Image recognition method for bird species related to bird-related fault of power transmission line

Abstract

The invention discloses an image recognition method for bird species related to a bird-related fault of a power transmission line. The image recognition method comprises the following steps of: firstly, establishing a bird-related fault related bird species image database by collecting bird species information around the power transmission line, and performing background removal preprocessing on a bird species image based on a category activation graph method; then, establishing a learning model by using four deep convolutional neural networks, pre-training the learning model through an ImageNet data set, finely tuning the pre-trained model network structure, re-training the finely-tuned model by using the pre-processed bird species image training set, and classifying and identifying a test set; and finally, according to the classification accuracy of the four network models, establishing a bird-related fault related bird species image recognition model fused with the multi-convolutional network by adopting a linear weighting method, and carrying out classification recognition on bird species images. According to the invention, a correct bird identification method and means can be provided for operation and maintenance personnel of the power transmission line, differential prevention and control of bird-related faults can be realized, and the trip-out rate of the bird-related faults can be reduced.

Description

technical field [0001] The invention relates to the field of power transmission lines, in particular to an image recognition method for bird species related to bird-related faults in power transmission lines. Background technique [0002] With the large-scale construction of the power grid and the improvement of the ecological environment, the contradiction between bird activities and transmission lines has become increasingly prominent, and bird faults have become an important reason for line trips. Due to the suddenness of the bird failure, it is often impossible to determine what kind of bird caused the failure, and it is difficult to install targeted bird prevention measures. Although the power grid operation unit has compiled a list of bird species related to transmission line bird faults and the types of faults that may be caused by them, due to the lack of ornithological knowledge of the operation and maintenance personnel, although they can be photographed around the...

AI Technical Summary

Problems solved by technology

[0003] At present, the research on image recognition of bird species related to transmission lines is mainly limited to the coarse-grained binary classification problem of bird detection, and there are few studies on multi-classification recognition of bird species that are endangered by bird faults on transmission lines. The number of bird images collected is limited, and it is easy to have insufficient generalization ability when used to train a brand new network, and the network trained by using a specific bird image data set is difficult to match the bird image recognition related to bird-related faults task

Images