Nighttime Image-Dehazing: A Review and Quantitative Benchmarking

Abstract

Visibility enhancement of images captured during hazy weather conditions is highly essential for various important applications like intelligent vehicles, surveillance, remote sensing, etc. In recent years, researchers proposed numerous image-dehazing methods mostly focusing on daytime images’ characteristics. In this work, we have highlighted the dissimilarities among the characteristics of daytime and nighttime hazy images and explained that well-known daytime image-dehazing priors cannot dehaze nighttime hazy images effectively. Following this discussion, we have provided a comprehensive review of existing nighttime image-dehazing methods after grouping them according to different nighttime hazy image models based on which they were designed as their methodologies vastly vary with those models. Thereafter, we have performed comparative qualitative and quantitative analyses of outputs obtained by applying these methods on images belonging to novel N-HAZE database. N-HAZE comprises of both indoor and outdoor real-world nighttime hazy images captured in the presence of haze created by artificial haze machines and corresponding Ground Truth images. Finally, we have concluded our work by stating the existing challenges and future scope of work in this field after analyzing the strengths and limitations of each method. Our main aim behind conducting this survey is to draw the attention of more researchers towards this less explored yet significant research topic and encourage them to design new methods which can solve the existing challenges. To the best of our knowledge, we are the first ones to review the nighttime image-dehazing methods and to design N-HAZE, which is the first database designed for benchmarking these methods.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22

Abbreviations

NHTSA:

National Highway Traffic Safety Administration

DCP:

Dark Channel Prior

GT:

Ground Truth

SSIM:

Structural Similarity Index

MSE:

Mean Square Error

PSNR:

Peak Signal-to-Noise Ratio

FADE:

Fog Aware Density Evaluator

GIF:

Guided Image Filter

CCT:

Color Channel Transfer

MRP:

Maximum Reflectance Prior

DF:

Dilation Factor

BCP:

Bright Channel Prior

HDP:

Haze Density Prediction

ReLU:

Rectified Linear Unit

HDP-Net:

Haze Density Prediction Network

References

  1. 1.

    Ramu M (2015) Poor visibility due to bad weather is killing hundreds in accidents. THE HINDU. https://www.thehindu.com/news/cities/Hyderabad/poor-visibility-due-to-bad-weather-is-killing-hundreds-in-accidents/article7439794.ece Accessed 9 Oct 2019

  2. 2.

    Federal Highway Administration (2018) Road weather Management Program. U.S. Department of Transportation. https://ops.fhwa.dot.gov/weather/q1_roadimpact.htm, Accessed 9 Oct 2019

  3. 3.

    Abdel-Aty A, Ekram A, Huang H, Choi K (2011) A study on crashes related to visibility obstruction due to fog and smoke. Accid Anal Prev 43:1730–1737. https://doi.org/10.1016/j.aap.2011.04.003

    Article  Google Scholar 

  4. 4.

    Plainis S, Murray IJ, Pallikaris IG (2006) Road traffic casualties: understanding the night-time death toll. Injury Prevention 12:125–128. https://doi.org/10.1136/ip.2005.011056

    Article  Google Scholar 

  5. 5.

    Ratanavaraha V, Suangka S (2014) Impacts of accident severity factors and loss values of crashes on expressways in Thailand. IATSS Res 37:130–136. https://doi.org/10.1016/j.iatssr.2013.07.001

    Article  Google Scholar 

  6. 6.

    Elliott H (2009) Most Dangerous Times To Drive. Forbes. https://www.forbes.com/2009/01/21/car-accident-times-forbeslife-cx_he_0121driving.html#654c29f36fc0, Accessed 9 Oct 2019

  7. 7.

    Koschmieder H (1924) Theorie der Horizontalen Sichtweite. Keim & Nemnich

  8. 8.

    He K, Sun J, Tang X (2011) Single image haze removal using dark channel prior. IEEE Trans Pattern Anal Mach Intell 33(12):2341–2353. https://doi.org/10.1109/TPAMI.2010.168

    Article  Google Scholar 

  9. 9.

    Wang Z, Bovik AC (2006) Modern Image Quality Assessment. Morgan & Claypool

  10. 10.

