Challenges exist in the power generation efficiency and safety of marine current turbines (MCTs), as the MCT blades are often attached by foreign objects when operating underwater. It is essential for the stable operation of an MCT to recognize attachments timely and accurately. However, underwater imaging suffers from blurry edges due to light attenuation and scattering. It is challenging for accurate recognition through underwater images since blurry edges result in unclear edge features. To alleviate this problem, LAW-IFF Net is proposed in this paper, which mainly contains two parts. Firstly, this paper proposes to transform the local averages of feature maps into weight matrices, namely the locally average weighting (LAW) mechanism. It is intended to alleviate the edge gradient reduction caused by blurry edges. Secondly, the proposed improved feature fusion (IFF) mechanism aims to overcome the deviation caused by the feature fusion of different attention branches based on spatial attention. At the same time, the lightweight networks are combined with the proposed method to improve the computation speed and ensure the timeliness of recognition. Experimental results on the MCT dataset show the superiority of the proposed method in terms of accuracy and speed of attachment recognition in images with blurry edges. The experimental results on publicly available datasets show the applicability of the proposed method to other underwater images.
SeguraEMoralesRSomolinosJA. A strategic analysis of tidal current Energy conversion systems in the European Union. Appl Energy2018; 212: 527–551.
2.
LiuSHeJZhangD, et al. Research on thruster fault diagnosis of underwater vehicle. In: Global oceans 2020: Singapore – U.S, Gulf Coast, Biloxi, MS, USA, 5–30 October 2020, pp.1–6. New York: IEEE.
3.
ZhangZZhouFZhangC, et al. A personalized federated learning-based fault diagnosis method for data suffering from network attacks. Appl Intell 2023.
4.
XieTWangTHeQ, et al. A review of current issues of marine current turbine blade fault detection. Ocean Eng2020; 218: 108194.
5.
ZhangMWangTTangT, et al. An imbalance fault detection method based on data normalization and EMD for marine current turbines. ISA Trans2017; 68: 302–312.
6.
ZhangMTangTWangT. Multi-domain reference method for fault detection of marine current turbine. In: IECON 2017 – 43rd Annual conference of the IEEE industrial electronics society, Beijing, China, 29 October–1 November 2017, pp.8087–8092. New York: IEEE.
7.
ZhengYWangTXinB, et al. A sparse autoencoder and softmax regression based diagnosis method for the attachment on the blades of marine current turbine. Sensors2019; 19(4): 826.
8.
LiuRYangDWangT. MobileNet-Based diagnosis for image of tidal stream turbine blades’ attachments. Control Eng China. 2022; 29(10): 1810–1815.
9.
HowardAGZhuMChenB, et al. MobileNets: efficient convolutional neural networks for mobile vision applications. ArXiv2017; abs/1704.04861.
10.
PengHYangDWangT, et al. An adaptive coarse-fine semantic segmentation method for the attachment recognition on marine current turbines. Comput Electr Eng2021; 93: 107182.
11.
WangJLiBZhouY, et al. Compact and fast underwater segmentation network for autonomous underwater vehicles. In: Computer vision – ACCV 2020, Kyoto, Japan, 30 November–4 December 2020, pp.688–703. Cham: Springer.
12.
XuSZhangJQinX, et al. Deep retinex decomposition network for underwater image enhancement. Comput Electr Eng2022; 100: 107822.
13.
PertuzSPuigDGarciaMA. Analysis of focus measure operators for shape-from-focus. Pattern Recognit2013; 46(5): 1415–1432.
14.
IslamMJLuoPSattarJ. Simultaneous enhancement and super-resolution of underwater imagery for improved visual perception. ArXiv2020; abs/2002.01155.
15.
ZhouYWangJLiB, et al. Under-water scene segmentation by deep neural network. In: 2nd UK Robotics and Autonomous Systems conference, (UK-RAS 2019), Loughborough University, UK, 24 January 2019, pp.44–47. Loughborough: UK-RAS Network.
16.
IslamMJEdgeCXiaoY, et al. Semantic segmentation of underwater imagery: Dataset and benchmark. In: 2020 IEEE/RSJ international conference on intelligent Robots and Systems (IROS), Las Vegas, USA, 24 October 2020–24 January 2021, pp.1769–1776. New York: IEEE.
17.
MaZLiHWangZ, et al. An underwater image semantic segmentation method focusing on boundaries and a real underwater scene semantic segmentation dataset. ArXiv 2021. abs/2108.11727.
18.
