WaveGNet: Wavelet-Guided Deep Learning for Efficient Aerial Power Line Detection

Numerous approaches exist for unmanned aerial vehicles (UAVs) to perceive the surrounding environment. CMOS and CCD image sensors are commonly used in machine perception due to their cost-effectiveness and ease of acquisition. The use of image sensors for UAV power line inspection presents challenges due to the disorganized nature of the power line aerial images and the abundance of redundant background information. To address these challenges, we propose a novel approach that combines wavelet transform theory and deep learning methods. The image acquired by the image sensor is decomposed into low-frequency coefficients and high-frequency coefficients using wavelet transform, and the high-frequency coefficients are used to guide the low-frequency coefficients to generate a feature map of weak semantic information. This approach helps suppress complex and redundant background feature information, enhancing the detection of slender power lines. Furthermore, we incorporate an asymmetric dilated convolution global attention mechanism, guided by wavelet decomposition, to further enhance the features of slender power lines. This attention mechanism focuses on key regions and details, improving the power line detection process. Finally, we present a lightweight power line detection algorithm, WaveGNet, which combines deep learning and wavelet transform. Through extensive experiments on pinhole and fish-eye aerial power line datasets, WaveGNet achieves a remarkable trade-off of speed and accuracy, surpassing current lightweight segmentation models. This algorithm offers a novel approach for power line detection using image sensors and provides valuable insights for future deployment on UAVs.