Unsupervised model-driven neural network based image denoising for transmission line monitoring

Abstract

With the expansion of smart grid and Internet of things (IoT) technology, edge computing has a wide variety of applications in these domains. The criteria for real-time monitoring and accuracy are particularly high in the field of online real-time monitoring of electricity lines. Based on edge technology, high-quality real-time monitoring can be performed for transmission lines using image processing techniques. Therefore, we propose an image denoising method, which can learn clean images using a stream-based generative model. The stream model uses a two-stage approach in the network to handle the different training periods of denoising separately. Experimental results show that the proposed method has good denoising performance.

References

[1] KrestinskayaO, JamesA P, ChuaL O. Neuromemristive circuits for edge computing: a review[J]. IEEE transactions on neural networks and learning systems, 2019, 31(1):4-23

[2] ShiW, CaoJ, ZhangQ, et al.. Edge computing: vision and challenges[J]. IEEE internet of things journal, 2016, 3(5):637-646

[3] ChenS, WenH, WuJ, et al.. Internet of things based smart grids supported by intelligent edge computing[J]. IEEE access, 2019, 7: 74089-74102

[4] MEHMOOD M Y, OAD A, ABRAR M, et al. Edge computing for IoT-enabled smart grid[J]. Security and communication networks, 2021.

[5] SAMIE F, BAUER L, HENKEL J. Edge computing for smart grid: an overview on architectures and solutions[J]. IoT for smart grids, 2019: 21–42.

[6] HuangY, LuY, WangF, et al.. An edge computing framework for real-time monitoring in smart grid[C], 2018, New York, IEEE: 99-108

[7] LiH, DongY, YinC, et al.. A real-time monitoring and warning system for power grids based on edge computing[J]. Mathematical problems in engineering, 2022, 2022: 8719227

[8] KhodayarM, LiuG, WangJ, et al.. Deep learning in power systems research: a review[J]. CSEE journal of power and energy systems, 2020, 7(2):209-220

[9] LI B, XIAO C, WANG L, et al. Dense nested attention network for infrared small target detection[EB/OL]. (2021-06-01) [2022-09-24]. https://arxiv.org/abs/2106.00487.

[10] HanM, LiuH. Retraction note: super-resolution restoration of degraded image based on fuzzy enhancement[J]. Arabian journal of geosciences, 2022, 15(9):1-1

[11] ZhangK, ZuoW, GuS, et al.. Learning deep CNN denoiser prior for image restoration[C], 2017, New York, IEEE: 3929-3938

[12] LiuW, LeeJ. A 3-D atrous convolution neural network for hyperspectral image denoising[J]. IEEE transactions on geoscience and remote sensing, 2019, 57(8):5701-5715

[13] LiuL, OuyangW, WangX, et al.. Deep learning for generic object detection: a survey[J]. International journal of computer vision, 2020, 128(2):261-318

[14] CALVARONS A F. Improved noise2noise denoising with limited data[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 20–25, 2021, Nashville, TN, USA. New York: IEEE, 202: 796–805.

[15] KrullA, BuchholzT O, JugF. Noise2void-learning denoising from single noisy images[C], 2019, New York, IEEE: 2129-2137

[16] UlyanovD, VedaldiA, LempitskyV. Deep image prior[C], 2018, New York, IEEE: 9446-9454

[17] OnishiY, HashimotoF, OteK, et al.. Anatomical-guided attention enhances unsupervised PET image denoising performance[J]. Medical image analysis, 2021, 74: 102226

[18] AgcaogluO, SilvaR F, CalhounV. Multimodal fusion of brain imaging data with joint non-linear independent component analysis[C], 2022, New York, IEEE: 1-5

[19] CaiZ, XiongZ, XuH, et al.. Generative adversarial networks: a survey toward private and secure applications[J]. ACM computing surveys, 2021, 54(6):1-38

[20] KINGMA D P, DHARIWAL P. Glow: generative flow with invertible 1×1 convolutions[EB/OL]. (2018-07-09) [2022-09-24]. https://arxiv.org/abs/1807.03039.

[21] KINGMA D P, BA J. Adam: a method for stochastic optimization[J]. Computer Science, 2014.

[22] HeK, ZhangX, RenS, et al.. Deep residual learning for image recognition[C], 2016, New York, IEEE: 770-778