Method and device for detecting and identifying stored grain insects

Abstract

The invention provides a method and device for detecting and identifying stored grain insects. The method comprises the steps of inputting an original stored grain insect image into an artificial intelligence analysis model to perform location positioning and category judgment on insects, wherein the artificial intelligence analysis model is a convolutional neural network which is trained and verified according to a data set formed by the stored grain insect image; and labeling the insect location and category on the original stored grain insect image according to a location positioning and category judgment result. According to the invention, a model capable of correctly positioning and identifying various stored grain insects is trained according to a deep leaning based target detectionalgorithm and collected stored grain insect data, thereby avoiding the drawbacks of poor robustness and generalization of manual design features, and improving the accuracy and efficiency of detectionand identification.

Description

technical field [0001] The invention relates to the field of artificial intelligence, and more specifically, to a method and device for detecting and identifying stored grain pests. Background technique [0002] In recent years, computer vision technology has made great progress, which is mainly due to the revolutionary development of artificial intelligence technology with deep learning as the core. With the continuous advancement of computer hardware and the massive data resources accumulated in the Internet era, giant neural networks can be trained and take advantage of them. Different from traditional computer vision technology, computer vision technology based on deep learning can automatically learn features from a large amount of data, has powerful feature representation capabilities, and can bring higher detection and recognition accuracy. [0003] The wide variety of stored grain pests poses difficulties for traditional computer vision methods of manually designing...

AI Technical Summary

Problems solved by technology

[0003] The wide variety of stored grain pests presents difficulties for traditional computer vision methods of manually designing features

The small target object and complex background of stored grain pest images also bring inconvenience to manual design features, while the target detection algorithm based on deep neural network can learn image features well without too much processing of the original image; for some For stored grain pests with a high degree of similarity in appearance (such as rice weevils and corn weevils), the features extracted manually by traditional methods cannot achieve good recognition results

Images