Method for intelligent automatic identification of transmission circuit parts

Abstract

The present invention discloses a method for intelligent automatic identification of transmission circuit parts. The method comprises the following steps: S1, the original image of an unmanned aerial vehicle polling transmission circuit is taken as an image source, positions of parts such as a tower, an insulator, a grading ring, a spacer and the like in the original image, attribute labels are added for each part, and a transmission circuit part identification training data set is constructed; S2, a convolutional neural network and a feature pyramid network is employed to extract the multi-layer features of a transmission circuit image; S3, the extracted image features and the calibrated label data are taken as training input data, a position sensitive scoring graph is calculated, the loss value of classification and regression networks is calculated, and the stochastic gradient descent is employed to optimize parameters of classification network and the regression network so as to realize optimal classification and location of the parts in the training data; and S4, according to the training parameters obtained according to the transmission network identification training, the transmission circuit polling data is introduced in batch to realize automatic location and classification of the parts.

Description

technical field [0001] The invention relates to the field of digital image processing, in particular to a method for intelligent automatic identification of power transmission line components. Background technique [0002] The transmission line is the skeleton support of the power grid. The normal operation of the transmission line directly affects the healthy development of the entire national economy and the normal life of the people. The UAV is equipped with special inspection equipment to collect data on the transmission line, and uses image processing technology to analyze and collect data to determine the operating status of the transmission line. A UAV inspection mission can obtain a large amount of image or video information of the transmission line. After the inspection is completed, the inspection personnel will conduct manual interpretation to determine the location of the transmission line components and their existing defects. Due to the large amount of data, m...

AI Technical Summary

Problems solved by technology

Patent CN201610906708.2 uses the Faster R-CNN method to identify small parts of transmission lines, but the proportion of auxiliary parts of transmission lines in the image varies greatly. This method does not take into account the spatial information of the image, and the final recognition of transmission line components is accurate The rate needs to be improved and increased

Images