    Sharma G, Wu W, Dalal EN (2004) The CIEDE2000 color-difference formula: implementation notes, supplementary test data, and mathematical observations. Color Res Appl 30(1):21–30. https://doi.org/10.1002/col.20070

    Article  Google Scholar 

  11. 11.

    Li D, Zang D, Qiao X, Wang L, Zhang M (2015) 3D synthesis and crosstalk reduction for lenticular autostereoscopic displays. J Display Technol 11(11):939–946. https://doi.org/10.1109/JDT.2015.2405065

    Article  Google Scholar 

  12. 12.

    Kang S-J (2014) HSI-based color error-aware subpixel rendering technique. J Display Technol 10(11):251–254. https://doi.org/10.1109/JDT.2014.2304716

    Article  Google Scholar 

  13. 13.

    Mittal A, Moorthy AK, Bovik AC (2012) No-reference image quality assessment in the spatial domain. IEEE Trans Image Process 21(12):4695–4708. https://doi.org/10.1109/TIP.2012.2214050

    MathSciNet  MATH  Article  Google Scholar 

  14. 14.

    Ancuti C, Ancuti CO (2016) D-HAZY: a dataset to evaluate quantitatively dehazing algorithms. IEEE International Conference on Image Processing (ICIP), Phoenix, Arizona, pp. 2226-2230. https://doi.org/10.1109/icip.2016.7532754

  15. 15.

    Ancuti CO, Ancuti C, Timofte R, Vleeschouwer CD (2018) I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images”. arXiv:1804.05091v1, pp 1–5

  16. 16.

    Ancuti CO, Ancuti C, Timofte R, Vleeschouwer CD (2018) O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images. arXiv:1804.05101v1, pp 1–9

  17. 17.

    Li Y, You S, Brown MS, Tan RT (2017) Haze visibility enhancement: a Survey and quantitative benchmarking. Comput Vis Image Underst 165:1–16. https://doi.org/10.1016/j.cviu.2017.09.003

    Article  Google Scholar 

  18. 18.

    Benoit A, Cuevas L, Thomas J-B (2018) Deep learning for dehazing: Comparison and analysis. Colour and Visual Computing Symposium (CVCS), Gjøvik, Norway. https://doi.org/10.1109/cvcs.2018.8496520

  19. 19.

    Chengtao C, Qiuyu Z, Yanhua L (2015) A survey of image dehazing approaches. IEEE Chinese Control and Decision Conference (CCDC), Qingdao, China, pp 3964–3969. https://doi.org/10.1109/ccdc.2015.7162616

  20. 20.

    Lee S, Yun S, Nam J-H, Won CS, Jung S-W (2016) A review on dark channel prior based image dehazing algorithms. EURASIP J Image Video Process 4:1–23. https://doi.org/10.1186/s13640-016-0104-y

    Article  Google Scholar 

  21. 21.

    Wang W, Yuan X (2017) Recent Advances in Image Dehazing. IEEE/CAA J Automatica Sinica 4(3):410–436. https://doi.org/10.1109/JAS.2017.7510532

    MathSciNet  Article  Google Scholar 

  22. 22.

    Singh D, Kumar V (2018) Comprehensive survey on haze removal techniques. Multimedia Tools Appl 77:9595–9620. https://doi.org/10.1007/s11042-017-5321-6

    Article  Google Scholar 

  23. 23.

    Singh D, Kumar V (2018) A comprehensive review of computational dehazing techniques. Arch Comput Methods Eng 26(5):1395–1413. https://doi.org/10.1007/s11831-018-9294-z

    Article  Google Scholar 

  24. 24.

    Pei S-C, Lee T-Y (2012) Nighttime haze removal using color transfer pre-processing and Dark Channel Prior. IEEE International Conference on Image Processing (ICIP), Orlando, FL, USA, pp 957–960. https://doi.org/10.1109/icip.2012.6467020

  25. 25.

    Jiang B, Men H, Ma Z, Wang L, Zhou Y, Pengfei X, Jiang X, Meng X (2018) Nighttime image Dehazing with modified models of color transfer and guided image filter. Multimedia Tools Appl 77(3):3125–3141. https://doi.org/10.1007/s11042-017-4954-9

    Article  Google Scholar 

  26. 26.

