Research Article
Multi-angle Identification of Small Target Faults in Transmission Lines Based on Improved YOLOX Algorithm
@INPROCEEDINGS{10.1007/978-3-031-31733-0_6, author={Shurong Peng and Jieni He and Huixia Chen and Bin Li and Jiayi Peng and Lijuan Guo}, title={Multi-angle Identification of Small Target Faults in Transmission Lines Based on Improved YOLOX Algorithm}, proceedings={Smart Grid and Innovative Frontiers in Telecommunications. 7th EAI International Conference, SmartGIFT 2022, Changsha, China, December 10-12, 2022, Proceedings}, proceedings_a={SMARTGIFT}, year={2023}, month={5}, keywords={Transmission Line Inspection Deep Learning Target Detection Multi Angle Channel Prunning}, doi={10.1007/978-3-031-31733-0_6} }- Shurong Peng
Jieni He
Huixia Chen
Bin Li
Jiayi Peng
Lijuan Guo
Year: 2023
Multi-angle Identification of Small Target Faults in Transmission Lines Based on Improved YOLOX Algorithm
SMARTGIFT
Springer
DOI: 10.1007/978-3-031-31733-0_6
Abstract
In the grid patrol work, there are some fault types with small targets in the line that needs to be detected. For the problem of partial feature loss when the target is small in UAV image recognition, CutMix is used to perform multi-angle image fusion on the line images captured by UAV, which is used to improve the accuracy of target detection. The improved YOLOX-pruning algorithm model is used for deep learning to prune and sparse the network structure, thus removing the redundant nodes of the network to improve the speed of target detection. In this experiment, manually labeled line images are fed into the model to train the features of the faulty components in the images. With a 50% reduction in channel parameter size and multi-angle feature fusion, the algorithm target detection speed is improved by 2.569 frames per second and the mAP value of the faulty data set is improved by 3.378%, reducing the amount of operation while improving the target detection accuracy.
