{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T06:32:20Z","timestamp":1784615540034,"version":"3.55.0"},"reference-count":26,"publisher":"SAGE Publications","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2021,3,4]]},"abstract":"<jats:p>A safe operation protocol of the wind blades is a critical factor to ensure the stability of a wind turbine. Sensors are most commonly applied for defect detection on wind turbine blades (WTBs). However, due to the high cost and the sensitivity to stochastic noise, computer vision-guided automatic detection remains a challenge for surface defect detection on WTBs in particularly, its accuracy in locating defects is yet to be optimized. In this paper, we developed a visual inspection model that can automatically and precisely classify and locate the surface defects, through the utilization of a deep learning framework based on the Cascade R-CNN. In order to obtain high mean average precision (mAP) according to the characteristics of the dataset, a model named Contextual Aligned-Deformable Cascade R-CNN (CAD Cascade R-CNN) using improved strategies of transfer learning, Deformable Convolution and Deformable RoI Align, as well as context information fusion is proposed and a dataset with surface defects categorized and labeled as crack, breakage and oil pollution is generated. Moreover to alleviate the problem of false detection under a complex background, an improved bisecting k-means is presented during the test process. The adaptability and generalization of the proposed CAD Cascade R-CNN model were validated by each type of defects in dataset and different IoU thresholds, whereas, each of the above improved strategies was verified by gradual ablation experiments. Finally experiments that compared with the baseline Cascade R-CNN, Faster R-CNN and YOLO-v3 demonstrate its superiority over these existing approaches with a maximum of 92.1% mAP.<\/jats:p>","DOI":"10.3233\/ida-205143","type":"journal-article","created":{"date-parts":[[2021,3,9]],"date-time":"2021-03-09T12:48:19Z","timestamp":1615294099000},"page":"463-482","source":"Crossref","is-referenced-by-count":38,"title":["Automatic image detection of multi-type surface defects on wind turbine blades based on cascade deep learning network"],"prefix":"10.1177","volume":"25","author":[{"given":"Yulin","family":"Mao","sequence":"first","affiliation":[{"name":"Beijing Jiaotong University, School of Mechanical, Electronic and Control Engineering, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuangxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, School of Mechanical, Electronic and Control Engineering, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingli","family":"Yu","sequence":"additional","affiliation":[{"name":"Liverpool John Moores University, School of Engineering, Control Systems Center, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juchao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, School of Mechanical, Electronic and Control Engineering, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","reference":[{"key":"10.3233\/IDA-205143_ref1","doi-asserted-by":"publisher","first-page":"2858","DOI":"10.3390\/s17122858","article-title":"Hybrid signal processing technique to improve the defect estimation in ultrasonic non-destructive testing of composite structures","volume":"12","author":"Tiwari","year":"2017","journal-title":"Sensors"},{"key":"10.3233\/IDA-205143_ref2","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1016\/j.renene.2014.11.030","article-title":"Transformation algorithm of wind turbine blade moment signals for blade condition monitoring","volume":"1","author":"Lee","year":"2015","journal-title":"Renewable Energy"},{"key":"10.3233\/IDA-205143_ref3","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1260\/0309-524X.38.6.575","article-title":"Feasibility of automatic detection of surface cracks in wind turbine blades","volume":"6","author":"Zhang","year":"2014","journal-title":"Wind Engineering"},{"key":"10.3233\/IDA-205143_ref4","doi-asserted-by":"publisher","first-page":"2059","DOI":"10.1049\/iet-ipr.2018.5542","article-title":"Detection and analysis of large-scale WT blade surface cracks based on UAV-taken images","volume":"11","author":"Peng","year":"2018","journal-title":"IET Image Processing"},{"key":"10.3233\/IDA-205143_ref5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIE.2017.2682037","article-title":"Automatic detection of wind turbine blade surface cracks based on UAV-taken images","volume":"1","author":"Wang","year":"2017","journal-title":"IEEE Transactions on Industrial Electronics"},{"key":"10.3233\/IDA-205143_ref6","doi-asserted-by":"publisher","first-page":"1360","DOI":"10.1016\/j.optlaseng.2013.05.002","article-title":"Application of a He3Ne infrared laser source for detection of geometrical dimensions of cracks and scratches on finished surfaces of metals","volume":"12","author":"Nazaryan","year":"2013","journal-title":"Optics and Lasers in Engineering"},{"key":"10.3233\/IDA-205143_ref7","doi-asserted-by":"publisher","first-page":"1531","DOI":"10.1109\/tsmcc.2012.2198814","article-title":"A visual detection system for rail surface