review · Artificial Intelligence Review
Plant diseases present a major risk to food security and agricultural yields, creating a need for rapid, non-destructive, and precise diagnostic methods. Computer vision powered by deep learning provides automated disease identification while reducing the human bias associated with manual feature selection. An analysis of over 278 research publications examines the frameworks, reference datasets, benefits, drawbacks, and performance of these technologies. Effective imaging sensors identified include standard RGB, multispectral, and hyperspectral cameras capable of early disease detection. Evaluated computational architectures encompass convolutional neural networks, vision transformers, generative adversarial networks, vision language models, and foundation models. In addition to technical assessments, research insights link algorithmic performance to practical crop protection requirements, offering guidance on the deployment suitability of deep learning models in real-world agricultural production settings.
Plant diseases reduce crop yields and threaten global food security. Identifying infections early and accurately without damaging crops allows for timely intervention. By consolidating the performance of emerging deep learning tools and advanced camera sensors, this synthesis helps agricultural practitioners and technology developers determine which automated diagnostic methods are best suited for deployment in working farm environments.
The work addresses automated plant disease detection tools for precision agriculture and crop protection. Potential users include agricultural practitioners, farm managers, and agronomic software developers seeking guidance on deploying deep learning models in production environments. Because the review evaluates existing research and datasets across over 278 studies, it indicates that while underlying models range from early-stage concepts to tested architectures, the transition to commercial production environments requires selecting models matched to specific operational requirements.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Plant diseases cause significant damage to agriculture, leading to substantial yield losses and posing a major threat to food security. Detection, identification, quantification, and diagnosis of plant diseases are crucial parts of precision agriculture and crop protection. Modernizing agriculture and improving production efficiency are significantly affected by using computer vision technology for crop disease diagnosis. This technology is notable for its non-destructive nature, speed, real-time responsiveness, and precision. Deep learning (DL), a recent breakthrough in computer vision, has become a focal point in agricultural plant protection that can minimize the biases of manually selecting disease spot features. This study reviews the techniques and tools used for automatic disease identification, state-of-the-art DL models, and recent trends in DL-based image analysis. The techniques, performance, benefits, drawbacks, underlying frameworks, and reference datasets of more than 278 research articles were analyzed and subsequently highlighted in accordance with the architecture of computer vision and deep learning models. Key findings include the effectiveness of imaging techniques and sensors like RGB, multispectral, and hyperspectral cameras for early disease detection. Researchers also evaluated various DL architectures, such as convolutional neural networks, vision transformers, generative adversarial networks, vision language models, and foundation models. Moreover, the study connects academic research with practical agricultural applications, providing guidance on the suitability of these models for production environments. This comprehensive review offers valuable insights into the current state and future directions of deep learning in plant disease detection, making it a significant resource for researchers, academicians, and practitioners in precision agriculture.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s10462-024-11100-x
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
