(49-5) 09 * << * >> * Русский * English * Содержание * Все выпуски

An efficient U-shaped transformer network for low-light power image denoising
J. Zhang 1, W.X. Huang 1, M.X. Lu 1, L.W. Li 1, X. Wang 1, Y.P. Shen 1, Y.F. Wang 1

1 College of Electrical and Information Engineering,
Zhengzhou University of Light Industry, Zhengzhou 450002, China

  PDF, 4392 kB

DOI: 10.18287/2412-6179-CO-1629

Страницы: 775-784.

Язык статьи: English.

Аннотация:
Unmanned aerial vehicle (UAV) inspection of transmission lines has been widely applied in recent years. However, in low-light weather conditions, random noise often appears in the captured transmission line images due to the combined effects of brightness, electromagnetic interference, and camera sensor limitations. This noise significantly undermines the quality and accuracy of the inspection. To address this challenge, we propose a novel transformer-based image denoising method called EUformer. First, we propose the Global Feature Compensator (GFC) module, which adaptively captures remote pixel dependencies for improved global image modelling. Second, we designed the Mixed-Gated feed-forward network (MG-FFN), to enhance the aggregation of local contextual information. Finally, the loss function is optimized by introducing a new regular term, effectively addressing negative effects such as artefacts in the reconstructed images. To assess the denoising capabilities of the EUformer model proposed in this study for transmission line images, we developed a benchmark dataset specifically for low-light transmission line image denoising. The results of extensive experiments demonstrate that the EUformer model achieves competitive performance while maintaining low complexity.

Ключевые слова:
deep learning, transformer, low-light transmission line, image denoising.

Citation:
Zhang J, Huang WX, Lu MX, Li LW, Wang X, Shen YP, Wang YF. An efficient U-shaped transformer network for low-light power image denoising. Computer Optics 2025; 49(5): 775-784. DOI: 10.18287/2412-6179-CO-1629.