defects","volume":"6","author":"Li","year":"2012","journal-title":"IEEE Transactions on Systems Man & Cybernetics Part C"},{"key":"10.3233\/IDA-205143_ref8","first-page":"1648","article-title":"Surface defect detection system for camshaft based on computer vision","volume":"6","author":"Sun","year":"2013","journal-title":"Infrared and Laser Engineering"},{"key":"10.3233\/IDA-205143_ref9","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1016\/j.patcog.2011.07.025","article-title":"Wavelet-based defect detection in solar wafer images with inhomogeneous texture","volume":"2","author":"Li","year":"2012","journal-title":"Pattern Recognition"},{"key":"10.3233\/IDA-205143_ref10","doi-asserted-by":"crossref","unstructured":"J. Redmon, S.K. Divvala, R.B. Girshick and A. Farhadi, You only look once: Unified, real-time object detection, in: IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"10.3233\/IDA-205143_ref11","doi-asserted-by":"crossref","unstructured":"W. Liu et al., SSD: single shot multibox detector, in: European Conference on Computer Vision, 2016, pp. 21\u201337.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"10.3233\/IDA-205143_ref12","doi-asserted-by":"crossref","unstructured":"J. Tao et al., An object detection system based on YOLO in traffic scene, in: The 6th International Conference on Computer Science and Network Technology, 2017, pp. 315\u2013319.","DOI":"10.1109\/ICCSNT.2017.8343709"},{"key":"10.3233\/IDA-205143_ref13","doi-asserted-by":"publisher","first-page":"011002","DOI":"10.3788\/LOP56.011002","article-title":"Real-time detection based on improved single shot multibox detector","volume":"1","author":"Chen","year":"2019","journal-title":"Laser & Optoelectronics Progress"},{"key":"10.3233\/IDA-205143_ref14","doi-asserted-by":"publisher","first-page":"043023","DOI":"10.1117\/1.JEI.28.4.043023","article-title":"Automatic visual defects inspection of wind turbine blades via YOLO-based small object detection approach","volume":"4","author":"Qiu","year":"2019","journal-title":"Journal of Electronic Imaging"},{"key":"10.3233\/IDA-205143_ref15","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"6","author":"Ren","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/IDA-205143_ref16","unstructured":"K.M. He et al., Mask R-CNN, in: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, pp. 2980\u20132988."},{"key":"10.3233\/IDA-205143_ref18","doi-asserted-by":"publisher","first-page":"053305","DOI":"10.1063\/1.5113532","article-title":"Wind turbine blade surface inspection based on deep learning and UAV-taken images","volume":"5","author":"Xu","year":"2019","journal-title":"Journal of Renewable and Sustainable Energy"},{"key":"10.3233\/IDA-205143_ref19","doi-asserted-by":"crossref","unstructured":"Z.W. Cai and N. Vasconcelos, Cascade R-CNN: Delving into High Quality Object Detection, in: IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6154\u20136162.","DOI":"10.1109\/CVPR.2018.00644"},{"key":"10.3233\/IDA-205143_ref20","doi-asserted-by":"crossref","unstructured":"J. Dai et al., Deformable Convolutional Network, in: IEEE International Conference on Computer Vision (ICCV), 2017, pp. 764\u2013773.","DOI":"10.1109\/ICCV.2017.89"},{"key":"10.3233\/IDA-205143_ref21","unstructured":"K.M. He et al., Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, in: IEEE International Conference on Computer Vision, IEEE Computer Society, 2015, pp. 1026\u20131034."},{"key":"10.3233\/IDA-205143_ref22","doi-asserted-by":"crossref","unstructured":"R. Girshick et al., Rich feature hierarchies for accurate object detection and semantic segmentation, in: IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 580\u2013587.","DOI":"10.1109\/CVPR.2014.81"},{"key":"10.3233\/IDA-205143_ref23","doi-asserted-by":"crossref","unstructured":"R. Girshick, Fast R-CNN, in: IEEE International Conference on Computer Vision, 2015, pp. 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"10.3233\/IDA-205143_ref24","doi-asserted-by":"crossref","unstructured":"M. Lan, Y.P. Zhang, L.F. Zhang and B. Du, Defect Detection from UAV Images Based on Region-Based CNNs, in: IEEE International Conference on Data Mining Workshops, 2018, pp. 385\u2013390.","DOI":"10.1109\/ICDMW.2018.00063"},{"key":"10.3233\/IDA-205143_ref25","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","article-title":"Selective search for object recognition","volume":"2","author":"Uijlings","year":"2013","journal-title":"International Journal of Computer Vision"},{"key":"10.3233\/IDA-205143_ref26","unstructured":"K.M. He et al., Deep Residual Learning for Image Recognition, in: IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, 2016, pp. 770\u2013778."},{"key":"10.3233\/IDA-205143_ref27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"3","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-205143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:19:01Z","timestamp":1777454341000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-205143"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,4]]},"references-count":26,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3233\/ida-205143","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,4]]}}}