Robust Wind Turbine Blade Segmentation from RGB Images in the Wild (2306.14810v1)
Abstract: With the relentless growth of the wind industry, there is an imperious need to design automatic data-driven solutions for wind turbine maintenance. As structural health monitoring mainly relies on visual inspections, the first stage in any automatic solution is to identify the blade region on the image. Thus, we propose a novel segmentation algorithm that strengthens the U-Net results by a tailored loss, which pools the focal loss with a contiguity regularization term. To attain top performing results, a set of additional steps are proposed to ensure a reliable, generic, robust and efficient algorithm. First, we leverage our prior knowledge on the images by filling the holes enclosed by temporarily-classified blade pixels and by the image boundaries. Subsequently, the mislead classified pixels are successfully amended by training an on-the-fly random forest. Our algorithm demonstrates its effectiveness reaching a non-trivial 97.39% of accuracy.
- M. Civera and C. Surace, “Non-destructive techniques for the condition and structural health monitoring of wind turbines: A literature review of the last 20 years,” Sensors, vol. 22, no. 4, pp. 1627, 2022.
- “Distributed demand side management with stochastic wind power forecasting,” IEEE Transactions on Control Systems Technology, vol. 30, no. 1, pp. 97–112, 2022.
- “DMNet: A new few-shot framework for wind turbine surface defect detection,” Machines, vol. 10, no. 6, pp. 487, 2022.
- “Wind turbine surface damage detection by deep learning aided drone inspection analysis,” Energies, vol. 12, no. 4, pp. 676, 2019.
- “Road crack detection using deep convolutional neural network,” in International Conference on Image Processing, 2016, pp. 3708–3712.
- “Bidirectional pyramid networks for semantic segmentation,” in Asian Conference on Computer Vision, 2020.
- “Multicopter unmanned aerial vehicle for automated inspection of wind turbines,” in 2016 24th Mediterranean Conference on Control and Automation (MED). IEEE, 2016, pp. 244–249.
- “Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs,” IEEE transactions on pattern analysis and machine intelligence, vol. 40, no. 4, pp. 834–848, 2017.
- “Switchable whitening for deep representation learning,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 1863–1871.
- J. Wang and T. Lukasiewicz, “Rethinking bayesian deep learning methods for semi-supervised volumetric medical image segmentation,” in Computer Vision and Pattern Recognition, 2022, pp. 182–190.
- “BI-GConv: Boundary-aware input-dependent graph convolution for biomedical image segmentation,” in British Machine Vision Conference, 2021.
- “Disentangled non-local neural networks,” in European Conference on Computer Vision. Springer, 2020, pp. 191–207.
- “Generic image segmentation in fully convolutional networks by superpixel merging map,” in Asian Conference on Computer Vision, 2020.
- “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in European Conference on Computer Vision, 2018, pp. 801–818.
- Hang Zhang et al., “Resnest: Split-attention networks,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 2736–2746.
- “U-net: Convolutional networks for biomedical image segmentation,” in International Conference on Medical image computing and computer-assisted intervention, 2015, pp. 234–241.
- “Unetformer: A unified vision transformer model and pre-training framework for 3d medical image segmentation,” arXiv preprint arXiv:2204.00631, 2022.
- P. Soille, Morphological image analysis: principles and applications, Springer Science & Business Media, 1999.
- L. Breiman, “Random forests,” Machine learning, vol. 45, no. 1, pp. 5–32, 2001.
- “Focal loss for dense object detection,” in International Conference on Computer Vision, 2017, pp. 2980–2988.
- “Physiological inspired deep neural networks for emotion recognition,” IEEE Access, vol. 6, pp. 53930–53943, 2018.
- D.P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.