Agronomy · 2024 · 21 citations · 21 references
ComputingComputer ScienceCrop SciencesAgricultural EntomologyComputer VisionFeature EngineeringAgricultural Machine VisionFeature ExtractionFeature-level FusionImage Feature EngineeringObject DetectionPest DetectionAutomated Pest IdentificationFeature FusionFeature-based RepresentationImage Feature FusionImage-based Pest DetectionImage-based Pest RecognitionInsect Pest IdentificationMultimodal Feature Fusion
Crop diseases and pests are important factors restricting agricultural production. Traditional pest detection methods are mainly targeted at a single pest species, which is difficult to meet the needs of multi-target identification and rapid response in real scenes. Therefore, this paper improves the YOLOv8n model for efficient multi-target pest detection. Two feature enhancement modules, EMSFEM and AFEM_SIE, are proposed in this paper. The EMSFEM module enriches the model’s receptive field through the combination of multi-scale asymmetric convolution kernel and different expansion rates and can better extract the width, height, texture, and edge information of the target. The AFEM_SIE module captures the similarities and differences between upper and lower features through spatial information exchange and enhances feature representation through inter-feature information exchange. In addition, an improved feature fusion operation, Concat_Weighting, is proposed on the basis of Concat. The module uses the learned weights to carry out channel weighting and feature graph weighting for input features, which realizes more flexible and effective feature fusion. The results of experiments conducted on the publicly available large-scale crop pest and disease dataset IP102 show that the performance of the AEC-YOLOv8n model is significantly improved compared with the original YOLOv8n model, with mAP50 increased by 8.9%, accuracy increased by 6.8%, and recall rate increased by 6.3%. The AEC-YOLOv8n model proposed in this study can effectively identify and deal with a variety of crop pests and has achieved the best detection accuracy on the IP102 dataset, which has high application value.
21
Feature Pyramid Networks for Object Detection
Tsung-Yi Lin, Piotr Dollár, Ross Girshick et al. · 2017 · 28.7K citations
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
Qilong Wang, Banggu Wu, Pengfei Zhu et al. · 2020 · 8.1K citations
Coordinate Attention for Efficient Mobile Network Design
Qibin Hou, Daquan Zhou, Jiashi Feng · 2021 · 5.7K citations
Transfer learning using computational intelligence: A survey
Jie Lü, Vahid Behbood, Hao Peng et al. · Knowledge-Based Systems · 2015 · 981 citations · Full text