    Ancuti CO, Ancuti C, Vleeschouwer CD, Sbetr M (2019) Color channel transfer for image dehazing. IEEE Signal Process Lett 26(9):1413:1417. https://doi.org/10.1109/lsp.2019.2932189

  27. 27.

    Zhang J, Cao Y, Wang Z (2014) Nighttime haze removal based on a new imaging model. IEEE International Conference on Image Processing (ICIP), Paris, France, pp 4557–4561. https://doi.org/10.1109/icip.2014.7025924

  28. 28.

    Li Y, Tan R-T, Brown MS (2015) Nighttime Haze Removal with Glow and Multiple Light Colors. IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, pp 226–234. https://doi.org/10.1109/iccv.2015.34

  29. 29.

    Kuanar S, Rao KR, Mahapatra D, Bilas M (2019) Night Time Haze and Glow Removal using Deep Dilated Convolutional Network. arXiv:1902.00855v1, pp 1–13

  30. 30.

    Narasimhan SG, Nayar SK (2003) Shedding light on the weather. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Madison, WI, USA. https://doi.org/10.1109/cvpr.2003.1211417

  31. 31.

    Lin J, Zhang X, Li H, Liu Z (2018) Nighttime image haze removal and enhancement based on improved atmospheric scattering model. International Conference on Image, Video Processing and Artificial Intelligence, Shanghai, China, pp. 10836:1-6. https://doi.org/10.1117/12.2502130

  32. 32.

    Xu L, Yan Q, Xia Y, Jia J (2012) Structure extraction from texture via relative total variation. ACM Trans Graphics (TOG) 31(6):139:1-139:10. https://doi.org/10.1145/2366145.2366158

  33. 33.

    Santra S, Chanda B (2016) Day/Night Unconstrained Image Dehazing. IEEE International Conference on Pattern Recognition (ICPR), Cancun, Mexico. https://doi.org/10.1109/icpr.2016.7899834

  34. 34.

    Liao Y, Su Z, Liang X, Qu B (2018) HDP-Net: Haze Density Prediction Network for Nighttime Dehazing. Pacific Rim Conference on Multimedia (PCM), Hefei, China, pp 469–480. https://doi.org/10.1007/978-3-030-00776-8_43

  35. 35.

    Levin A, Lischinski D, Weiss Y (2008) A closed form solution to natural image matting. IEEE Trans Pattern Anal Mach Intell 30(2):228–242. https://doi.org/10.1109/TPAMI.2007.1177

    Article  Google Scholar 

  36. 36.

    Reinhard E, Adhikhmin M, Gooch B, Shirley P (2001) Color Transfer between Images. IEEE Trans Comput Graph Appl 21(5):31–41. https://doi.org/10.1109/38.946629

    Article  Google Scholar 

  37. 37.

    He K, Sun J, Tang X (2013) Guided image filtering. IEEE Trans Pattern Anal Mach Intell 35(6):1397–1409. https://doi.org/10.1109/TPAMI.2012.213

    Article  Google Scholar 

  38. 38.

    Schettini R, Gasparini F, Corchs S, Marini F (2010) Contrast image correction method. J Electron Imaging 19(2):023005-1–023005-11. https://doi.org/10.1117/1.3386681

  39. 39.

    Kou F, Chen W, Wen C, Li Z (2015) Gradient domain guided image filtering. IEEE Trans Image Process 24(11):4528–4539. https://doi.org/10.1109/TIP.2015.2468183

    MathSciNet  MATH  Article  Google Scholar 

  40. 40.

    Prewitt JMS (1970) Object enhancement and extraction. Picture processing and psychopictorics. Academic Press, Cambridge

    Google Scholar 

  41. 41.

    Achantay R, Hemamiz S, Estraday F, Susstrunky S (2009) Frequency tuned salient region detection. IEEE International Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, pp 1597–1604. https://doi.org/10.1109/cvpr.2009.5206596

  42. 42.

    Ancuti C, Ancuti CO, Vleeschouwer CD, Bovik AC (2016) Night-time dehazing by fusion. IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA, pp 2256–2260. https://doi.org/10.1109/icip.2016.7532760

  43. 43.

