An image stitching method for blades of wind turbine based on background removal preprocessing

The damage detection of the wind turbine (WT) blade is an important aspect of its health situation monitoring. In order to catch small damages, it is necessary to stitch the multi segment images of the blade to obtain a high resolution image. In image stitching, a blurring of the image is carried out to reduce the influence of noise. However, the preprocessing may decrease the amount of feature points and cannot avoid the interaction of feature points in the background and the target parts. To overcome these problems, a preprocessing method based on background removal is proposed. The idea of the method is to carry out image segmentation to get the background part, then the intensities of pixels in background part are replaced by a same value, such as average intensity. Employing the proposed preprocessing method, the image stitching is implemented on several groups of WT blade images. Feature points extraction result are compared between the proposed and the blurring preprocessing, which shows that the proposed method is more robust to the parameters in image stitching process. Moreover, the capability about image stitching and multi-image stitching of the proposed method is well verified by the experiment results.