Powerline Detection in Aerial Images Using Neural Networks

This study builds a machine learning (ML) model to identify the components of a powerline. The power infrastructure is subject to extreme weather conditions, wear, and environment changes. Power structures require routine maintenance to provide reliable power to the community. Inspections are often done by humans, requiring special equipment to climb up to great heights. This can be dangerous as there is electricity, and the risk of falling. This is a time-consuming process which can be streamlined with the use of drones. Drone-acquired images can be used where a ML model processes the data and finds all the issues present. Using an existing dataset a YOLOv8 deep neural network model was developed to identify the different components on a powerline. The developed model quickly unveiled the challenges of creating an accurate model for powerline inspection. It was found that the components on a powerline are very small and look so similar to each other, making accurate classifications very difficult. There were problems within the dataset identified such as the data disparity between classes. Overall, the model developed is a good starting point for further development, and much information was gained which will be used to further improve the model.