Precise Crop Pest Detection Based on Co-Ordinate-Attention-Based Feature Pyramid Module
Insect pests strongly affect crop growth and value globally. Fast and precise pest detection and counting are crucial measures in the management and mitigation of pest infestations. In this area, deep learning technologies have come to represent the method with the most potential. However, for small...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Insects |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4450/16/1/103 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588318097801216 |
|---|---|
| author | Chenrui Kang Lin Jiao Kang Liu Zhigui Liu Rujing Wang |
| author_facet | Chenrui Kang Lin Jiao Kang Liu Zhigui Liu Rujing Wang |
| author_sort | Chenrui Kang |
| collection | DOAJ |
| description | Insect pests strongly affect crop growth and value globally. Fast and precise pest detection and counting are crucial measures in the management and mitigation of pest infestations. In this area, deep learning technologies have come to represent the method with the most potential. However, for small-sized crop pests, recent deep-learning-based detection attempts have not accomplished accurate recognition and detection due to the challenges posed by feature extraction and positive and negative sample selection. Therefore, to overcome these limitations, we first designed a co-ordinate-attention-based feature pyramid network, termed CAFPN, to extract the salient visual features that distinguish small insects from each other. Subsequently, in the network training stage, a dynamic sample selection strategy using positive and negative weight functions, which considers both high classification scores and precise localization, was introduced. Finally, several experiments were conducted on our constructed large-scale crop pest datasets, the AgriPest 21 dataset and the IP102 dateset, achieving accuracy scores of 77.2% and 29.8% for mAP (mean average precision), demonstrating promising detection results when compared to other detectors. |
| format | Article |
| id | doaj-art-fa56ce537e3d4ec7836d64076091e522 |
| institution | Kabale University |
| issn | 2075-4450 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Insects |
| spelling | doaj-art-fa56ce537e3d4ec7836d64076091e5222025-01-24T13:35:55ZengMDPI AGInsects2075-44502025-01-0116110310.3390/insects16010103Precise Crop Pest Detection Based on Co-Ordinate-Attention-Based Feature Pyramid ModuleChenrui Kang0Lin Jiao1Kang Liu2Zhigui Liu3Rujing Wang4School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, ChinaInstitute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaDepartment of Aeronautical and Aviation Engineering, Hong Kong Polytechnic University, Hong Kong 999077, ChinaSchool of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, ChinaSchool of InterNet, the National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, Hefei 230031, ChinaInsect pests strongly affect crop growth and value globally. Fast and precise pest detection and counting are crucial measures in the management and mitigation of pest infestations. In this area, deep learning technologies have come to represent the method with the most potential. However, for small-sized crop pests, recent deep-learning-based detection attempts have not accomplished accurate recognition and detection due to the challenges posed by feature extraction and positive and negative sample selection. Therefore, to overcome these limitations, we first designed a co-ordinate-attention-based feature pyramid network, termed CAFPN, to extract the salient visual features that distinguish small insects from each other. Subsequently, in the network training stage, a dynamic sample selection strategy using positive and negative weight functions, which considers both high classification scores and precise localization, was introduced. Finally, several experiments were conducted on our constructed large-scale crop pest datasets, the AgriPest 21 dataset and the IP102 dateset, achieving accuracy scores of 77.2% and 29.8% for mAP (mean average precision), demonstrating promising detection results when compared to other detectors.https://www.mdpi.com/2075-4450/16/1/103crop pestobject detectionsmall pestfeature pyramid networkco-ordinate attentionsample selection |
| spellingShingle | Chenrui Kang Lin Jiao Kang Liu Zhigui Liu Rujing Wang Precise Crop Pest Detection Based on Co-Ordinate-Attention-Based Feature Pyramid Module Insects crop pest object detection small pest feature pyramid network co-ordinate attention sample selection |
| title | Precise Crop Pest Detection Based on Co-Ordinate-Attention-Based Feature Pyramid Module |
| title_full | Precise Crop Pest Detection Based on Co-Ordinate-Attention-Based Feature Pyramid Module |
| title_fullStr | Precise Crop Pest Detection Based on Co-Ordinate-Attention-Based Feature Pyramid Module |
| title_full_unstemmed | Precise Crop Pest Detection Based on Co-Ordinate-Attention-Based Feature Pyramid Module |
| title_short | Precise Crop Pest Detection Based on Co-Ordinate-Attention-Based Feature Pyramid Module |
| title_sort | precise crop pest detection based on co ordinate attention based feature pyramid module |
| topic | crop pest object detection small pest feature pyramid network co-ordinate attention sample selection |
| url | https://www.mdpi.com/2075-4450/16/1/103 |
| work_keys_str_mv | AT chenruikang precisecroppestdetectionbasedoncoordinateattentionbasedfeaturepyramidmodule AT linjiao precisecroppestdetectionbasedoncoordinateattentionbasedfeaturepyramidmodule AT kangliu precisecroppestdetectionbasedoncoordinateattentionbasedfeaturepyramidmodule AT zhiguiliu precisecroppestdetectionbasedoncoordinateattentionbasedfeaturepyramidmodule AT rujingwang precisecroppestdetectionbasedoncoordinateattentionbasedfeaturepyramidmodule |