    Zhang J, Cao Y, Wang Z (2016) Nighttime Haze Removal with Illumination Correction. arXiv:1606.01460v1

  44. 44.

    Elad M (2005) Retinex by two bilateral filters. International Conference on Scale-Space Theories in Computer Vision (Springer), Hofgeismar, Germany, pp 217–229. https://doi.org/10.1007/11408031_19

  45. 45.

    Wang L, Xiao L, Liu H, Wei Z (2014) Variational bayesian method for retinex. IEEE Trans Image Process 23(8):3381–3396. https://doi.org/10.1109/TIP.2014.2324813

    MathSciNet  MATH  Article  Google Scholar 

  46. 46.

    Tang K, Yang J, Wang J (2014) Investigating haze-relevant features in a learning framework for image dehazing. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA. https://doi.org/10.1109/cvpr.2014.383

  47. 47.

    Zhang J, Cao Y, Fang S, Kang Y, Chen CW (2017) Fast HAZE REMOVAL FOR NIGHTTIME IMAGE USING MAXIMUM REflECTANCE PRIor. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp 7418–7426. https://doi.org/10.1109/cvpr.2017.742

  48. 48.

    Li Y, Brown MS (2014) Single image layer separation using relative smoothness. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA. https://doi.org/10.1109/cvpr.2014.346

  49. 49.

    Park D, Han D.K, Ko H (2017) Nighttime image dehazing using local atmospheric selection rule and weighted entropy for visible-light systems. Opt Eng 56(5):05050-1-05050-4. https://doi.org/10.1117/1.oe.56.5.050501

  50. 50.

    Strobach P (1991) Quadtree-structured recursive plane decomposition coding of images. IEEE Trans Signal Process 39(6):1380–1397. https://doi.org/10.1109/78.136544

    Article  Google Scholar 

  51. 51.

    Park D, Han D.K, Ko H (2016) Nighttime image dehazing with local atmospheric light and weighted entropy. IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA, pp 2261–2265. https://doi.org/10.1109/icip.2016.7532761

  52. 52.

    Jin X, Yang X, Zhang J, Li Z (2017) Nighttime Haze Removal with Fusion Atmospheric Light and Improved Entropy. Chinese Conference on Computer Vision (CCF), Tianjin, China, pp 323–333. https://doi.org/10.1007/978-981-10-7302-1_27

  53. 53.

    Yang M, Liu J, Li Z (2018) Super-pixel based single nighttime image haze removal. IEEE Trans Multimedia 20(11):3008–3018. https://doi.org/10.1109/TMM.2018.2820327

    Article  Google Scholar 

  54. 54.

    Achanta R, Shaji A, Smith K, Lucchi A, Fua P (2012) SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274–2282. https://doi.org/10.1109/TPAMI.2012.120

    Article  Google Scholar 

  55. 55.

    Cai B, Xu X, Jia K, Qing C, Tao D (2016) DehazeNet: an end-to-end system for single image haze removal. IEEE Trans Image Process 25(11):5187–5198. https://doi.org/10.1109/TIP.2016.2598681

    MathSciNet  MATH  Article  Google Scholar 

  56. 56.

    Xu L, Yan Q, Xia Y, Jia J (2012) Structure extraction from texture via relative total variation. ACM Trans Graph 31(6):1391–13910. https://doi.org/10.1145/2366145.2366158

    Article  Google Scholar 

  57. 57.

    Boor CD (1962) Bicubic Spline Interpolation. J Math Phys 41:212–218. https://doi.org/10.1145/2366145.2366158

    MathSciNet  MATH  Article  Google Scholar 

  58. 58.

    Omer I, Werman M (2004) Color lines: image specific color representation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Washington, DC, USA. https://doi.org/10.1109/cvpr.2004.1315267

  59. 59.

    Santra S Chanda B (2015) Single image dehazing with varying atmospheric light intensity. IEEE National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), Patna, India. https://doi.org/10.1109/ncvpripg.2015.7490015

  60. 60.

    Yu T, Song K, Miao P, Yang G, Yang H, Chen C (2019) Nighttime single image dehazing via pixel-wise alpha blending. IEEE Access 7:114619–114630. https://doi.org/10.1109/ACCESS.2019.2936049

    Article  Google Scholar 

  61. 61.