References:
  1. Nguyen VN, Jenssen R, Roverso D. Automatic autonomous vision-based power line inspection: A review of current status and the potential role of deep learning. Int J Electr Power Energy Syst 2018; 99: 107-120. DOI: 10.1016/j.ijepes.2017.12.016.
  2. Liba O, Murthy K, Tsai Y-T, et al. Handheld mobile photography in very low light. ACM Trans Graph 2019; 38(6): 164. DOI: 10.1145/3355089.3356508.
  3. Dabov K, Foi A, Katkovnik V, Egiazarian K. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans Image Process 2007; 16(8): 2080-2095. DOI: 10.1109/TIP.2007.901238.
  4. Lebrun M, Buades A, Morel J-M. A nonlocal bayesian image denoising algorithm, SIAM J Imaging Sci 2013; 6(3): 1665-1688. DOI: 10.1137/120874989.
  5. Xu J, Zhang L, Zhang D. A trilateral weighted sparse coding scheme for real-world image denoising. In Book: Ferrari V, Hebert M, Sminchisescu C, Weiss Y, eds. Computer vision – ECCV 2018. 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part VIII. Cham, Switzerland: Springer Nature Switzerland AG; 2018: 20-36. DOI: 10.1007/978-3-030-01237-3_2.
  6. Rudin LI, Osher S, Fatemi E. Nonlinear total variation based noise removal algorithms. Phys D: Nonlinear Phenom 1992; 60(1-4): 259-268. DOI: 10.1016/0167-2789(92)90242-F.
  7. Krasheninnikov VR, Kuvayskova YE, Malenova OE, Subbotin AU. Models and filtering of circular images with harmonic components of the covariance function. Procedia Comput Sci 2021; 192: 4047-4054. DOI: 10.1016/j.procs.2021.09.179.
  8. Andriyanov NA, Vasiliev KK, Dementiev VE, Belyanchikov AV. Restoration of spatially inhomogeneous images based on a doubly stochastic model. Optoelectron Instrum Data Process 2022; 58(5): 465-471. DOI: 10.3103/S8756699022050028.
  9. Zhang J, Wang FX, Zhang HL, Shi XL. A Novel CS 2G-starlet denoising method for high noise astronomical image. Opt Laser Technol 2023; 163: 109334. DOI: 10.1016/j.optlastec.2023.109334.
  10. Zhang K, Zuo W, Chen Y, Meng D, Zhang L. Beyond a Gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Trans Image Process 2017; 26(7): 3142-3155. DOI: 10.1109/TIP.2017.2662206.
  11. Haghi P, Tan C, Guo A, Wu C, Liu D, Li A, Skjellum A, Geng T, Herbordt M. Smartfuse: Reconfigurable smart switches to accelerate fused collectives in hpc applications. Proc 38th ACM Int Conf on Supercomputing (ICS ’24) 2024: 413-425. DOI: 10.1145/3650200.3656616.
  12. Lukas J, Fridrich J, Goljan M. Digital camera identification from sensor pattern noise. IEEE Trans Inf Forensics Secur 2006; 1(2): 205-214. DOI: 10.1109/TIFS.2006.873602.
  13. Yang L, Wang QF, Chi JF, et al. EAVE: Efcient product attribute value extraction via lightweight sparse-layer interaction. arXiv Preprint. 2024. Source: <https://arxiv.org/abs/2406.06839>.     DOI: 10.18653/v1/2024.findings-emnlp.80.
  14. Zhang J, Wang F, Zhang H, Shi X. Compressive sensing spatially adaptive total variation method for high-noise astronomical image denoising. Vis Comput 2024; 40(2): 1215-1227. DOI: 10.1007/s00371-023-02842-w.
  15. Chen H, Wang Y, Guo T, Xu C, Deng Y, Liu Z. Pre-trained image processing transformer. 2021 IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR) 2021: 12299-12310. DOI: 10.1109/CVPR46437.2021.01212.
  16. Liang J, Cao J, Sun G, Zhang K, Gool LV, Timofte R. Swinir: Image restoration using swin transformer. 2021 IEEE/CVF Int Conf on Computer Vision Workshops (ICCVW) 2021: 1833-1844. DOI: 10.1109/ICCVW54120.2021.00210.
  17. Wang Z, Cun X, Bao J, Zhou W, Liu J, Li H. Uformer: A general u-shaped transformer for image restoration. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR) 2022: 17662-17672. DOI: 10.1109/CVPR52688.2022.01716.
  18. Zamir SW, Arora A, Khan S, Hayat M, Khan FS, Yang M-H, Shao L. Learning enriched features for real image restoration and enhancement. In Book: Vedaldi A, Bischof H, Brox T, Frahm J-M, eds. Computer vision – ECCV 2020. 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXV. Cham, Switzerland: Springer Nature Switzerland AG; 2020: 492-511. DOI: 10.1007/978-3-030-58595-2_30.
  19. Shi W, Caballero J, Huszár F, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. 2016 IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2016: 1874-1883. DOI: 10.1109/CVPR.2016.207.
  20. Chen X, Wang X, Zhou J, Qiao Y. Activating more pixels in image super-resolution transformer. 2023 IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR) 2023: 22367-22377. DOI: 10.1109/CVPR52729.2023.02142.
  21. Zamir SW, Arora A, Khan S, Hayat M, Khan FS, Yang M-H. Multi-stage progressive image restoration. 2021 IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR) 2021: 14821-14831. DOI: 10.1109/CVPR46437.2021.01458.
  22. Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. 31st Conference on Neural Information Processing Systems (NIPS 2017) 2017: 6000-6010.
  23. Chen X, Li H, Li M, Pan J. Learning a sparse transformer network for effective image deraining. 2023 IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR) 2023: 5896-5905. DOI: 10.1109/CVPR52729.2023.00571.
