Abstract
With the rapid development of machine learning, deep learning-based image defogging algorithms are receiving more and more attention from scholars compared to traditional image defogging method. A novel method for synthesizing high-quality haze images in fixed surveillance scenes is proposed, based on a dark channel-based approach for image fusion. The method also contributes a synthetic haze image dataset, which accurately corresponds to real-world scenarios, for use in deep learning network training and evaluation of defogging effects. To address the issue of chromatic aberration in the sky and local areas when using a deblurring network for defogging, the SKNet module in the Attention mechanism is integrated into DeblurGAN. The defogging network is trained using the synthetic haze image dataset, and is tested on various sets of synthetic and actual haze images, yielding improved results in metrics such as SSIM, PSNR, and MSE.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Liu, S., Huang, S., Xu, X., Lloret, J., Muhammad, K.: Efficient visual tracking based on fuzzy inference for intelligent transportation systems. IEEE Trans. Intell. Trans. Syst. (2023)
Mangla, C., Rani, S., Herencsar, N.: A misbehavior detection framework for cooperative intelligent transport systems. ISA Trans. 132, 52–60 (2023)
Hijji, M., et al.: 6G connected vehicle framework to support intelligent road maintenance using deep learning data fusion. IEEE Trans. Intell. Trans. Syst/ (2023)
Wang, L., et al.: SAT-GCN: Self-attention graph convolutional network-based 3D object detection for autonomous driving. Knowl.-Based Syst..-Based Syst. 259, 110080 (2023)
Zhao, C., Song, A., Zhu, Y., Jiang, S., Liao, F., Du, Y.: Data-driven indoor positioning correction for infrastructure-enabled autonomous driving systems: A lifelong framework. IEEE Trans. Intell. Trans. Syst. (2023)
Alaba, S.Y., Ball, J.E.: Deep learning-based Image 3D object detection for autonomous driving. IEEE Sensors J. (2023)
Kulkarni, R., Jenamani, R.K., Pithani, P., Konwar, M., Nigam, N., Ghude, S.D.: Loss to aviation economy due to winter fog in New Delhi during the winter of 2011–2016. Atmosphere 10, 198 (2019)
Huang, H., Chen, C.: Climatological aspects of dense fog at Urumqi Diwopu International Airport and its impacts on flight on-time performance. Nat. Hazards 81, 1091–1106 (2016)
Saffarian, M., Happee, R., de Winter, J.: Why do drivers maintain short headways in fog? A driving-simulator study evaluating feeling of risk and lateral control during automated and manual car following. Ergonomics 55, 971–985 (2012)
Liang, C.-W., Chang, C.-C., Liang, J.-J.: The impacts of air quality and secondary organic aerosols formation on traffic accidents in heavy fog–haze weather, Heliyon (2023)
Peng, Y., Abdel-Aty, M., Lee, J., Zou, Y.: Analysis of the impact of fog-related reduced visibility on traffic parameters. J. Trans. Eng. Part A: Syst. 144, 04017077 (2018)
Sitao, H., Xuemei, W., Chuchu, D., Jing, Z.: Influence mechanism of mass fog on highway traffic safety. In: Proceedings 2011 International Conference on Transportation, Mechanical, and Electrical Engineering (TMEE), pp. 791–794. IEEE (2011)
He, S., Chen, Z., Wang, F., Wang, M.: Integrated image defogging network based on improved atmospheric scattering model and attention feature fusion. Earth Sci Inform. 14, 2037–2048 (2021)
Dong, T., Zhao, G., Wu, J., Ye, Y., Shen, Y.: Efficient traffic video dehazing using adaptive dark channel prior and spatial-temporal correlations. Sensors. 19, 1593 (2019)
Kuanar, S., Mahapatra, D., Bilas, M., Rao, K.R.: Multi-path dilated convolution network for haze and glow removal in nighttime images. Vis. Comput.Comput. 38, 1121–1134 (2022)
Mat Nor, M.N., Rupenthal, I.D., Green, C.R., Acosta, M.L.: Differential action of connexin hemichannel and pannexin channel therapeutics for potential treatment of retinal diseases. Int. J. Mol. Sci. 22, 1755 (2021)
Liu, X., Liu, C., Lan, H., Xie, L.: Dehaze enhancement algorithm based on retinex theory for aerial images combined with dark channel. Open Access Library J. 7 (2020)
Wu, M., Li, B.: Single image dehazing based on generative adversarial networks. In: Intelligent Computing Theories and Application: 18th International Conference, ICIC 2022, Xi’an, China, 7–11 August 2022, Proceedings, Part II, pp. 460–469. Springer (2022). https://doi.org/10.1007/978-3-031-13829-4_40
Ma, D., Fang, H., Wang, N., Zheng, H., Dong, J., Hu, H.: Automatic defogging, deblurring, and real-time segmentation system for sewer pipeline defects. Autom. Constr. 144, 104595 (2022)
Li, Y., Cheng, J., Li, Z., Pan, Q., Zeng, R., Tian, T.: Single image defogging method based on improved generative adversarial network. In: 2022 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC), pp. 781–787. IEEE (2022)
Deqiang, C., Yangyang, Y., Qiqi, K., Jinyang, X.: A generative adversarial network incorporating dark channel prior loss used for single image defogging. Opto-Elect. Eng. 49, 210448–210451 (2022)
Kupyn, O., Martyniuk, T., Wu, J., Wang, Z.: Deblurgan-v2: Deblurring (orders-of-magnitude) faster and better. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8878–8887 (2019)
Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 510–519 (2019)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)
Laskar, Z., Kannala, J.: Context aware query image representation for particular object retrieval. In: Sharma, P., Bianchi, F.M. (eds.) SCIA 2017. LNCS, vol. 10270, pp. 88–99. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59129-2_8
Pei, W., Baltrusaitis, T., Tax, D.M., Morency, L.-P.: Temporal attention-gated model for robust sequence classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6730–6739 (2017)
Cordts, M., et al.: The cityscapes dataset. In: CVPR Workshop on the Future of Datasets in Vision. sn (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hu, X. et al. (2023). A Novel Attention-DeblurGAN-Based Defogging Algorithm. In: Lu, H., et al. Image and Graphics. ICIG 2023. Lecture Notes in Computer Science, vol 14356. Springer, Cham. https://doi.org/10.1007/978-3-031-46308-2_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-46308-2_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46307-5
Online ISBN: 978-3-031-46308-2
eBook Packages: Computer ScienceComputer Science (R0)