Automatic Detection of Wind Turbine Blade Surface Cracks Based on UAV-Taken Images

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

116 Scopus Citations
View graph of relations


Original languageEnglish
Pages (from-to)7293-7303
Journal / PublicationIEEE Transactions on Industrial Electronics
Issue number9
Online published14 Mar 2017
Publication statusPublished - Sep 2017


In this paper, a data-driven framework is proposed to automatically detect wind turbine (WT) blade surface cracks based on images taken by unmanned aerial vehicles (UAVs). Haar-like features are applied to depict crack regions and train a cascading classifier for detecting cracks. Two sets of Haar-like features, the original and extended Haar-like features, are utilized. Based on selected Haar-like features, an extended cascading classifier is developed to perform the crack detection through stage classifiers selected from a set of base models, the LogitBoost, Decision Tree (DT), and Support Vector Machine (SVM). In the detection, a scalable scanning window is applied to locate crack regions based on developed cascading classifiers using the extended feature set. The effectiveness of the proposed data-driven crack detection framework is validated by both UAV-taken images collected from a commercial wind farm and artificially generated. The extended cascading classifier is compared with a cascading classifier developed by the LogitBoost only to show its advantages in the image-based crack detection. A computational study is performed to further demonstrate the success of the proposed framework in identifying the number of cracks and locating them in original images.

Research Area(s)

  • Blade image, crack detection, data-driven model, Haar-like features, wind turbine (WT)