Abstract
Recently, disease prevention in jute plants has become an urgent topic as a result of the growing demand for finer quality fiber. This research presents a deep learning network called YOLO-JD for detecting jute diseases from images. In the main architecture of YOLO-JD, we integrated three new modules such as Sand Clock Feature Extraction Module (SCFEM), Deep Sand Clock Feature Extraction Module (DSCFEM), and Spatial Pyramid Pooling Module (SPPM) to extract image features effectively. We also built a new large-scale image dataset for jute diseases and pests with ten classes. Compared with other state-of-the-art experiments, YOLO-JD has achieved the best detection accuracy, with an average mAP of 96.63%.
Funder
Shanghai Rising-Star Program
Shanghai Natural Science Foundation
National Natural Science Foundation of China
Subject
Plant Science,Ecology,Ecology, Evolution, Behavior and Systematics
Reference34 articles.
1. Research on jute (Corchorus olitorius and C. capsularis) and kenaf (Hibiscus cannabinus and H. sabdariffa): Present status and future perspective;Mahapatra;Indian J. Agric. Sci.,2009
2. Fabrication and Characterization of Jute Fiber Reinforced Low Density Polyethylene Based Composites: Effects of Chemical Treatment
3. Plastic & Climate: The Hidden Costs of a Plastic Planet,2019
4. Flame-Retardancy Properties of Intumescent Ammonium Poly(Phosphate) and Mineral Filler Magnesium Hydroxide in Combination with Graphene;Barkoula;Polym. Polym. Compos.,2008
5. Precision agriculture technologies for management of plant diseases;Balasundram,2020
Cited by
41 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献