submitted to IEEE Trans.
Optimized Contrast Enhancement for
Real-Time Image and Video Dehazing

Supplementary Materials

Authors

Abstract

A fast and optimized dehazing algorithm for hazy images and videos is proposed in this work. Based on the observation that a hazy image exhibits low contrast in general, we restore the hazy image by enhancing its contrast. However, the overcompensation of the degraded contrast may cause truncated pixel values. Therefore, we design a cost function to maximize the contrast and minimize the information loss in the restored image simultaneously. Moreover, we extend the static image dehazing algorithm to real-time video dehazing. We reduce flickering artifacts in a dehazed video sequence, based on the assumption that transmission values are temporally coherent. Experimental results show that the proposed algorithm effectively removes haze and is sufficiently fast for real-time dehazing applications.

Experiental results

Image dehazing results

The original
Image
The transmission Map
The results of
the proposed algorithm

Image dehazing results using various

The original
Image
The results of
=1
The results of
=2
The results of
=3
The results of
=8

Comparative Image dehazing results

The original
Image
The results of
Fattal's algorithm1
The results of
Tan's algorithm2
The results of
Kopf et al.'s algorithm3
The results of
Tarel et al.'s algorithm4
The results of
He et al.'s algorithm5
The results of
the proposed algorithm
1R. Fattal, “Single image dehazing,” ACM Trans. Graph., vol. 27, no. 3, pp. 1–9, Aug. 2008.
2R. Tan, “Visibility in bad weather from a single image,” in Proc. IEEE CVPR, Jun. 2008, pp. 1–8.
3J. Kopf, B. Neubert, B. Chen, M. Cohen, D. Cohen-Or, O. Deussen, M. Uyttendaele, and D. Lischinski, “Deep photo: Model-based photograph enhancement and viewing,” ACM Trans. Graph., vol. 27, no. 5, pp. 1–10, Dec. 2008.
4J. Tarel and N. Hautiere, “Fast visibility restoration from a single color or gray level image,” in Proc. IEEE ICCV, Sep. 2009, pp. 2201–2208.
5K. He, J. Sun, and X. Tang, “Single image haze removal using dark channel prior,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 12, pp. 1956–1963, Jun. 2011.

Comparative video dehazing results

Hazy
Sequence
Frame-by-frame
Proposed

Related Paper

Jin-Hwan Kim, Won-Dong Jang, Yongsup Park, Dong-Hahk Lee, Jae-Young Sim, and Chang-Su Kim, "Temporally coherent real-time video dehazing," to appear in Proc. IEEE ICIP, Orlando, Florida, Sep. 2012.
Jin-Hwan Kim, Jae-Young Sim, and Chang-Su Kim, "Single image dehazing based on contrast enhancement," Proc. International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, May 2011.