Instrument identification method, mobile device and storage medium

Abstract

The invention discloses an instrument identification method, a mobile device and a storage medium, and the method comprises the following steps: employing a trained convolutional neural network to perform preliminary detection and positioning of a collected instrument image, so as to preliminarily obtain an instrument detection result display region; an image processing method is used to identifyand interpret the preliminarily acquired instrument detection result display area; and returning an identification and interpretation result to the edge node of the pre-constructed cloud edge cooperative network, and further returning the identification and interpretation result to the fog node and the cloud center through the edge node. According to the invention, the convolutional neural networkis combined with the image processing method to identify the instrument, the calculation amount can be reduced, and the accuracy and real-time performance of the identification result are improved; the calculation processing process is realized by the mobile equipment, the identification result is returned to the fog node and the cloud center in sequence through the edge node, access of vast mobile equipment is supported, the purpose of reliably transmitting the identification result in real time can be achieved, and data processing and analysis of the cloud center are facilitated.

Description

technical field [0001] The invention relates to an instrument identification method, a mobile device and a storage medium, and belongs to the technical field of visual inspection. Background technique [0002] At present, the conventional method of substation instrument identification is manual identification. Manual identification has high flexibility, but it is not considerable in terms of applicability, reliability and economic benefits. For this reason, in the prior art, a method for instrument identification by remote collection of pictures or videos has also been developed, which can replace manual identification, by identifying and processing the video or image information remotely transmitted to the background, and finally get the identification the result of. The remote collection of image and video information for processing greatly reduces the workload of manual inspection, and has great advantages in applicability, reliability, economy, and universality. Howeve...

AI Technical Summary

Problems solved by technology

However, with the increase in the number of mobile terminal access and the requirements for real-time and security of the network, the current network structure uses a large number of image and video transmissions, resulting in more and more serious network delay and security issues, which cannot adapt Security and real-time requirements

Images