Images degraded by haze usually have low contrast and fide colours, and thus have bad effects on applications such as object tracking, face recognition, and intelligent surveillance. So the purpose of dehazing is to recover the image contrast without colour distortion. The dark channel prior (DCP) is widely used in the field of haze removal because of its simplicity and effectiveness. However, when faced with bright white objects, DCP overestimates the haze from its true value and thus causes colour distortion. In this study, the authors propose a dehazing model combining saliency detection with DCP to obtain recovered images with little colour distortion. There are three main contributions. First, they introduce a novel saliency detection method, focusing on superpixel intensity contrast, to extract bright white objects in the hazy image. Those objects are not used to estimate the atmospheric light and transmission in the dark channel image. Second, a self-adaptive upper bound is set for the scene radiance to prevent some regions being too bright. Third, they propose a quantitative indicator, colour variance distance, to evaluate the colour restoration. Experimental results show that their proposed model generates less colour distortion and has better comprehensive performance than competing models.

References

1. 1)
  - 14. Koch, C., Ullman, S.: ‘Shifts in selective visual attention: towards the underlying neural circuitry’, Human Neurbiol., 1985, 4, (4), pp. 219–227.
2. 2)
  - 16. Hou, X., Zhang, L.: ‘Saliency detection: a spectral residual approach’. IEEE Conf. Computer Vision and Pattern Recognition, Minneapolis, Minnesota, USA, June 2007, pp. 1–8.
3. 3)
  - 26. Yu, J., Xu, D., Liao, Q.: ‘Image defogging: a survey’, J. Image Graph., 2011, 16, (9), pp. 1561–1576.
4. 4)
  - 1. Zhang, W., Liang, J., Ren, L., et al: ‘Real-time image haze removal using an aperture-division polarimetric camera’, Appl. Opt., 2017, 56, (4), pp. 942–947.
5. 5)
  - 23. Levinshtein, A., Stere, A., Kutulakos, K.N., et al: ‘Turbopixels: fast superpixels using geometric flows’, IEEE Trans. Pattern Anal. Mach. Intell., 2009, 31, (12), pp. 2290–2297.
6. 6)
  - 15. Itti, L., Koch, C., Niebur, E.: ‘A model of saliency-based visual attention for rapid scene analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 1998, 20, (11), pp. 1254–1259.
7. 7)
  - 9. He, K., Sun, J., Tang, X.: ‘Single image haze removal using dark channel prior’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (12), pp. 2341–2353.
8. 8)
  - 18. Achanta, R., Hemami, S., Estrada, F., et al: ‘Frequency-tuned salient region detection’. IEEE Conf. Computer Vision and Pattern Recognition, Miami, FL, USA, June 2009, pp. 1597–1604.
9. 9)
  - 2. Tripathi, A.K., Mukhopadhyay, S.: ‘Single image fog removal using anisotropic diffusion’, IET Image Process.., 2012, 6, (7), pp. 966–975.
10. 10)
  - 25. Wang, Z., Bovik, A.C., Sheikh, H.R., et al: ‘Image quality assessment: from error visibility to structural similarity’, IEEE Trans. Image Process., 2004, 13, (4), pp. 600–612.
11. 11)
  - 20. Cheng, M.M., Mitra, N.J., Huang, X., et al: ‘Global contrast based salient region detection’, IEEE Trans. Pattern Anal. Mach. Intell., 2015, 37, (3), pp. 569–582.
12. 12)
  - 8. Tarel, J.P., Hautière, N.: ‘Fast visibility restoration from a single color or gray level image’. Proc. IEEE Int. Conf. Computer Vision, Kyoto, Japan, September 2009, pp. 2201–2208.
13. 13)
  - 10. Li, Z., Zheng, J.: ‘Edge-preserving decomposition-based single image haze removal’, IEEE Trans. Image Process., 2015, 24, (12), pp. 5432–5441.
14. 14)
  - 21. Narasimhan, S.G., Nayar, S.K.: ‘Vision and the atmosphere’, Int. J. Comput. Vis., 2002, 48, (3), pp. 233–254.
15. 15)
  - 6. Kopf, J., Neubert, B., Chen, B., et al: ‘Deep photo: model-based photograph enhancement and viewing’, ACM Trans. Graph., 2008, 27, (5), pp. 116:1–116:10.
16. 16)
  - 3. Cui, T., Tian, J., Wang, E., et al: ‘Single image dehazing by latent region-segmentation based transmission estimation and weighted L1-norm regularisation’, IET Image Process., 2016, 11, (2), pp. 145–154.
17. 17)
  - 4. Meng, G., Wang, Y., Duan, J., et al: ‘Efficient image dehazing with boundary constraint and contextual regularization’. Proc. IEEE Int. Conf. Computer Vision, Sydney, Australia, December 2013, pp. 617–624.
18. 18)
  - 19. Shi, J., Yan, Q., Xu, L., et al: ‘Hierarchical image saliency detection on extended CSSD’, IEEE Trans. Pattern Anal. Mach. Intell., 2016, 38, (4), pp. 717–729.
19. 19)
  - 5. Narasimhan, S.G., Nayar, S.K.: ‘Contrast restoration of weather degraded images’, IEEE Trans. Pattern Anal. Mach. Intell., 2003, 25, (6), pp. 713–724.
20. 20)
  - 17. Harel, J., Koch, C., Perona, P.: ‘Graph-based visual saliency’. Proc. Advances in Neural Information Processing Systems, 2007, vol. 19, pp. 545–552.
21. 21)
  - 7. Tan, R.T.: ‘Visibility in bad weather from a single image’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Anchorage, Alaska, USA, June 2008, pp. 1–8.
22. 22)
  - 22. He, K., Sun, J., Tang, X.: ‘Guided image filtering’, IEEE Trans. Pattern Anal. Mach. Intell., 2013, 35, (6), pp. 1397–1409.
23. 23)
  - 13. Sulami, M., Glatzer, I., Fattal, R., et al: ‘Automatic recovery of the atmospheric light in hazy images’. Proc. IEEE Int. Conf. Computational Photography, Santa Clara, CA, USA, May 2014, pp. 1–11.
24. 24)
  - 12. Yu, T., Riaz, I., Piao, J., et al: ‘Real-time single image dehazing using block-to-pixel interpolation and adaptive dark channel prior’, IET Image Process., 2015, 9, (9), pp. 725–734.
25. 25)
  - 24. Hautière, N., Tarel, J.P., Aubert, D., et al: ‘Blind contrast enhancement assessment by gradient rationing at visible edges’, J. Image Anal. Stereol., 2011, 27, (2), pp. 87–95.
26. 26)
  - 11. Tang, K., Yang, J., Wang, J.: ‘Investigating haze-relevant features in a learning framework for image dehazing’. IEEE Conf. Computer Vision and Pattern Recognition, Columbus, OH, USA, June 2014, pp. 2995–3002.

Saliency-based dark channel prior model for single image haze removal

References

Related content