EarlyCropGuard: A Risk-Adaptive Edge AI Framework for Early Crop Disease Prediction and Real-Time Detection Using Computer Vision: A Review

This review examined recent research on AI-based crop disease detection using Deep Learning, Computer Vision, Edge AI, disease localization, severity assessment, and Explainable AI. The reviewed studies demonstrate that AI-based approaches have significantly improved automated disease identification compared with traditional manual inspection methods. CNN-based models, object detection, and image segmentation techniques have provided effective solutions for disease classification and affected-region analysis. However, the review also identified several important challenges in existing approaches. These include limited early-stage disease datasets, poor performance under real-field conditions, high computational requirements, fixed processing pipelines, limited severity assessment, and insufficient model explainability. In addition, many existing studies address classification, localization, severity analysis, and explainability as separate tasks rather than providing an integrated approach. Based on the comparative analysis and identified research gaps, this review proposed EarlyCropGuard: A Risk-Adaptive Edge AI Framework for Early Crop Disease Prediction and Real-Time Detection Using Computer Vision as a conceptual framework for future research. The framework introduces a risk-adaptive processing strategy in which crop images can receive different levels of analysis according to their estimated risk and prediction characteristics. The proposed framework conceptually combines fast initial screening, risk analysis, detailed disease classification, localization, severity assessment, and Explainable AI. Rather than applying computationally intensive analysis to every image, detailed processing can be directed toward medium-risk, high-risk, or uncertain cases. This approach provides a potential direction for balancing computational efficiency with detailed disease analysis. In conclusion, the reviewed literature confirms the growing potential of AI and Computer Vision for intelligent crop disease monitoring. Future work can focus on implementing and experimentally evaluating the EarlyCropGuard framework using diverse real-world datasets and Edge devices. Such research can contribute toward the development of more efficient, adaptive, transparent, and practical crop disease detection systems for modern agriculture.

[1] S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using Deep Learning for Image-Based Plant Disease Detection,” Frontiers in Plant Science, vol. 7, p. 1419, 2016, DOI: 10.3389/fpls.2016.01419. [2] S. Sladojevic, M. Arsenovic, A. Anderla, D. Culibrk, and D. Stefanovic, “Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification,” Computational Intelligence and Neuroscience, vol. 2016, Article ID 3289801, 2016, DOI: 10.1155/2016/3289801. [3] K. P. Ferentinos, “Deep Learning Models for Plant Disease Detection and Diagnosis,” Computers and Electronics in Agriculture, vol. 145, pp. 311–318, 2018, DOI: 10.1016/j.compag.2018.01.009. [4] E. C. Too, L. Yujian, S. Njuki, and L. Yingchun, “A Comparative Study of Fine-Tuning Deep Learning Models for Plant Disease Identification,” Computers and Electronics in Agriculture, vol. 161, pp. 272–279, 2019, DOI: 10.1016/j.compag.2018.03.032. [5] P. Sajitha, A. D. Andrushia, N. Anand, and M. Z. Naser, “A Review on Machine Learning and Deep Learning Image-Based Plant Disease Classification for Industrial Farming Systems,” Journal of Industrial Information Integration, vol. 38, p. 100572, 2024, DOI: 10.1016/j.jii.2024.100572. [6] I. Pacal, I. Kunduracioglu, M. H. Alma, et al., “A Systematic Review of Deep Learning Techniques for Plant Diseases,” Artificial Intelligence Review, vol. 57, p. 304, 2024, DOI: 10.1007/s10462-024-10944-7. [7] A. Fuentes, S. Yoon, S. C. Kim, and D. S. Park, “A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition,” Sensors, vol. 17, no. 9, p. 2022, 2017, DOI: 10.3390/s17092022. [8] A. Picon, A. Alvarez-Gila, M. Seitz, A. Ortiz-Barredo, J. Echazarra, and A. Johannes, “Deep Convolutional Neural Networks for Mobile Capture Device-Based Crop Disease Classification in the Wild,” Computers and Electronics in Agriculture, vol. 161, pp. 280–290, 2019. [9] A. Picon, M. Seitz, A. Alvarez-Gila, P. Mohnke, A. Ortiz-Barredo, and J. Echazarra, “Crop Conditional Convolutional Neural Networks for Massive Multi-Crop Plant Disease Classification Over Cell Phone Acquired Images Taken on Real Field Conditions,” Computers and Electronics in Agriculture, 2019, DOI: 10.1016/j.compag.2019.105093. [10] C. DeChant, T. Wiesner-Hanks, S. Chen, E. L. Stewart, J. Yosinski, M. A. Gore, R. J. Nelson, and H. Lipson, “Automated Identification of Northern Leaf Blight-Infected Maize Plants from Field Imagery Using Deep Learning,” Phytopathology, vol. 107, no. 11, pp. 1426–1432, 2017, DOI: 10.1094/PHYTO-11-16-0417-R.