Research on Identification Technology of Field Pests with Protective Color Characteristics
Accurate identification of field pests has crucial decision-making significance for integrated pest control. Most current research focuses on the identification of pests on the sticky card or the case of great differences between the target and the background. There is little research on field pest...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/8/3810 |
| _version_ | 1797437054076846080 |
|---|---|
| author | Zhengfang Hu Yang Xiang Yajun Li Zhenhuan Long Anwen Liu Xiufeng Dai Xiangming Lei Zhenhui Tang |
| author_facet | Zhengfang Hu Yang Xiang Yajun Li Zhenhuan Long Anwen Liu Xiufeng Dai Xiangming Lei Zhenhui Tang |
| author_sort | Zhengfang Hu |
| collection | DOAJ |
| description | Accurate identification of field pests has crucial decision-making significance for integrated pest control. Most current research focuses on the identification of pests on the sticky card or the case of great differences between the target and the background. There is little research on field pest identification with protective color characteristics. Aiming at the problem that it is difficult to identify pests with protective color characteristics in the complex field environment, a field pest identification method based on near-infrared imaging technology and YOLOv5 is proposed in this paper. Firstly, an appropriate infrared filter and ring light source have been selected to build an image acquisition system according to the wavelength with the largest spectral reflectance difference between the spectral curves of the pest (<i>Pieris rapae</i>) and its host plants (cabbage), which are formed by specific spectral characteristics. Then, field pest images have been collected to construct a data set, which has been trained and tested through YOLOv5. Experimental results demonstrate that the average time required to detect one pest image is 0.56 s, and the mAP reaches 99.7%. |
| first_indexed | 2024-03-09T11:13:27Z |
| format | Article |
| id | doaj.art-e8ea17a7fd0d4d148e3f7d13221b5d71 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T11:13:27Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e8ea17a7fd0d4d148e3f7d13221b5d712023-12-01T00:39:14ZengMDPI AGApplied Sciences2076-34172022-04-01128381010.3390/app12083810Research on Identification Technology of Field Pests with Protective Color CharacteristicsZhengfang Hu0Yang Xiang1Yajun Li2Zhenhuan Long3Anwen Liu4Xiufeng Dai5Xiangming Lei6Zhenhui Tang7College of Mechanical and Electrical Engineering, Hunan Agricultural University, Changsha 410128, ChinaCollege of Mechanical and Electrical Engineering, Hunan Agricultural University, Changsha 410128, ChinaCollege of Mechanical and Electrical Engineering, Hunan Agricultural University, Changsha 410128, ChinaCollege of Mechanical and Electrical Engineering, Hunan Agricultural University, Changsha 410128, ChinaCollege of Mechanical and Electrical Engineering, Hunan Agricultural University, Changsha 410128, ChinaCollege of Mechanical and Electrical Engineering, Hunan Agricultural University, Changsha 410128, ChinaCollege of Mechanical and Electrical Engineering, Hunan Agricultural University, Changsha 410128, ChinaCollege of Mechanical and Electrical Engineering, Hunan Agricultural University, Changsha 410128, ChinaAccurate identification of field pests has crucial decision-making significance for integrated pest control. Most current research focuses on the identification of pests on the sticky card or the case of great differences between the target and the background. There is little research on field pest identification with protective color characteristics. Aiming at the problem that it is difficult to identify pests with protective color characteristics in the complex field environment, a field pest identification method based on near-infrared imaging technology and YOLOv5 is proposed in this paper. Firstly, an appropriate infrared filter and ring light source have been selected to build an image acquisition system according to the wavelength with the largest spectral reflectance difference between the spectral curves of the pest (<i>Pieris rapae</i>) and its host plants (cabbage), which are formed by specific spectral characteristics. Then, field pest images have been collected to construct a data set, which has been trained and tested through YOLOv5. Experimental results demonstrate that the average time required to detect one pest image is 0.56 s, and the mAP reaches 99.7%.https://www.mdpi.com/2076-3417/12/8/3810deep learninghyperspectral technologypest identificationYOLOv5near-infrared imaging technology |
| spellingShingle | Zhengfang Hu Yang Xiang Yajun Li Zhenhuan Long Anwen Liu Xiufeng Dai Xiangming Lei Zhenhui Tang Research on Identification Technology of Field Pests with Protective Color Characteristics Applied Sciences deep learning hyperspectral technology pest identification YOLOv5 near-infrared imaging technology |
| title | Research on Identification Technology of Field Pests with Protective Color Characteristics |
| title_full | Research on Identification Technology of Field Pests with Protective Color Characteristics |
| title_fullStr | Research on Identification Technology of Field Pests with Protective Color Characteristics |
| title_full_unstemmed | Research on Identification Technology of Field Pests with Protective Color Characteristics |
| title_short | Research on Identification Technology of Field Pests with Protective Color Characteristics |
| title_sort | research on identification technology of field pests with protective color characteristics |
| topic | deep learning hyperspectral technology pest identification YOLOv5 near-infrared imaging technology |
| url | https://www.mdpi.com/2076-3417/12/8/3810 |
| work_keys_str_mv | AT zhengfanghu researchonidentificationtechnologyoffieldpestswithprotectivecolorcharacteristics AT yangxiang researchonidentificationtechnologyoffieldpestswithprotectivecolorcharacteristics AT yajunli researchonidentificationtechnologyoffieldpestswithprotectivecolorcharacteristics AT zhenhuanlong researchonidentificationtechnologyoffieldpestswithprotectivecolorcharacteristics AT anwenliu researchonidentificationtechnologyoffieldpestswithprotectivecolorcharacteristics AT xiufengdai researchonidentificationtechnologyoffieldpestswithprotectivecolorcharacteristics AT xiangminglei researchonidentificationtechnologyoffieldpestswithprotectivecolorcharacteristics AT zhenhuitang researchonidentificationtechnologyoffieldpestswithprotectivecolorcharacteristics |