Abstract
Smog is one of the air pollutants that makes it difficult for drivers to see. Smog is a mixture of fog and smoke that produces black fumes and reduces the visibility of drivers within the range of one kilometre. The small size and high density of smog particles, in comparison to other air pollutants, impede drivers’ vision on the road. To resolve these problems, researchers designed a number of visibility restoration models. However, the development of an adequate desmogging technique is a challenging issue. The aerial and sensing imaging of machine vision systems are modified by the desmogging model. In this paper, a residual regression network (RRNet) is proposed followed by morphological erosion to produce a transmission map. The atmospheric light is estimated by using a 2D order statistic filter. The smoggy image is further reconstructed to obtain the clear scene radiance. Thus, the proposed model has a susceptibility to remove smog from road images in an effective manner. The proposed model is evaluated on the four well-known benchmark datasets and compared with five well-known desmogging techniques. The performance of the proposed desmogging model is evaluated in terms of color deviation, structure similarity index, and peak signal to noise ratio. It is found superior as compared to the existing models in terms of various performance metrics namely, fog aware density evaluation, naturalness image quality evaluator, perception-based image-quality, blind/referenceless image spatial quality evaluator, and image entropy by 2.2%, 1.17%, 8.05%, 2.64%, and 0.69% respectively.
Similar content being viewed by others
References
Agrawal SC and Jalal AS (2021) Distortion-free image dehazing by superpixels and ensemble neural network. Vis Comput. pp.1–16
An S, Huang X, Wang L, Wang L and Zheng Z (2021) Semi-Supervised image dehazing network. Vis Comput, pp.1–15
Babu HG, Venkatram N (2022) An efficient image dahazing using Googlenet based convolution neural networks. Multimed Tools Appl 81(30):43897–43917
Bala J and Lakhwani K (2019) Desmogging of smog affected images using illumination channel prior. Int Conf Innov Comput Comm. pp. 417–425
Bala J, Lakhwani K (2019) Performance evaluation of various desmogging techniques for single smoggy images. Mod Phys Lett B 33(5):1950056
Bala J, Lakhwani K (2020) Single image desmogging using oblique gradient profile prior and variational minimization. Multidimens Syst Signal Proc 31:1259–1275
Bala J, and Lakhwani K (2020) Single image desmogging using Gradient channel prior and Information gain based bilateral. 2020 3rdIntConf Emerg Technol Comput Eng: Machine Learn Int Things (ICETCE). pp. 1–6, https://doi.org/10.1109/ICETCE48199.2020.9091768.
Barner KE, Arce GR (1998) 21 Order-statistic filtering and smoothing of time-series: Part II. Handbook Statist 17:555–602
Bindal A (2019). Normalization Techniques in Deep Neural Networks. [Online] Available at: https://medium.com/techspace-usict/normalization-techniques-in-deep-neural-networks-9121bf100d8. Accessed 13 Jun 2021
Brownlee J (2019) A Gentle Introduction to the Rectified Linear Unit (ReLU). [Online]. Available: [Accessed 13 June 2021]
Chen WT, Yuan SY, Tsai GC, Wang HC and Kuo SY (2018) Color channel-based smoke removal algorithm using machine learning for static images. In 2018 25th IEEE Int Conf Image Proc (ICIP) (pp. 2855–2859). IEEE
Chen Z, Hu Z, Sheng B, Li P, Kim J, Wu E (2020) Simplified non-locally dense network for single-image dehazing. Vis Comput 36(10):2189–2200
Choi LK, You J and Bovik AC (2014) February. Referenceless perceptual fog density prediction model. In Human Vis Electron ImagingXIX (Vol. 9014, pp. 90–101). SPIE
Choi LK, You J and Bovik AC (2014) Referenceless perceptual image defogging. In2014 Southwest Symposium on Image Analysis and Interpretation;(pp. 165–168). IEEE
Choi LK, You J, and Bovik AC (2015) “FADE Software Release,” http://live.ece.utexas.edu/research/fog/FADE_release.zip. Accessed 13 Jun 2021
Choi LK, You J, Bovik AC (2015) Referenceless prediction of perceptual fog density and perceptual image defogging. IEEE Trans Image Process 24(11):3888–3901
Fang Z, Zhao M, Yu Z, Li M and Yang Y (2021) A guiding teaching and dual adversarial learning framework for a single image dehazing. Vis Comput, pp.1–13
Gadekallu TR, Srivastava G, Liyanage M, Iyapparaja M, Chowdhary CL, Koppu S, Maddikunta PKR (2022) Hand gesture recognition based on a Harris hawks optimized convolution neural network. Comput Electr Eng 100:107836
Ganguly B, Bhattacharya A, Srivastava A, Dey D, Munshi S (2021) Single image haze removal with haze map optimization for various haze concentrations. IEEE Trans Circuits Syst Video Technol 32(1):286–301
He K, Zhang X, Ren S and Sun J (2016) Deep residual learning for image recognition. In Proc IEEE Conf Comput Vis Patt Recog (pp. 770–778)
Hu X, Chu L, Pei J, Liu W, Bian J (2021) Model complexity of deep learning: A survey. Knowl Inf Syst 63:2585–2619
Jain A, Kumar A (2021) Desmogging of still smoggy images using a novel channel prior. J Ambient Intell Humaniz Comput 12(1):1161–1177
Janocha K. and Czarnecki WM (2017) On Loss Functions for Deep Neural Networks in Classification. arXiv
Juneja A, Kumar V, Singla SK (2021) A Systematic Review on Foggy Datasets: Applications and Challenges. Arch Computat Methods Eng. https://doi.org/10.1007/s11831-021-09637-z
Kingma DP, and Ba J (2017) Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980
