faces great challenges. In this study, an end-to-end pest detection algorithm has been proposed on the basis of deep convolutional neural networks. The detection method adopts a deformable residual network to extract pest features and a global context-aware module for obtaining region-of-interests of agricultural pests. The detection results of the proposed method are compared with the detection results of other state-of-the-art methods, for example, RetinaNet, YOLO, SSD, FPN, and Cascade RCNN modules. The experimental results show that our method can achieve an average accuracy of 77.8% on 21 categories of agricultural pests. The proposed detection algorithm can achieve 20.9 frames per second, which can satisfy real-time pest detection. Frontiers Media S.A. 2022-06-02 /pmc/articles/PMC9201688/ /pubmed/35720529 http://dx.doi.org/10.3389/fpls.2022.895944 Text en Copyright © 2022 Jiao, Li, Chen, Wang, Du, Liu and Dong. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Plant Science
Jiao, Lin
Li, Gaoqiang
Chen, Peng
Wang, Rujing
Du, Jianming
Liu, Haiyun
Dong, Shifeng
Global Context-Aware-Based Deformable Residual Network Module for Precise Pest Recognition and Detection
title Global Context-Aware-Based Deformable Residual Network Module for Precise Pest Recognition and Detection
title_full Global Context-Aware-Based Deformable Residual Network Module for Precise Pest Recognition and Detection
title_fullStr Global Context-Aware-Based Deformable Residual Network Module for Precise Pest Recognition and Detection
title_full_unstemmed Global Context-Aware-Based Deformable Residual Network Module for Precise Pest Recognition and Detection
title_short Global Context-Aware-Based Deformable Residual Network Module for Precise Pest Recognition and Detection
title_sort global context-aware-based deformable residual network module for precise pest recognition and detection
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9201688/
https://www.ncbi.nlm.nih.gov/pubmed/35720529
http://dx.doi.org/10.3389/fpls.2022.895944
work_keys_str_mv AT jiaolin globalcontextawarebaseddeformableresidualnetworkmoduleforprecisepestrecognitionanddetection
AT ligaoqiang globalcontextawarebaseddeformableresidualnetworkmoduleforprecisepestrecognitionanddetection
AT chenpeng globalcontextawarebaseddeformableresidualnetworkmoduleforprecisepestrecognitionanddetection
AT wangrujing globalcontextawarebaseddeformableresidualnetworkmoduleforprecisepestrecognitionanddetection
AT dujianming globalcontextawarebaseddeformableresidualnetworkmoduleforprecisepestrecognitionanddetection
AT liuhaiyun globalcontextawarebaseddeformableresidualnetworkmoduleforprecisepestrecognitionanddetection
AT dongshifeng globalcontextawarebaseddeformableresidualnetworkmoduleforprecisepestrecognitionanddetection