AGRICULTURAL DISEASE AND PEST DETECTION BASED ON MACHINE VISION
Keywords:
Disease and insect pest detection, Machine vision, STM 32 microcontroller, Deep learningAbstract
With the growth of the global population and the rise of agricultural demand, crop pest monitoring and control has become a key link to ensure food security. The traditional manual monitoring method has low efficiency and poor accuracy, which is difficult to meet the needs of modern agriculture. Therefore, a monitoring system for agricultural pests and diseases based on machine vision was designed, which combined with image recognition, deep learning, embedded system and wireless communication technology to realize real-time monitoring and automatic identification of pests. The experimental results show that the identification accuracy of common pests is 92%, the data transmission is stable, and the average response time is 10 seconds, which can meet the real-time monitoring needs of farmland. The introduction of solar powered systems further reduces maintenance costs and improves the sustainability of the system. This study provides an efficient and accurate solution for agricultural pest monitoring, which is of great significance for improving agricultural production efficiency and ensuring food security.References
[1] Wang Linlin. Design of identification and monitoring system of crop leaf pests and diseases. Harbin University of Science and Technology, 2023.
[2] Pang Zongyang. Design of identification and monitoring system for crop leaf pests and diseases. Journal of Agricultural Engineering Technology, 2023, 43(26): 20-21.
[3] Wei Jiafu. Design and implementation of leaf recognition system for crop pests and diseases based on improved DenseNet network model. Zhejiang Normal University, 2023.
[4] Liu X, Zhao Y, Chen J. A novel real-time monitoring system for agricultural pests using machine vision and wireless sensor networks. Sensors, 2023, 23(10): 4747.
[5] Wang Y, Li J, Zhou M. Design and optimization of solar-powered agricultural monitoring system. Energy Procedia, 2021, 186, 286-293.
[6] Chen H, Liu Y, Huang C. Development of an intelligent pest monitoring and early warning system for greenhouse crops. Acta Horticulturae Sinica, 2023, 50(8): 1667-1678.
[7] Kamal R. Embedded Systems: Architecture, Programming, and Design (Chen, S. H, et al., Trans.). Tsinghua University Press, 2005.
[8] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 2017, 60(6): 84-90.