Kumar A, and Jain A (2021) Image smog restoration using oblique gradient profile prior and energy minimization. Front Comput Sci 15. pp. 156706. https://doi.org/10.1007/s11704-020-9305-8
Li J, Hu Q, Ai M (2018) Haze and thin cloud removal via sphere model improved dark channel prior. IEEE Geosci Remote Sens Lett 16(3):472–476
Li B, Ren W, Fu D, Tao D, Feng D, Zeng W, Wang Z (2018) Benchmarking single-image dehazing and beyond. IEEE Trans Image Process 28(1):492–505
Liu X, Fu L, Chun-Wei Lin J, Liu S (2022) SRAS-net: Low-resolution chromosome image classification based on deep learning. IET Syst Biol 16(3–4):85–97
Mittal A, Soundararajan R, Bovik AC (2012) Making a “completely blind” image quality analyzer. IEEE Signal Process Lett 20(3):209–212
Mittal A, Moorthy AK, Bovik AC (2012) No-reference image quality assessment in the spatial domain. IEEE Trans Image Process 21(12):4695–4708
Mondal R, Dey MS, Chanda B (2020) Image restoration by learning morphological opening-closing network. Mathematical Morphology-Theory Appl 4(1):87–107
Mondal K, Rabidas R and Dasgupta R (2022) Single image haze removal using contrast limited adaptive histogram equalization based multiscale fusion technique. Multimed Tools Appl, pp.1–26
Naeem A, Javed AR, Rizwan M, Abbas S, Lin JCW, Gadekallu TR (2021) DARE-SEP: A hybrid approach of distance aware residual energy-efficient SEP for WSN. IEEE transactions on green communications and networking 5(2):611–621
Ogueke NV, Emekwuru N (2017) Regulation of Nanorefrigerant Use: A Proactive Measure Against Possible Undesirable Health and Environmental Implications. Eur J Sustain Dev Res 1:1–13
Rehman MU, Shafique A, Ghadi YY, Boulila W, Jan SU, Gadekallu TR, Driss M, Ahmad J (2022) A Novel Chaos-Based Privacy-Preserving Deep Learning Model for Cancer Diagnosis. IEEE Transactions on Network Science and Engineering 9(6):4322–4337
Sharma G, Wu W and Dalal EN (2005) The CIEDE2000 color‐difference formula: Implementation notes, supplementary test data, and mathematical observations. Color Research & Application: Endorsed by Inter‐Society Color Council, The Colour Group (Great Britain), Canadian Society for Color, Color Science Association of Japan, Dutch Society for the Study of Color, The Swedish Colour Centre Foundation, Colour Society of Australia, Centre Français de la Couleur, 30(1), pp.21–30
Sharma N, Kumar V, Singla SK (2021) Single image defogging using deep learning techniques: past, present and future. Arch Comput Methods Eng 28(7):4449–4469
Si Y, Yang F, Chong N (2022) A novel method for single nighttime image haze removal based on gray space. Multimedia Tools and Applications 81(30):43467–43484
Singh D, Kumar V (2018) Comprehensive survey on haze removal techniques. Multimedia Tools and Applications 77:9595–9620
Singh D, Kumar V (2019) A comprehensive review of computational dehazing techniques. Arch Comput Methods Eng 26(5):1395–1413
Soille P (2013) Morphological image analysis: principles and applications. Springer Science & Business Media
Sun XJ, Lin JCW (2022) A target recognition algorithm of multi-source remote sensing image based on visual Internet of Things. Mobile Networks and Applications 27(2):784–793
Tarel J et al. (2010) Improved visibility of road scene images under heterogeneous fog. 2010 IEEE Intell Vehicles Symposium. pp 478–485
Tarel J et al (2012) Vision enhancement in homogeneous and heterogeneous fog. IEEE Intell Transp Syst Mag 4(2):6–20
Tian C, Zhang X, Lin JCW, Zuo W, Zhang Y. and Lin CW (2022) Generative adversarial networks for image super-resolution: A survey. arXiv preprint arXiv:2204.13620
Venkatanath N, Praneeth D, Bh MC, Channappayya SS and Medasani SS (2015) Blind image quality evaluation using perception based features. In 2015 Twenty First National Conf Comm (NCC) (pp. 1–6). IEEE
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Wang C, Shen HW (2011) Information theory in scientific visualization. Entropy 13(1):254–273
Wang R and Wang G (2016) Single smog image dehazing method. In 2016 3rd Int Conf Inf Sci Control Eng (ICISCE) (pp. 621–625). IEEE
Wang Y, Yin S, Basu A (2021) A multi-scale attentive recurrent network for image dehazing. Multimed Tools Appl 80(21–23):32539–32565
Yang F and Zhang Q (2021) Depth aware image dehazing. Vis Comput. pp. 1–9
Zhang L, Li X, Hu B and Ren X (2015) Research on fast smog free algorithm on single image. In 2015 First International Conference on Computational Intelligence Theory, Systems and Applications (CCITSA);(pp. 177–182). IEEE
Zhang et al. (2021) Visible light polarization image desmogging via cycle convolutional neural network. Multimed Syst. https://doi.org/10.1007/s00530-021-00802–9
Acknowledgements
This research is supported by Council of Scientific and Industrial Research (CSIR), India. The sanction number of the scheme is 22(0801)/19/EMR-II.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no conflict of interest to declare. All co-authors have seen and agree with the contents of the manuscript. We certify that the submission is original work and is not under review at any other publication.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Juneja, A., Kumar, V. & Singla, S.K. Desmogging of still images using residual regression network and morphological erosion. Multimed Tools Appl 83, 7179–7214 (2024). https://doi.org/10.1007/s11042-023-15893-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15893-x