Power Line Detection for Aerial Navigation Using Deep Learning

Power line detection is crucial for ensuring the safety of low-altitude aircraft such as uncrewed aerial vehicles and helicopters. Al-though many traditional techniques have been used for this task, their detection accuracy has often been limited. To address this issue, we propose a deep learning–based approach for power line detection that demonstrates strong performance on both visible-spectrum and infrared images, achieving detection accuracies of 91.75% and 99.12%, respectively. The proposed method effectively identifies power lines across varying environmental conditions and complex backgrounds. Its stable performance over a wide range of experimental settings highlights the robustness of the approach. In addition, the superior effectiveness of infrared imagery compared to visible-band images, as observed in this study, is particularly noteworthy.