Automatic tobacco insect identifying and counting method and computer readable medium

Abstract

An automatic tobacco insect identifying and counting method disclosed in the invention is used for identifying tobacco insect types captured by a tobacco insect trapper and counting the number of tobacco insects, and comprises the following steps: s1, acquiring historical tobacco insect trapper photo data; s2, processing historical tobacco insect trapper photo data to form batch labeling data set information; s3, training a neural network model by using the obtained batch labeling data set information to obtain a tobacco insect identification neural network model; and s4, identifying to-be-counted tobacco insect trapper photos by using the obtained tobacco insect identification neural network model, and automatically obtaining tobacco insect types and tobacco insect quantity information on the photos. Historical tobacco insect trapper picture data are processed, and a deep learning neural network model is adopted for training to obtain a tobacco insect identification neural network model capable of accurately identifying and predicting the types and the number of tobacco insects on tobacco insect trapper pictures. By utilizing the model, tobacco insects trapped by a tobacco insect trapper can be automatically and quickly identified and counted, and the type and quantity information of the tobacco insects can be obtained.

Description

technical field [0001] The application belongs to the technical field of automatic measurement, and in particular relates to a method for automatic identification and counting of smoke insects and a computer-readable medium. Background technique [0002] A large number of high-value tobacco leaves stored in tobacco warehouses and workshops of tobacco enterprises are vulnerable to insect damage, which seriously affects the availability of tobacco leaves and the quality of cigarettes. [0003] In the prior art, when tobacco companies prevent and control tobacco pests, they usually use tobacco traps to monitor the storage warehouses of tobacco leaf raw materials and cigarette production and processing sites, and judge the severity of pest problems and their impacts from the monitoring data. Therefore, the monitoring data is the decision to take An important basis for which pest control measures. [0004] In the prior art, after the tobacco insect traps are hung in the tobacco ...

AI Technical Summary

Problems solved by technology

Since there are a large number of tobacco insect traps in the tobacco leaf warehouse and workshop, it is necessary to manually complete the identification, counting and input of the tobacco insect species into the information system. Such an operation process not only requires a lot of human resources, but also takes a long time. Real-time feedback, unable to monitor tobacco leaf insects in a timely and effective manner

Images