An Infrared Image Stitching Method for Wind Turbine Blade Using UAV Flight Data and U-Net

Abstract

Infrared image stitching of wind turbine blades is a challenging task due to weak texture and low contrast. To address this issue, an infrared image stitching method for wind turbine blades based on unmanned aerial vehicle (UAV) flight data and u-shaped neural network (U-Net) is proposed in this article. Remove complex background using U-Net semantic segmentation network and retain the complete area of the blades to be stitched. The rotation angle of blades is calculated to unify the orientation of the blades in all images to be horizontal, the increasing pixel between adjacent images is calculated by the velocity, diagonal field of view (DFOV), and object distance of UAV, and the scaling coefficient is calculated to align the upper and lower edges of blades. Based on the above parameters, the panoramic infrared images of wind turbine blades can be finally obtained. Through comparative analysis and quantitative evaluation with the widely used image stitching algorithms, it is shown that the proposed method can obtain better quality results.