Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Depth estimation for underwater images from single view image

© The Institution of Engineering and Technology
Received 02/12/2019, Accepted 13/11/2020, Revised 12/11/2020, Published 07/12/2020

Underwater images often undergo distortions from scattering, absorption, colour loss, diffraction, polarisation, and varying attenuation depending on the light frequency, due to the water medium. This study answers problems associated with the recovery of underwater images, by developing novel depth map estimation which may be used as an intermediary step for underwater image restoration. The depth map is an important factor for the recovery of the underwater image, as it has been shown that proper estimation of depth, results in better restoration of the underwater image. The proposed algorithm estimates a depth map from a single view image, using blurriness and lighting information, obtained using a simple background neutralisation method. Results from the algorithm on selected raw underwater image data set have been compared with other algorithms and it has been shown that the proposed method gives Pearson coefficients in the range of 0.75–0.95, which are considerably higher and better log root mean square value compared to other methods in the literature. This suggests a better estimation of depth by the proposed method.

Inspec keywords: image restoration; oceanographic techniques; geophysical image processing; image reconstruction

Other keywords: selected raw underwater image data; depth estimation; underwater image restoration; single view image; depth map estimation

Subjects: Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research; Optical, image and video signal processing; Computer vision and image processing techniques

References

    1. 1)
      • 34. Godard, C., Aodha, O., Firman, M., et al: ‘Digging into self-supervised monocular depth estimation’. Proc. IEEE Int. Conf. Computer Vision, Seoul, South Korea, October 2019, pp. 1–18.
    2. 2)
      • 26. Bryson, M., Johnson, R., Matthew Pizarro, O., et al: ‘true color correction of autonomous underwater vehicle imagery’, J. Field Robot., 2015, 33, (6), pp. 853–874.
    3. 3)
      • 28. Yamashita, A., Fujii, M., Kaneko, T.: ‘Color registration of underwater images for underwater sensing with consideration of light attenuation’. Proc. IEEE Int. Conf. Robotics and Automation, Rome, Italy, April 2007, pp. 4570–4575.
    4. 4)
      • 31. Zhang, H., Sindagi, V., Patel, V.M.: ‘Joint transmission map estimation and dehazing using deep networks’, IEEE Trans. Circuits Syst. Video Technol., 2020, 30, (7), pp. 1975–1986.
    5. 5)
      • 4. Anwar, S., Li, C., Porikli, F.: ‘Deep underwater image enhancement’, J. Comput. Vis. Pattern Recogn., 2018, 10, pp. 1–12.
    6. 6)
      • 8. Fabbri, C., Islam, M.J., Sattar, J.: ‘Enhancing underwater imagery using generative adversarial networks’. Proc. Int. Conf. Robotics and Automation, Brisbane, Australia, May 2018, pp. 7159–7165.
    7. 7)
      • 14. Galdran, A., Pardo, D., Picón, A., et al: ‘Automatic red-channel underwater image restoration’, J. Vis. Commun. Image Represent., 2015, 26, pp. 132–145.
    8. 8)
      • 22. Levin, A., Lischinski, D., Weiss, Y.: ‘A closed form solution to natural image matting’. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, New York, USA, December 2006, pp. 1–10.
    9. 9)
      • 13. Emberton, S., Chittka, L., Cavallaro, A.: ‘Hierarchical rank-based veiling light estimation for underwater dehazing’. Proc. British Conf. Machine Vision, Swansea, UK, September 2015, pp. 125.1–125.12.
    10. 10)
      • 23. Lu, H., Li, Y., Nakashima, S., et al: ‘Turbidity underwater image restoration using spectral properties and light compensation’, IEICE Trans. Inf. Syst., 2016, E99.D, (1), pp. 219–227.
    11. 11)
      • 33. Godard, C., Aodha, O., Gabriel, J.: ‘Unsupervised monocular depth estimation with left-right consistency’. Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Honolulu, USA, November 2017, pp. 1–10.
    12. 12)
      • 20. Chiang, J.Y., Chen, Y.: ‘Underwater image enhancement by wavelength compensation and dehazing’, IEEE Trans. Image Process., 2012, 21, (4), pp. 1756–1769.
    13. 13)
      • 25. Berman, D., Levy, D., Avidan, S.: ‘Underwater single image color restoration using haze-lines and a new quantitative dataset’, IEEE Trans. Pattern Anal. Mach. Intell., 2018, 1, pp. 1–13.
    14. 14)
