AI-Enabled Crop Management Framework for Pest Detection Using Visual Sensor Data
Open Access
Abstract
Our research focuses on addressing the challenge of crop diseases and pest infestations in agriculture by utilizing UAV technology for improved crop monitoring through unmanned aerial vehicles (UAVs) and enhancing the detection and classification of agricultural pests. Traditional approaches often require arduous manual feature extraction or computationally demanding deep learning (DL) techniques. To address this, we introduce an optimized model tailored specifically for UAV-based applications. Our alterations to the YOLOv5s model, which include advanced attention modules, expanded cross-stage partial network (CSP) modules, and refined multiscale feature extraction mechanisms, enable precise pest detection and classification. Inspired by the efficiency and versatility of UAVs, our study strives to revolutionize pest management in sustainable agriculture while also detecting and preventing crop diseases. We conducted rigorous testing on a medium-scale dataset, identifying five agricultural pests, namely ants, grasshoppers, palm weevils, shield bugs, and wasps. Our comprehensive experimental analysis showcases superior performance compared to various YOLOv5 model versions. The proposed model obtained higher performance, with an average precision of 96.0%, an average recall of 93.0%, and a mean average precision (mAP) of 95.0%. Furthermore, the inherent capabilities of UAVs, combined with the YOLOv5s model tested here, could offer a reliable solution for real-time pest detection, demonstrating significant potential to optimize and improve agricultural production within a drone-centric ecosystem.Keywords
Funding Information
- Ministry of Education (2020R1A6A1A03038540, IITP-2023-RS-2023-00254529, 322063-03-1-SB010)
- Institute of Information & Communications Technology Planning & Evaluation (IITP) (2020R1A6A1A03038540, IITP-2023-RS-2023-00254529, 322063-03-1-SB010)
- Ministry of Agriculture, Food and Rural Affairs (MAFRA) (2020R1A6A1A03038540, IITP-2023-RS-2023-00254529, 322063-03-1-SB010)
This publication has 43 references indexed in Scilit:
- A method of citrus epidermis defects detection based on an improved YOLOv5Biosystems Engineering, 2023
- A new mobile application of agricultural pests recognition using deep learning in cloud computing systemAlexandria Engineering Journal, 2021
- Multi-feature decision fusion algorithm for disease detection on crop surface based on machine visionNeural Computing and Applications, 2021
- Pest24: A large-scale very small object data set of agricultural pests for multi-target detectionComputers and Electronics in Agriculture, 2020
- AF-RCNN: An anchor-free convolutional neural network for multi-categories agricultural pest detectionComputers and Electronics in Agriculture, 2020
- Species‐level image classification with convolutional neural network enables insect identification from habitus imagesEcology and Evolution, 2019
- A novel analysis-prediction approach for geometrically nonlinear problems using group method of data handlingComputer Methods in Applied Mechanics and Engineering, 2019
- Recognition pest by image‐based transfer learningJournal of the Science of Food and Agriculture, 2019
- An effective pest management approach in potato to combat insect pests and herbicide3 Biotech, 2019
- Early detection and classification of plant diseases with Support Vector Machines based on hyperspectral reflectanceComputers and Electronics in Agriculture, 2010