A multi-objective parallel detection algorithm for images of power transmission line corridors

The application of deep learning-based image recognition technology in remote monitoring of power transmission lines has improved the protection level of power transmission lines. However, since the current hidden danger detection is based on a single general algorithm, the accuracy of the detection results needs to be improved. In this paper, we proposed a multi-objective parallel detection algorithm for images of power transmission line corridors based on basic feature sharing. Firstly, we tested the detection effects of different detection algorithms on various types of hidden danger images, based on which benchmark algorithms are selected and optimized for various types of hidden dangers. After that, we designed a multi-objective parallel detection framework to implement the parallel detection of the above three detection algorithms. The experimental results show that the multiobjective parallel detection algorithm proposed in this paper can improve the detection accuracy, as well the detection speed.