Pest and disease damage detection method based on deep convolutional neural network

Abstract

The invention discloses a pest and disease detection method based on a deep convolutional neural network. The method includes: classifying crop pests and diseases to be detected according to crop categories, pest and disease categories and severity degrees; shooting leaves of the diseased crops by using a camera instrument to make a data set related to plant diseases and insect pests; setting a stacked network module, the stacked network module comprising a convolutional layer, a normalization layer and an activation function layer in a convolutional neural network, the number of feature map layers of each layer being superposed and fused with each other; embedding the stacked network module into a pest and disease damage detection deep convolutional neural network; building a network model through a pest and disease damage detection deep convolutional neural network framework, training the network model on the basis of a data set, and finally sending crop leaves to be detected into the network model to obtain a detection result. The method is high in detection precision and wide in application range, and can be applied to the field of agricultural crop prevention and control, suchas paddy field disease and pest detection, fruit tree disease and pest detection and soybean disease and pest detection.

Description

technical field [0001] The invention belongs to the field of classification of crop diseases and insect pests, in particular to a method for detecting diseases and insect pests based on a deep convolutional neural network. Background technique [0002] Crop diseases and insect pests have many adverse effects on agricultural production, including reducing yield, reducing quality, and affecting the economy. Traditional pest control methods are limited to human monitoring, observation, and data calculation and sorting, which are time-consuming, inaccurate, and the control effect is not timely. Crop diseases and insect pests are very complicated, and there will be various diseases in different seasons. In complex situations, various factors such as climate, planting area, crop variety, and region should still be considered for prevention and control. Since the crop data set only includes leaf image information, the extraction of multi-faceted damage information of crops and lea...

AI Technical Summary

Problems solved by technology

[0002] Crop diseases and insect pests have many adverse effects on agricultural production, including reducing yield, reducing quality, affecting the economy, etc.

Traditional pest control methods are limited to human monitoring, observation, and data calculation and sorting, which are time-consuming, inaccurate, and the control effect is not timely.

Images