Research on the identification and detection of field pests in the complex background based on the rotation detection algorithm
As a large agricultural and population country, China’s annual demand for food is significant. The crop yield will be affected by various natural disasters every year, and one of the most important factors affecting crops is the impact of insect pests. The key to solving the problem is to detect, id...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-12-01
|
Series: | Frontiers in Plant Science |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2022.1011499/full |
_version_ | 1811178214037389312 |
---|---|
author | Wei Zhang Wei Zhang Xulu Xia Guotao Zhou Jianming Du Tianjiao Chen Zhengyong Zhang Xiangyang Ma |
author_facet | Wei Zhang Wei Zhang Xulu Xia Guotao Zhou Jianming Du Tianjiao Chen Zhengyong Zhang Xiangyang Ma |
author_sort | Wei Zhang |
collection | DOAJ |
description | As a large agricultural and population country, China’s annual demand for food is significant. The crop yield will be affected by various natural disasters every year, and one of the most important factors affecting crops is the impact of insect pests. The key to solving the problem is to detect, identify and provide feedback in time at the initial stage of the pest. In this paper, according to the pest picture data obtained through the pest detection lamp in the complex natural background and the marking categories of agricultural experts, the pest data set pest rotation detection (PRD21) in different natural environments is constructed. A comparative study of image recognition is carried out through different target detection algorithms. The final experiment proves that the best algorithm for rotation detection improves mean Average Precision by 18.5% compared to the best algorithm for horizontal detection, reaching 78.5%. Regarding Recall, the best rotation detection algorithm runs 94.7%, which is 7.4% higher than horizontal detection. In terms of detection speed, the rotation detection time of a picture is only 0.163s, and the model size is 66.54MB, which can be embedded in mobile devices for fast detection. This experiment proves that rotation detection has a good effect on pests’ detection and recognition rate, which can bring new application value and ideas, provide new methods for plant protection, and improve grain yield. |
first_indexed | 2024-04-11T06:14:42Z |
format | Article |
id | doaj.art-e87511450df242bdb49abb0a34ff8a2a |
institution | Directory Open Access Journal |
issn | 1664-462X |
language | English |
last_indexed | 2024-04-11T06:14:42Z |
publishDate | 2022-12-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Plant Science |
spelling | doaj.art-e87511450df242bdb49abb0a34ff8a2a2022-12-22T04:41:06ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2022-12-011310.3389/fpls.2022.10114991011499Research on the identification and detection of field pests in the complex background based on the rotation detection algorithmWei Zhang0Wei Zhang1Xulu Xia2Guotao Zhou3Jianming Du4Tianjiao Chen5Zhengyong Zhang6Xiangyang Ma7Institute of Physical Science and Information Technology, Anhui University, HeFei, ChinaInstitute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, ChinaInstitute of Physical Science and Information Technology, Anhui University, HeFei, ChinaTechnology Research and Deveplopment Center, Henan Yunfei Technology Development Co. LTD, Henan, ChinaInstitute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, ChinaInstitute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, ChinaInstitute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, ChinaHarvesting and Processing Department, Liaoning Provincial Institiute of Agricultural Mechanization, Shengyang, ChinaAs a large agricultural and population country, China’s annual demand for food is significant. The crop yield will be affected by various natural disasters every year, and one of the most important factors affecting crops is the impact of insect pests. The key to solving the problem is to detect, identify and provide feedback in time at the initial stage of the pest. In this paper, according to the pest picture data obtained through the pest detection lamp in the complex natural background and the marking categories of agricultural experts, the pest data set pest rotation detection (PRD21) in different natural environments is constructed. A comparative study of image recognition is carried out through different target detection algorithms. The final experiment proves that the best algorithm for rotation detection improves mean Average Precision by 18.5% compared to the best algorithm for horizontal detection, reaching 78.5%. Regarding Recall, the best rotation detection algorithm runs 94.7%, which is 7.4% higher than horizontal detection. In terms of detection speed, the rotation detection time of a picture is only 0.163s, and the model size is 66.54MB, which can be embedded in mobile devices for fast detection. This experiment proves that rotation detection has a good effect on pests’ detection and recognition rate, which can bring new application value and ideas, provide new methods for plant protection, and improve grain yield.https://www.frontiersin.org/articles/10.3389/fpls.2022.1011499/fullimage recognitionobject detectionrotation detectionpest detectionplant protection |
spellingShingle | Wei Zhang Wei Zhang Xulu Xia Guotao Zhou Jianming Du Tianjiao Chen Zhengyong Zhang Xiangyang Ma Research on the identification and detection of field pests in the complex background based on the rotation detection algorithm Frontiers in Plant Science image recognition object detection rotation detection pest detection plant protection |
title | Research on the identification and detection of field pests in the complex background based on the rotation detection algorithm |
title_full | Research on the identification and detection of field pests in the complex background based on the rotation detection algorithm |
title_fullStr | Research on the identification and detection of field pests in the complex background based on the rotation detection algorithm |
title_full_unstemmed | Research on the identification and detection of field pests in the complex background based on the rotation detection algorithm |
title_short | Research on the identification and detection of field pests in the complex background based on the rotation detection algorithm |
title_sort | research on the identification and detection of field pests in the complex background based on the rotation detection algorithm |
topic | image recognition object detection rotation detection pest detection plant protection |
url | https://www.frontiersin.org/articles/10.3389/fpls.2022.1011499/full |
work_keys_str_mv | AT weizhang researchontheidentificationanddetectionoffieldpestsinthecomplexbackgroundbasedontherotationdetectionalgorithm AT weizhang researchontheidentificationanddetectionoffieldpestsinthecomplexbackgroundbasedontherotationdetectionalgorithm AT xuluxia researchontheidentificationanddetectionoffieldpestsinthecomplexbackgroundbasedontherotationdetectionalgorithm AT guotaozhou researchontheidentificationanddetectionoffieldpestsinthecomplexbackgroundbasedontherotationdetectionalgorithm AT jianmingdu researchontheidentificationanddetectionoffieldpestsinthecomplexbackgroundbasedontherotationdetectionalgorithm AT tianjiaochen researchontheidentificationanddetectionoffieldpestsinthecomplexbackgroundbasedontherotationdetectionalgorithm AT zhengyongzhang researchontheidentificationanddetectionoffieldpestsinthecomplexbackgroundbasedontherotationdetectionalgorithm AT xiangyangma researchontheidentificationanddetectionoffieldpestsinthecomplexbackgroundbasedontherotationdetectionalgorithm |