Department of Computer Science and Engineering, Sejong University, Seoul 05006, Republic of Korea.
Department of Convergence Engineering for Intelligent Drone, Sejong University, Seoul 05006, Republic of Korea.
Sensors (Basel). 2023 May 24;23(11):5032. doi: 10.3390/s23115032.
In recent years, the development of deep learning technology has significantly benefited agriculture in domains such as smart and precision farming. Deep learning models require a large amount of high-quality training data. However, collecting and managing large amounts of guaranteed-quality data is a critical issue. To meet these requirements, this study proposes a scalable plant disease information collection and management system (PlantInfoCMS). The proposed PlantInfoCMS consists of data collection, annotation, data inspection, and dashboard modules to generate accurate and high-quality pest and disease image datasets for learning purposes. Additionally, the system provides various statistical functions allowing users to easily check the progress of each task, making management highly efficient. Currently, PlantInfoCMS handles data on 32 types of crops and 185 types of pests and diseases, and stores and manages 301,667 original and 195,124 labeled images. The PlantInfoCMS proposed in this study is expected to significantly contribute to the diagnosis of crop pests and diseases by providing high-quality AI images for learning about and facilitating the management of crop pests and diseases.
近年来，深度学习技术在智慧和精准农业等领域为农业带来了显著的发展。深度学习模型需要大量的高质量训练数据。然而，收集和管理大量保证质量的数据是一个关键问题。为了满足这些需求，本研究提出了一个可扩展的植物病害信息采集和管理系统（PlantInfoCMS）。所提出的 PlantInfoCMS 由数据采集、标注、数据检查和仪表板模块组成，用于生成用于学习的准确和高质量的病虫害图像数据集。此外，该系统提供了各种统计功能，使用户可以轻松检查每个任务的进度，从而实现高效管理。目前，PlantInfoCMS 处理 32 种作物和 185 种病虫害的数据，并存储和管理 301667 张原始图像和 195124 张标注图像。本研究提出的 PlantInfoCMS 有望通过为学习和管理作物病虫害提供高质量的 AI 图像，为作物病虫害的诊断做出重大贡献。