  24. Wang Z, Fu Y, Liu J, Zhang Y. LG-BPN: Local and global blind-patch network for self-supervised real-world denoising. 2023 IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR) 2023: 18156-18165. DOI: 10.1109/CVPR52729.2023.01741.
  25. Plotz T, Roth S. Benchmarking denoising algorithms with real photographs, 2017 IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2017: 1586-1595. DOI: 10.1109/CVPR.2017.294.
  26. Ding X, Zhang X, Han J, Ding G. Scaling up your kernels to 31×31: Revisiting large kernel design in cnns. 2022 IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR) 2022: 11963-11975. DOI: 10.1109/CVPR52688.2022.01166.
  27. Chen L, Chu X, Zhang X, Sun J. Simple baselines for image restoration. In Book: Avidan S, Brostow G, Cissé M, Farinella GM, Hassner T, eds. Computer vision – ECCV 2022. 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VII. Cham, Switzerland: Springer Nature Switzerland AG; 2022: 17-33. DOI: 10.1007/978-3-031-20071-7_2.
  28. Abdelfattah R, Wang X, Wang S. Ttpla: An aerial-image dataset for detection and segmentation of transmission towers and power lines. In Book: Ishikawa H, Liu C-L, Pajdla T, Shi J, eds. Computer vision – ACCV 2020. 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30 – December 4, 2020, Revised Selected Papers, Part VI. 2020: 601-618. DOI: 10.1007/978-3-030-69544-6_36.
  29. Vieira-e-Silva ALB, de Castro Felix H, de Menezes Chaves T, Simões FPM, Teichrieb V, dos Santos MM. Stn plad: A dataset for multi-size power line assets detection in high-resolution uav images. 2021 34th SIBGRAPI Conf on Graphics, Patterns and Images (SIBGRAPI) 2021: 215-222. DOI: 10.1109/SIBGRAPI54419.2021.00037.
  30. Allard WK. Total variation regularization for image denoising, I. Geometric theory. SIAM J Math Anal 2008; 39(4): 1150-1190. DOI: 10.1137/060662617.
  31. Charbonnier P, Blanc-Feraud L, Aubert G, Barlaud M. Two deterministic half-quadratic regularization algorithms for computed imaging. Proc 1st Int Conf on Image Processing 1994; 2: 168-172. DOI: 10.1109/ICIP.1994.413553.
  32. Abdelhamed A, Lin S, Brown MS. A high-quality denoising dataset for smartphone cameras. 2018 IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR) 2018: 1692-1700. DOI: 10.1109/CVPR.2018.00182.
  33. Zamir SW, Arora A, Khan S, Hayat M, Khan FS, Yang M-H. Cycleisp: Real image restoration via improved data synthesis. 2020 IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR) 2020: 2696-2705. DOI: 10.1109/CVPR42600.2020.00277.
  34. Loshchilov I, Hutter F. Decoupled weight decay regularization. arXiv Preprint. 2017. Source: <https://arxiv.org/abs/1711.05101>. DOI: 10.48550/arXiv.1711.05101.
  35. Loshchilov I, Hutter F. Sgdr: Stochastic gradient descent with warm restarts. arXiv Preprint. 2016. Source: <https://arxiv.org/abs/1608.03983>. DOI: 10.48550/arXiv.1608.03983.
  36. Yue Z, Zhao Q, Zhang L, Meng D. Dual adversarial network: Toward real-world noise removal and noise generation. In Book: Vedaldi A, Bischof H, Brox T, Frahm J-M, eds. Computer vision – ECCV 2020. 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part X. Cham, Switzerland: Springer Nature Switzerland AG; 2020: 41-58. DOI: 10.1007/978-3-030-58607-2_3.
  37. Fan C-M, Liu T-J, Liu K-H, Chiu C-H. Selective residual m-net for real image denoising. 2022 30th European Signal Processing Conf (EUSIPCO) 2022: 469-473. DOI: 10.23919/EUSIPCO55093.2022.9909521.
  38. Anwar S, Barnes N. Real image denoising with feature attention. 2019 IEEE/CVF International Conference on Computer Vision (ICCV) 2019: 3155-3164. DOI: 10.1109/ICCV.2019.00325.
  39. Yue Z, Yong H, Zhao Q, Zhang L, Meng D. Variational denoising network: Toward blind noise modeling and removal. Proc 33rd Int Conf on Neural Information Processing Systems 2019: 1690-1701.
  40. Ren C, He X, Wang C, Zhao Z. Adaptive consistency prior based deep network for image denoising. 2021 IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR) 2021: 8596-8606. DOI: 10.1109/CVPR46437.2021.00849.
  41. Huang J-B, Singh A, Ahuja N. Single image super-resolution from transformed self-exemplars. 2015 IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2015: 5197-5206. DOI: 10.1109/CVPR.2015.7299156.
  42. Cheng S, Wang Y, Huang H, Liu D, Fan H, Liu S. Nbnet: Noise basis learning for image denoising with subspace projection. 2021 IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR) 2021: 4896-4906. DOI: 10.1109/CVPR46437.2021.00486.
  43. Liu K, Du X, Liu S, Zheng Y. Ddt: Dual-branch deformable transformer for image denoising. 2023 IEEE Int Conf on Multimedia and Expo (ICME) 2023: 2765-2770. DOI: 10.1109/ICME55011.2023.00470.

© 2009, IPSI RAS
Россия, 443001, Самара, ул. Молодогвардейская, 151; электронная почта: journal@computeroptics.ru; тел: +7 (846) 242-41-24 (ответственный секретарь), +7 (846) 332-56-22 (технический редактор), факс: +7 (846) 332-56-20