Citation format
Shao Mingyue, Zhang Jianhua, Feng Quan, Chai Xiujuan, Zhang Ning, Zhang Wenrong. Research Progress of Deep Learning in Plant Leaf Disease Detection and Identification[J]. Smart Agriculture, 2022, 4(1): 29-46.
SHAO Mingyue, ZHANG Jianhua, FENG Quan, CHAI Xiujuan, ZHANG Ning, ZHANG Wenrong. Research progress of deep learning in detection and recognition of plant leaf diseases[J]. Smart Agriculture, 2022, 4(1): 29-46.
Click to read directly to CNKI
Click to read directly to the official website (full text, free)
Research progress of deep learning in the detection and identification of plant leaf diseases
Shao Ming-yue1, Zhang Jian-hua1*, Feng Quan2, Chai Xiu-juan1, Zhang Ning1, Zhang Wen-rong1
(1.Institute of Agricultural Information, Chinese Academy of Agricultural Sciences/Key Laboratory of Agricultural Big Data, Ministry of Agriculture and Rural Affairs, Beijing, 100081; 2.College of Mechanical and Electrical Engineering, Gansu Agricultural University, Lanzhou 730070, Gansu, China)
Abstract: Accurate detection and identification of plant diseases is the key to early diagnosis and intelligent monitoring, and the core of precise pest control and information management. The application of deep learning in the detection and identification of plant diseases can overcome the drawbacks of traditional diagnostic methods and greatly improve the accuracy of disease detection and identification, which has attracted widespread attention. In this paper, we first collect and introduce some public plant disease image datasets, and then systematically review the research progress of deep learning in plant disease detection and identification in recent years, and expound the research progress from early detection and recognition algorithms to deep learning-based detection and recognition algorithms, as well as the advantages and existing problems of each algorithm. The relevant research literature was investigated, and it was proposed that the main challenges in the detection and identification of plant diseases were light, occlusion, complex background, similarity between disease symptoms, different changes in disease symptoms at different times, and overlapping coexistence of multiple diseases. It is further pointed out that the combination of better neural networks, large-scale datasets and agricultural theoretical foundations is the main development trend in the future, and it is also pointed out that multimodal data can be used for the identification of early plant diseases, which is also one of the future development directions. This paper can provide a reference for the in-depth research and development of plant disease identification.
Key words: plants; leaf diseases; deep learning; disease detection; Identify; convolutional neural networks; Disease image dataset
Long click on the picture to identify the QR code and listen to the introduction of this article
Graphic text of the article
Fig.1 Flow of second-order detection algorithm for plant disease detection
Fig. 1 Two-stage detection algorithm diagram of plant disease detection
Fig.2 Diagram of the first-order detection algorithm for plant disease detection
Fig. 2 One-stage detection algorithm diagram of plant disease detection
Fig.3 Deep learning network diagram for plant disease identification
Fig. 3 Deep learning network diagram for plant disease recognition
Table 1 Publicly available plant disease image dataset and website
Table 1 Publicly available plant disease image data sets and websites
Table 2 Research progress in target detection of plant diseases based on second-order detectors in recent years
Table 2 Recent advances in plant disease target detection based on second-order detector
Table 3 Research progress on target detection of plant diseases based on first-order detectors in recent years
Table 3 Recent advances in plant disease target detection based on first-order detector
Table 4 Research progress of target detection of plant diseases based on anchorless frames and self-built networks in recent years
Table 4 Recent advances in plant disease target detection based on anchor-free and self-built networks
Table 5 Research progress on plant disease identification based on deep network in recent years
Table 5 Recent advances in plant disease recognition based on deep network
Table 6 Recent research progress on plant disease identification based on lightweight networks and simultaneous disease detection and identification
Table 6 Recent advances in plant disease recognition based on lightweight network and disease detection and recognition simultaneously
About the corresponding author
Zhang Jianhua Associate ResearcherZhang Jianhua, male, Doctor of Engineering, Associate Researcher, Master's Supervisor. He has been engaged in agricultural information technology research for a long time, and his research directions include: machine vision and agricultural robots, intelligent identification of crop diseases and pests, and intelligent animal husbandry visual detection. At present, he has presided over more than 10 projects such as the National Natural Science Foundation of China, the Beijing Agricultural Research Project, and the Basic Scientific Research Funds of the Central Public Welfare Research Institutes, and participated in the research of more than 30 scientific research projects such as the National Key Research and Development Program. He has published more than 50 academic papers, including more than 10 SCI papers, nearly 20 EI papers, and 30 Chinese core papers. It has obtained more than 10 invention patents, more than 10 software copyrights, and 3 provincial and ministerial scientific and technological achievement awards. He was awarded the second "Outstanding Youth" honor of the Agricultural Information Institute of the Chinese Academy of Agricultural Sciences, the honor of the Young Model of the Agricultural Information Institute of the Chinese Academy of Agricultural Sciences, and the hospital-level selection of the "Scientific Research Talent Cultivation Project" of the Young Talent Program of the Chinese Academy of Agricultural Sciences. He is a member of the Agricultural Engineering Society, the Agricultural Machinery Society, and the Information Technology Branch of the Chinese Animal Husbandry and Veterinary Association.
Source: Smart Agriculture, Issue 1, 2022
Please contact the editorial department for authorization for reprinting
Supported units in this issue
Jinglan Yunzhi Internet of Things Technology Co., Ltd
Zhejiang Zhenshan Technology Co., Ltd
Weichai Lovol Heavy Industry Co., Ltd
WeChat communication service group
In order to facilitate the academic exchange of readers, authors and reviewers in the field of agricultural science, promote the development of smart agriculture, and better serve the readers, authors and reviewers, the editorial department has established a WeChat communication service group, where questions related to issues in the professional field and submissions can be consulted. How to join the group: Add the editor's WeChat 331760296, note: name, unit, research direction, the editor pulls you into the group, and the institutional marketing and advertising personnel do not disturb.
Release of Information
Introduction of scientific research team and recruitment information, publicity and promotion of academic conferences and related activities