ChenWLiuZZhangH, et al. A submarine pipeline segmentation method for noisy forward-looking sonar images using global information and coarse segmentation. Appl Ocean Res2021; 112: 102691.
19.
LiHQiuKChenL, et al. SCAttNet: Semantic segmentation network with spatial and channel attention mechanism for high-resolution remote sensing images. ArXiv2019; abs/1912.09121.
TakosG. A Survey on deep learning methods for semantic image segmentation in real-time. ArXiv2020; abs/2009.12942.
22.
Garcia-GarciaAOrts-EscolanoSOpreaSO, et al. A review on deep learning techniques applied to semantic segmentation. ArXiv2017. abs/1704.06857.
23.
ShelhamerELongJDarrellT. Fully convolutional networks for semantic segmentation. In: IEEE conference on Computer Vision and Pattern Recognition (CVPR), Boston, USA, 07–12 June 2015, pp.3431–3440. New York: IEEE.
24.
RonnebergerOFischerPBroxT. U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Munich, Germany, 5–9 October 2015, pp.234–241. Cham: Springer.
25.
BadrinarayananVKendallACipollaR. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell2017; 39(12): 2481–2495.
26.
ChenLCPapandreouGKokkinosI, et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell2018; 40(4): 834–848.
27.
ChenLCZhuYPapandreouG, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Computer vision – ECCV 2018, Munich, Germany, 8–14 September 2018, pp.833–851. Cham: Springer.
28.
ZhouYChenSWangY, et al. Review of research on lightweight convolutional neural networks. In: 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China, 12–14 June 2020, pp.1713–1720. New York: IEEE.
29.
ForrestNIMatthewWMKhalidA, et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1mb model size. ArXiv2016. abs/1602.07360.
30.
CholletF.Xception: deep learning with depth wise separable convolutions. In: 2017 IEEE conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, USA, 21–26 July 2017, pp.1800–1807. New York: IEEE.
31.
SandlerMHowardAZhuM, et al. MobileNetV2: inverted residuals and linear bottlenecks. In: 2018 IEEE/CVF conference on computer vision and pattern recognition, Salt Lake City, USA, 18–23 June 2018, pp.4510–4520. New York: IEEE.
32.
HowardASandlerMChenB, et al. Searching for MobileNetV3. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 27 October–2 November 2019, pp.1314–1324. New York: IEEE.
33.
GuoMHXuTXLiuJJ, et al. Attention mechanisms in computer vision: a survey. ArXiv2022. abs/2111.07624.
34.
MnihVHeessNGravesA, et al. Recurrent models of visual attention. In: Advances in Neural Information Processing Systems 27 (NIPS 2014), Montreal, Canada, January2014, pp.2204–2212. New York: Curran Associates.
35.
JaderbergMSimonyanKZissermanA, et al. Spatial transformer networks. In: Advances in Neural Information Processing Systems 28 (NIPS 2015), Montreal, Canada, January2015, pp.2017–2025. New York: Curran Associates.
36.
HuJShenLAlbanieS, et al. Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell2020; 42(8): 2011–2023.
YangCXieTWangT, et al. Blade attachment degree classification for marine current turbines using AGMF-DFA under instantaneous variable current speed. Proc IMechE, Part M: J Engineering2023; 237(2): 531–543.
39.
TanHLGelfandSBDelpEJ. A cost minimization approach to edge detection using simulated annealing. IEEE Trans Pattern Anal Mach Intell1992; 14(1): 3–18.
40.
MercyJLawanyaRNandhiniS, et al. Effective image deblurring based on improved image edge information and blur Kernel estimation. In: 2022 8th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India, 25–26 March 2022, pp.855–859. New York: IEEE.
41.
SharmaADronawatRJhapateA.Automatic diabetic retinopathy detection using roberts cross edge detection in DIP. In: 2021 10th IEEE international conference on Communication Systems and Network Technologies (CSNT), Bhopal, India, 18–19 June 2021, pp.363–368. New York: IEEE.
42.
WangJSunKChengT, et al. Deep high-resolution representation learning for visual recognition. IEEE Trans Pattern Anal Mach Intell2019; 43(10): 3349–3364.
43.
SimonyanKZissermanA. Very deep convolutional networks for large-scale image recognition. ArXiv 2014. abs/1409.1556.
44.
SunKXiaoBLiuD, et al. Deep high-resolution representation learning for human pose estimation. In: 2019 IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, 15–20 June 2019, pp.5686–5696. New York: IEEE.
