In this work, we propose a novel way of performing remote inspection of wooden utility poles, based on state-of-the-art computer vision techniques. We collect regular pictures, LiDAR scans and hyperspectral scans from a set of five poles, and apply state-of-the-art deep learning algorithms to detect and crop the poles in the pictures and scans to extract features from these. We then study the correlations of these features with pole density and surface depth by employing linear models. Our results show that our features can be used to predict density and depth with good accuracy, a MAE between 500 and 900 for a density range of 14000–22000 (unitless) and a MAE of 0.04 for a depth range of 0.6–0.9. This study emphasises the potential of both remote sensing and state-of-the-art deep learning for wooden pole inspection, with techniques suitable for real-world automation.