Abstract:  【Aim】 In order to reduce the workload of forecasting technicians, improve the precision and the real-time of Cnaphalocrocis medinalis forecasting and realize the traceability of monitoring pest data, a pheromone-baited intelligent monitoring system of C. medinalis based on machine vision was established. 【Methods】 The pheromone-baited intelligent monitoring system of C. medinalis includes an intelligent pest trap based on machine vision, a detection model of C. medinalis based on deep learning, a system Web front-end and a server. Several devices including an industrial camera, a light source and an Android pad were integrated into the machine vision system of pheromone-based intelligent trap. A two-layer network detection model based on improved YOLOv3 and DBTNet-101 was developed. HTML, CSS, JavaScript and Vue were adopted to build the Web front-end for displaying the results of detecting and counting the pests in the trap. Django framework was used to build a server to receive the images from the intelligent traps uploaded through 4G network and provide feedback. MySQL database was used to store the images, model detection results and other information.【Results】 The pheromone-baited intelligent monitoring system of C. medinalis based on machine vision used the intelligent trap to automatically upload the images of C. medinalis to the server on a regular time. The object detection model deployed on the server performs could automatically detect C. medinalis adults in real time, with the precision rate and recall rate of 97.6% and 98.6%, respectively. Users could check the detection results of C. medinalis images through the Web front-end. 【Conclusion】 The pheromone-baited intelligent monitoring system of C. medinalis can automatically capture the images, and accurately detect and count C. medinalis adults. This system can realize the real-time and intelligentized monitoring of C. medinalis by pheromonebaited trap, reduce the workload of forecasting technicians, and trace back the data easily.

Key words: Cnaphalocrocis medinalis, pheromone-baited trap, machine vision, intelligent monitoring, deep learning, object detection