Multi-scale inspection image recognition method and device based on deep convolutional neural network

Abstract

The invention discloses a multi-scale inspection image recognition method and device based on a deep convolutional neural network, and the method comprises the steps: obtaining a video information image of an insulator in real time through an airborne visual sensor, processing the obtained video information image, and obtaining a to-be-detected image; inputting the to-be-detected image into a preliminary image recognition model for primary recognition, and outputting a recognition result or an unidentified image; further processing the unrecognized image, inputting the processed unrecognized image into the final image recognition model for secondary recognition, and outputting a recognition result; through two times of recognition, the problem that the calculation burden and the recognition time are increased due to the fact that a simple and easy-to-recognize graph still needs to be subjected to complex conversion is solved, the calculation burden is reduced, meanwhile, the deep convolutional neural network is improved, the generalization ability of an algorithm model is improved, the influence of a shielding object on a recognition result is solved, and the detection accuracy is further improved.

Description

technical field [0001] The invention relates to a power inspection image recognition method, in particular to a multi-scale inspection image recognition method and device based on a deep convolutional neural network. Background technique [0002] Smart grid is the trend and direction of power grid development, and smart substation is the substation link of smart grid, which is an important foundation and support for a strong smart grid. Due to the large number of high-voltage equipment in the power place of the substation and the complex environment, regular inspections are required to ensure power safety. At present, most substations still use manual inspections. With the continuous development of robot technology, more and more substations have begun to use inspections. Robot inspection and automation technology replace traditional manual work, which can reduce labor costs. [0003] The use of drones for inspections of transmission lines, although information collection i...

AI Technical Summary

Problems solved by technology

[0004] The technical problem mainly solved by the present invention is to provide a multi-feature fusion end-to-end target recognition method and device for power transmission system insulators, which can solve the problems of low recognition accuracy and large amount of calculation in the recognition method in the prior art

Images