Video Defogging Based on Adaptive Tolerance

Dark channel prior is a kind of statistics of the haze-free outdoor images, which is widely used in image defogging. But when the image contains a large bright region, such as sky and white object, the prior will cause color distortion in these bright regions because of the underestimated transmission. To solve this problem, a video defogging technology based on adaptive tolerance is presented in this paper, and it is applied to video defogging by combining with the guided filter. First, the transmission of each video frame is estimated according to the dark channel prior, and then it is fast refined by the guided filter for restoration. If a large bright region exists in the video frame, the transmission of these regions will be corrected according to the adaptive tolerance, which avoids the color distortion in the video defogging. For the video of dynamic scenes which are caused by camera motion, each frame is defogged as a single image. But for the video of static scenes whose background is almost invariant, the transmission of the background is estimated and used for the defogging of all the frames instead of estimating the transmission of each frame. In this way, the rate of video defogging is greatly improved. Experimental results show that the algorithm has a strong applicability, and the proposed method can be further used for many applications, such as outdoor surveillance, remote sensing and intelligent vehicles. DOI: http://dx.doi.org/10.11591/telkomnika.v10i7.1556 Full Text: PDF

[1]  Robby T. Tan,et al.  Visibility in bad weather from a single image , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Henning Titi Ciptaningtyas,et al.  A Video Streaming Application Using Mobile Media Application Programming Interface , 2010 .

[3]  Kartika Firdausy,et al.  IMAGE ENHANCEMENT USING CONTRAST STRETCHING ON RGB AND IHS DIGITAL IMAGE , 2007 .

[4]  Shree K. Nayar,et al.  Contrast Restoration of Weather Degraded Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  S. Nayar,et al.  Interactive ( De ) Weathering of an Image using Physical Models ∗ , 2003 .

[6]  Jian Sun,et al.  Guided Image Filtering , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Shree K. Nayar,et al.  Chromatic framework for vision in bad weather , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[8]  S. G. Narasimhan,et al.  Interactive Deweathering of An Image Using Physical Model , 2003 .

[9]  Raanan Fattal.  Single image dehazing , 2008, SIGGRAPH 2008.

[10]  Ric,et al.  BLIND CONTRAST ENHANCEMENT ASSESSMENT BY GRADIENT RATIOING AT VISIBLE EDGES , 2008 .

[11]  Shree K. Nayar,et al.  Instant dehazing of images using polarization , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.