    Sun S, Guo X (2017) Image Enhancement Using Bright Channel Prior. IEEE International Conference on Industrial Informatics—Computing Technology, Intelligent Technology, Industrial Information Integration (ICIICII), Wuhan, China. https://doi.org/10.1109/iciicii.2016.0031

  62. 62.

    Land EH (1977) The retinex theory of color vision. Sci Am 237(6):108–128. https://doi.org/10.1038/scientificamerican1277-108

    Article  Google Scholar 

  63. 63.

    Pharr M, Humphreys G (2010) Physically Based Rendering: From Theory to Implementation. Morgan Kaufmann, San Francisco

    Google Scholar 

  64. 64.

    Narasimhan SG, Wang C, Nayar SK (2002) All the images of an outdoor scene. European Conference on Computer Vision, Copenhagen, Denmark, pp 148–162

  65. 65.

    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. https://doi.org/10.1109/TIP.2015.2456502

    MathSciNet  MATH  Article  Google Scholar 

  66. 66.

    Negru M, Nedevschi S, Peter RI (2015) Exponential contrast restoration in fog conditions for driving assistance. IEEE Trans Intell Transp Syst 16(4):2257–2268. https://doi.org/10.1109/TITS.2015.2405013

    Article  Google Scholar 

  67. 67.

    Pavlic M, Rigoll G, Ilic S (2013) Classification of images in fog and fog-free scenes for use in vehicles. IEEE Intelligent Vehicles Symposium, Gold Coast, Australia pp 481–486. https://doi.org/10.1109/ivs.2012.6232256

  68. 68.

    Huang SC, Chen BH, Cheng YJ (2014) An efficient visibility enhancement algorithm for road scenes captured by intelligent transportation systems. IEEE Trans Intell Transp Syst 15(5):2321–2332. https://doi.org/10.1109/TITS.2014.2314696

    Article  Google Scholar 

  69. 69.

    Hautiere N, Tarel JP, Halmaoui H, Bremond R, Aubert D (2014) Enhanced fog detection and free-space segmentation for car navigation. Mach Vis Appl 25(3):667–679. https://doi.org/10.1007/s00138-011-0383-3

    Article  Google Scholar 

  70. 70.

    Hautiere N, Tarel JP, Aubert D (2010) Mitigation of visibility loss for advanced camera-based driver assistance”. IEEE Trans Intell Transp Syst 11(2):474–484. https://doi.org/10.1109/TITS.2010.2046165

    Article  Google Scholar 

  71. 71.

    Long J, Shi ZW, Tang W, Zhang CS (2014) Single remote sensing image dehazing. IEEE Geosci Remote Sens Lett 11(1):59–63. https://doi.org/10.1109/LGRS.2013.2245857

    Article  Google Scholar 

  72. 72.

    Makarau A, Richter R, Muller R, Reinartz P (2014) Haze detection and removal in remotely sensed multispectral imagery. IEEE Trans Geosci Remote Sens 52(9):5895–5905. https://doi.org/10.1109/TGRS.2013.2293662

    Article  Google Scholar 

  73. 73.

    Pan XX, Xie FY, Jiang ZG, Yin JH (2015) Haze removal for a single remote sensing image based on deformed haze imaging model. IEEE Signal Process Lett 22(10):1806–1810. https://doi.org/10.1109/LSP.2015.2432466

    Article  Google Scholar 

  74. 74.

    Sabu A, Vishwanath N (2016) An improved visibility restoration of single haze images for security surveillance systems. IEEE Online International Conference on Green Engineering and Technologies, Coimbatore, India. https://doi.org/10.1109/GET.2016.7916635

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Sriparna Banerjee.

Ethics declarations

Conflict of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Banerjee, S., Sinha Chaudhuri, S. Nighttime Image-Dehazing: A Review and Quantitative Benchmarking. Arch Computat Methods Eng (2020). https://doi.org/10.1007/s11831-020-09485-3

Download citation

Keywords

  • Nighttime image-dehazing survey
  • Dark Channel Prior
  • Spatially varying illumination characteristics
  • Glow characteristics
  • Nighttime hazy image models
  • N-HAZE database