      • 12. Drews, P.Jr., Nascimento, E.D., Moraes, F., et al: ‘Transmission estimation in underwater single images’. Proc. Int. Conf. Computer Vision Workshops, Sydney, Australia, December 2013, pp. 825–830.
    15. 15)
      • 32. Soille, P.: ‘Morphological image analysis. Principles and applications’ (Springer-Verlag Berlin Heidelberg, Berlin, Germany, 1999, 2nd edn. 2004), pp. 173–174.
    16. 16)
      • 29. Zhao, X., Jin, T., Qu, S.: ‘Deriving inherent optical properties from background color and underwater image enhancement’, J. Ocean Eng., 2015, 94, pp. 163–172.
    17. 17)
      • 5. Hu, Y., Wang, K., Zhao, X.: ‘Underwater image restoration based on convolutional neural network’. Proc. Asian Conf. Machine Learning, Beijing, China, November 2018, pp. 296–311.
    18. 18)
      • 19. Yang, H., Chen, P., Huang, C., et al: ‘Low complexity underwater image enhancement based on dark channel prior’. Proc. Int. Conf. Innovations in Bio-inspired Computing and Applications, Shenzan, China, December 2011, pp. 17–20.
    19. 19)
      • 21. He, K., Sun, J., Tang, X.: ‘Guided image filtering’, IEEE Trans. Pattern Anal. Mach. Intell., 2013, 35, (6), pp. 1397–1409.
    20. 20)
      • 10. He, K., Sun, J., Tang, X., et al: ‘Single image haze removal using dark channel prior’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (12), pp. 2341–2353.
    21. 21)
      • 18. Liu, C., Meng, W.: ‘Removal of water scattering’. Proc. Int. Conf. Computer Engineering and Technology, Chengdu, China, April 2010, pp. 35–39.
    22. 22)
      • 16. Peng, Y., Zhao, X., Cosman, P.C.: ‘Underwater image restoration based on image blurriness and light absorption’, IEEE Trans. Image Process., 2017, 26, (4), pp. 1579–1594.
    23. 23)
      • 2. Garcia, R., Nicosevici, T., Gracias, N., et al: ‘Exploring the seafloor with underwater robots: land, sea & air’, in Lopez, A.M., Imiya, A., Pajdla, T., et al (Eds): ‘Computer vision in vehicle technology’ (John Wiley & Sons Ltd, Barcelona, 2017), pp. 75–99.
    24. 24)
      • 3. Jarina Raihan, A., Emeroylariffion, A., Liyanage, C.: ‘Review of underwater image restoration algorithms’, J. IET Image Process., 2019, 13, (10), pp. 1587–1596.
    25. 25)
      • 7. Lu, H., Xu, X., Kim, H.: ‘Underwater light field depth map restoration using deep convolutional neural fields’, in Lu, H., Xi, X., (Eds): ‘Artificial intelligence and robotics’ (Springer Int. publishing press, Switzerland, 2018), pp. 305–312.
    26. 26)
      • 17. Akkaynak, D., Treibitz, T.: ‘A revised underwater image formation model’. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, Salt Lake City, USA, June, 2018, pp. 6723–6732.
    27. 27)
      • 24. Ancuti, C.O., Ancuti, C., De Vleeschouwer, C., et al: ‘Color transfer for underwater dehazing and depth estimation’. Proc. IEEE Int. Conf. Image processing, Beijing, China, September 2017, pp. 695–699.
    28. 28)
      • 1. Biegański, W., Kasiński, A.: ‘Image acquisition in an underwater vision system with NIR and VIS illumination’, J. Comput. Sci. Inf. Technol., 2014, 4, pp. 1–10.
    29. 29)
      • 30. Cao, Y., Wu, Z., Shen, C.: ‘Estimating depth from monocular images as classification using deep fully convolutional residual networks’, IEEE Trans. Circuits Syst. Video Technol., 2018, 28, (11), pp. 3174–3182.
    30. 30)
      • 11. Wen, H., Tian, Y., Huang, T., et al: ‘Single underwater image enhancement with a new optical model’. Proc. Int. Symp. Circuits and Systems, Beijing, China, May 2013, pp. 753–756.
    31. 31)
      • 9. Li, J., Skinner, K.A., Eustice, R.M.: ‘Watergan: unsupervised generative network to enable real-time color correction of monocular underwater images’, IEEE Robot. Autom. Lett., 2018, 3, (1), pp. 387–394.
    32. 32)
      • 15. Carlevaris-Bianco, N., Mohan, A., Eustice, R.M.: ‘Initial results in underwater single image dehazing’. Proc. OCEANS MTS, Seattle, USA, September 2010, pp. 1–8.
    33. 33)
      • 27. Bryson, M., Johnson, R., Matthew Pizarro, O., et al: ‘Colour-consistent structure-from-motion models using underwater imagery’, J. Robot.: Sci. Syst., 2012, pp. 1–8.
    34. 34)
      • 6. Wang, Y., Zhang, J., Cao, Y., et al: ‘A deep CNN method for underwater image enhancement’. Proc. Int. Conf. Image Processing, Beijing, China, September 2017, pp. 1382–1386.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2019.1533
Loading

Related content

content/journals/10.1049/iet-ipr.2019.1533
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address