Abstract
Single image de-hazing is an important and challenging research topic in computer vision. The computational efficiency and robustness of this issue are key problems in real-time applications. In this paper, a graphic processing unit (GPU)-accelerated real-time image enhancing method is proposed to remove haze from a single hazy input image. The foundation of this method is a novel pixel-level optimal de-hazing criterion proposed to combine a virtual hazy-free candidate image sequence into a final single hazy-free image. This image sequence is estimated from the input hazy image by exhausting all possible discretely sampled scene depth values. The main advantage of proposed method is the single pixel independently computing fashion. Its computing at one single pixel position is independent of others. Based on this property, it is straightforward to implement the proposed method with fully parallel GPU acceleration. The sufficient experimentations on various scenes indicate that the proposed method can process a large hazy image with one megapixel to visually moderate haze-free result at a rate of 80 frames/s. Moreover, the proposed method is also less affected by the nonuniform illumination compared to previous methods.
Similar content being viewed by others
References
Shwartz, S., Namer, E., Schechner, Y. Y.: Blind Haze Separation. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1984–1991. IEEE Computer Society, New York (2006)
Narasimhan, S.G., Nayar, S.K.: Contrast restoration of weather degraded images. IEEE Trans. Pattern Anal. Mach. Intell. 25(6), 713–724 (2003)
Narasimhan, S.G., Nayar, S.K.: Vision and the atmosphere. Int. J. Comp. Vis. 48(3), 233–254 (2002)
Narasimhan, S. G., Nayar, S. K.. Chromatic framework for vision in bad weather. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 598–605. IEEE Computer Society (2000)
Hautire, N., Tarel, J., Aubert, D., et al.: Blind contrast enhancement assessment by gradient ratioing at visible edges. Imag. Anal. Stereol. J. 27(2), 87–95 (2008)
Kopf, J., Neubert, B., Chen, B., et al.: Deep photo: model-based photograph enhancement and viewing. ACM Trans. Graph. 27(5), 116 (2008)
Tan, R. T.: Visibility in bad weather from a single image. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE Computer Society, Anchorage, AK, USA (2008)
Fattal, R.: Single image dehazing. ACM Trans. Graph. 2008, 27(3: Article 72):1–9
Carr, P., Hartley, R.: Improved single image dehazing using geometry. In: Digital image computing: techniques and applications, 103–110. IEEE Computer Society, Melbourne, Australia, (2009)
Kratz, L., Nishino, K.: Factorizing scene albedo and depth from a single foggy image. In: Proceedings of IEEE International Conference on Computer Vision, 1701–1708. Kyoto, Japan: IEEE Computer Society (2009)
Oakley, J.P., Bu, H.: Correction of simple contrast loss in color images. IEEE Trans. Imag. Process. 16(2), 511–522 (2007)
He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1956–1963. IEEE Computer Society, Miami Beach, Florida, USA (2009)
Tarel, J. P., Hautiere, N.: Fast visibility restoration from a single color or gray level image. In: Proceedings of IEEE International Conference on Computer Vision, 2201–2208. IEEE Computer Society, Kyoto, Japan (2009)
Ancuti, C. O., Ancuti, C., Bekaert, P.: Effective single image dehazing by fusion. In: International Conference on Image Processing, 3541–3544. IEEE Computer Society, Hong Kong, China (2010)
Nayar, S. K., Narasimhan, S. G.: Vision in bad weather. In: The Proceedings of the Seventh IEEE International Conference on Computer Vision, 820–827. IEEE Computer Society. Kerkyra, Greece (1999)
Wang, Z., Bovik, A.C.: Modern image quality assessment. Morgan & Claypool, New York (2006)
Li, H., Manjunath, B.S., Mitra, S.K.: Multisensor image fusion using the wavelet transform. Graph. Model. Imag. Process. 57(3), 234–245 (1995)
Corporation N. NVIDIA Home. http://www.nvidia.co.uk/page/home.html (2011)
Vytla, L., Hassan, F., Carletta, J.: A real-time implementation of gradient domain high dynamic range compression using a local Poisson solver. J. Real-Time Imag. Proc. (2011). doi:10.1007/s11554-011-0198-5
Akil, M., Grandpierre, T., Perroton, L.: Real-time dynamic tone-mapping operator on GPU [J]. J. Real-Time Imag Proc. (2011). doi:10.1007/s11554-011-0196-7
Acknowledgments
This paper is jointly supported by the National Natural Science Foundation of China (Project No. 61074106) and China Aviation Science Foundation (Project No. 2009ZC57003).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhang, J., Hu, S. A GPU-accelerated real-time single image de-hazing method using pixel-level optimal de-hazing criterion. J Real-Time Image Proc 9, 661–672 (2014). https://doi.org/10.1007/s11554-012-0244-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-012-0244-y