Detecting and Positioning of Wind Turbine Blade Tips for UAV-Based Automatic Inspection

Abstract

Wind turbine detecting and blade tip positioning are essential parts of UAV-based automatic inspection. Previous methods which adopt LiDAR or ultrasonic sensor may cause cost increasement and system instability. We propose a vision-based approach for blade tip detecting and positioning. More precisely, we first detect each structure of wind turbine by combining Mask R-CNN detector and shape constraints. The pixel coordinates of blade tips can be extracted and then be used to solve a PnP problem. Finally we get GPS coordinates of blade tips which are useful for achieving path planning during the inspection. We evaluate the method on a well-annotated wind turbine datasets. The experimental results show the effectiveness and feasibility of the proposed method.