Cargando…

Pest-YOLO: A model for large-scale multi-class dense and tiny pest detection and counting

Frequent outbreaks of agricultural pests can reduce crop production severely and restrict agricultural production. Therefore, automatic monitoring and precise recognition of crop pests have a high practical value in the process of agricultural planting. In recent years, pest recognition and detectio...

Descripción completa

Detalles Bibliográficos
Autores principales: Wen, Changji, Chen, Hongrui, Ma, Zhenyu, Zhang, Tian, Yang, Ce, Su, Hengqiang, Chen, Hongbing
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9783619/
https://www.ncbi.nlm.nih.gov/pubmed/36570910
http://dx.doi.org/10.3389/fpls.2022.973985
_version_ 1784857620533739520
author Wen, Changji
Chen, Hongrui
Ma, Zhenyu
Zhang, Tian
Yang, Ce
Su, Hengqiang
Chen, Hongbing
author_facet Wen, Changji
Chen, Hongrui
Ma, Zhenyu
Zhang, Tian
Yang, Ce
Su, Hengqiang
Chen, Hongbing
author_sort Wen, Changji
collection PubMed
description Frequent outbreaks of agricultural pests can reduce crop production severely and restrict agricultural production. Therefore, automatic monitoring and precise recognition of crop pests have a high practical value in the process of agricultural planting. In recent years, pest recognition and detection have been rapidly improved with the development of deep learning-based methods. Although certain progress has been made in the research on pest detection and identification technology based on deep learning, there are still many problems in the production application in a field environment. This work presents a pest detector for multi-category dense and tiny pests named the Pest-YOLO. First, the idea of focal loss is introduced into the loss function using weight distribution to improve the attention of hard samples. In this way, the problems of hard samples arose from the uneven distribution of pest populations in a dataset and low discrimination features of small pests are relieved. Next, a non-Intersection over Union bounding box selection and suppression algorithm, the confluence strategy, is used. The confluence strategy can eliminate the errors and omissions of pest detection caused by occlusion, adhesion and unlabeling among tiny dense pest individuals to the greatest extent. The proposed Pest-YOLO model is verified on a large-scale pest image dataset, the Pest24, which includes more than 20k images with over 190k pests labeled by agricultural experts and categorized into 24 classes. Experimental results show that the Pest-YOLO can obtain 69.59% for mAP and 77.71% for mRecall on the 24-class pest dataset, which is 5.32% and 28.12% higher than the benchmark model YOLOv4. Meanwhile, our proposed model is superior to other several state-of-the-art methods, including the SSD, RetinaNet, Faster RCNN, YOLOv3, YOLOv4, YOLOv5s, YOLOv5m, YOLOX, DETR, TOOD, YOLOv3-W, and AF-RCNN detectors. The code of the proposed algorithm is available at: https://github.com/chr-secrect/Pest-YOLO.
format Online
Article
Text
id pubmed-9783619
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-97836192022-12-24 Pest-YOLO: A model for large-scale multi-class dense and tiny pest detection and counting Wen, Changji Chen, Hongrui Ma, Zhenyu Zhang, Tian Yang, Ce Su, Hengqiang Chen, Hongbing Front Plant Sci Plant Science Frequent outbreaks of agricultural pests can reduce crop production severely and restrict agricultural production. Therefore, automatic monitoring and precise recognition of crop pests have a high practical value in the process of agricultural planting. In recent years, pest recognition and detection have been rapidly improved with the development of deep learning-based methods. Although certain progress has been made in the research on pest detection and identification technology based on deep learning, there are still many problems in the production application in a field environment. This work presents a pest detector for multi-category dense and tiny pests named the Pest-YOLO. First, the idea of focal loss is introduced into the loss function using weight distribution to improve the attention of hard samples. In this way, the problems of hard samples arose from the uneven distribution of pest populations in a dataset and low discrimination features of small pests are relieved. Next, a non-Intersection over Union bounding box selection and suppression algorithm, the confluence strategy, is used. The confluence strategy can eliminate the errors and omissions of pest detection caused by occlusion, adhesion and unlabeling among tiny dense pest individuals to the greatest extent. The proposed Pest-YOLO model is verified on a large-scale pest image dataset, the Pest24, which includes more than 20k images with over 190k pests labeled by agricultural experts and categorized into 24 classes. Experimental results show that the Pest-YOLO can obtain 69.59% for mAP and 77.71% for mRecall on the 24-class pest dataset, which is 5.32% and 28.12% higher than the benchmark model YOLOv4. Meanwhile, our proposed model is superior to other several state-of-the-art methods, including the SSD, RetinaNet, Faster RCNN, YOLOv3, YOLOv4, YOLOv5s, YOLOv5m, YOLOX, DETR, TOOD, YOLOv3-W, and AF-RCNN detectors. The code of the proposed algorithm is available at: https://github.com/chr-secrect/Pest-YOLO. Frontiers Media S.A. 2022-10-25 /pmc/articles/PMC9783619/ /pubmed/36570910 http://dx.doi.org/10.3389/fpls.2022.973985 Text en Copyright © 2022 Wen, Chen, Ma, Zhang, Yang, Su and Chen 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
Wen, Changji
Chen, Hongrui
Ma, Zhenyu
Zhang, Tian
Yang, Ce
Su, Hengqiang
Chen, Hongbing
Pest-YOLO: A model for large-scale multi-class dense and tiny pest detection and counting
title Pest-YOLO: A model for large-scale multi-class dense and tiny pest detection and counting
title_full Pest-YOLO: A model for large-scale multi-class dense and tiny pest detection and counting
title_fullStr Pest-YOLO: A model for large-scale multi-class dense and tiny pest detection and counting
title_full_unstemmed Pest-YOLO: A model for large-scale multi-class dense and tiny pest detection and counting
title_short Pest-YOLO: A model for large-scale multi-class dense and tiny pest detection and counting
title_sort pest-yolo: a model for large-scale multi-class dense and tiny pest detection and counting
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9783619/
https://www.ncbi.nlm.nih.gov/pubmed/36570910
http://dx.doi.org/10.3389/fpls.2022.973985
work_keys_str_mv AT wenchangji pestyoloamodelforlargescalemulticlassdenseandtinypestdetectionandcounting
AT chenhongrui pestyoloamodelforlargescalemulticlassdenseandtinypestdetectionandcounting
AT mazhenyu pestyoloamodelforlargescalemulticlassdenseandtinypestdetectionandcounting
AT zhangtian pestyoloamodelforlargescalemulticlassdenseandtinypestdetectionandcounting
AT yangce pestyoloamodelforlargescalemulticlassdenseandtinypestdetectionandcounting
AT suhengqiang pestyoloamodelforlargescalemulticlassdenseandtinypestdetectionandcounting
AT chenhongbing pestyoloamodelforlargescalemulticlassdenseandtinypestdetectionandcounting