Image recognition method, device, electronic device and computer readable medium

Abstract

Embodiments of the present disclosure disclose image recognition methods, devices, electronic equipment, and computer-readable media. A specific implementation of the method includes: in response to receiving the request for detecting the shell of the electric meter box, collecting the shell image of the above-mentioned electric meter box; performing feature extraction processing on the above-mentioned shell image to obtain the feature vector of the shell image; inputting the feature vector of the above-mentioned shell image Into the pre-trained cascade classifier, the image recognition result is obtained; in response to detecting that the image recognition result meets the meter box maintenance condition, according to the image recognition result, the associated maintenance robot is controlled to maintain the meter box shell. This embodiment can timely maintain the abnormal electric meter box shell, reducing the potential safety hazard caused by the abnormal electric meter box shell.

Description

technical field [0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular, to an image recognition method, device, electronic equipment, and computer-readable medium. Background technique [0002] With the rapid development of electric power technology, a dense circuit network has been formed. Because the meter box runs 24 hours a day, it is difficult to maintain systematically. At present, when detecting and maintaining the shell of the electric meter box, the usual method is: by taking pictures of the shell of the electric meter box, using the VGG (Visual Geometry Group Network, Visual Geometry Group Network) 16 model to extract the image feature vector of the shell image of the electric meter box, responding In case of the falling of parts on the shell of the meter box or the detection of man-made damage to the meter box, the maintenance personnel shall be notified in time for maintenance. [0003] However, the follow...

AI Technical Summary

Problems solved by technology

[0004] First, the captured images of the electric meter box shells were not classified and detected, and the abnormal electric meter box shells (for example, the shells were rusted) could not be accurately identified, and the abnormal electric meter box shells were maintained in a timely manner, resulting in failures due to abnormal electric meter box shells. The safety hazards (such as leakage) of the meter box are relatively high;

[0005] Second, the vector dimension of the image feature vector extracted by VGG is high, resulting in a large amount of calculation and a long time for image detection

Images