Back to Search
Start Over
Image Enhanced Mask R-CNN: A Deep Learning Pipeline with New Evaluation Measures for Wind Turbine Blade Defect Detection and Classification
- Source :
- Journal of Imaging, Volume 7, Issue 3, Journal of Imaging, Vol 7, Iss 46, p 46 (2021)
- Publication Year :
- 2021
- Publisher :
- Multidisciplinary Digital Publishing Institute, 2021.
-
Abstract
- Demand for wind power has grown, and this has increased wind turbine blade (WTB) inspections and defect repairs. This paper empirically investigates the performance of state-of-the-art deep learning algorithms, namely, YOLOv3, YOLOv4, and Mask R-CNN for detecting and classifying defects by type. The paper proposes new performance evaluation measures suitable for defect detection tasks, and these are: Prediction Box Accuracy, Recognition Rate, and False Label Rate. Experiments were carried out using a dataset, provided by the industrial partner, that contains images from WTB inspections. Three variations of the dataset were constructed using different image augmentation settings. Results of the experiments revealed that on average, across all proposed evaluation measures, Mask R-CNN outperformed all other algorithms when transformation-based augmentations (i.e., rotation and flipping) were applied. In particular, when using the best dataset, the mean Weighted Average (mWA) values (i.e., mWA is the average of the proposed measures) achieved were: Mask R-CNN: 86.74%, YOLOv3: 70.08%, and YOLOv4: 78.28%. The paper also proposes a new defect detection pipeline, called Image Enhanced Mask R-CNN (IE Mask R-CNN), that includes the best combination of image enhancement and augmentation techniques for pre-processing the dataset, and a Mask R-CNN model tuned for the task of WTB defect detection and classification.
- Subjects :
- Turbine blade
Computer science
defect detection
Pipeline (computing)
convolutional neural network
02 engineering and technology
wind turbine blade
lcsh:Computer applications to medicine. Medical informatics
Convolutional neural network
lcsh:QA75.5-76.95
Article
evaluation measure
Image (mathematics)
law.invention
YOLOv4
law
0202 electrical engineering, electronic engineering, information engineering
Radiology, Nuclear Medicine and imaging
mask R-CNN
lcsh:Photography
Electrical and Electronic Engineering
Wind power
business.industry
Deep learning
deep learning
Pattern recognition
021001 nanoscience & nanotechnology
lcsh:TR1-1050
YOLOv3
Computer Graphics and Computer-Aided Design
Transformation (function)
region-based convolutional neural networks
lcsh:R858-859.7
020201 artificial intelligence & image processing
Computer Vision and Pattern Recognition
Artificial intelligence
lcsh:Electronic computers. Computer science
0210 nano-technology
business
Rotation (mathematics)
Subjects
Details
- Language :
- English
- ISSN :
- 2313433X
- Database :
- OpenAIRE
- Journal :
- Journal of Imaging
- Accession number :
- edsair.doi.dedup.....1c0c576cac4f75ecf23633bd0dc1d3dc
- Full Text :
- https://doi.org/10.3390/jimaging7030046