Abstract
Outdoor images are vulnerable to environment and may suffer various distortions. Therefore, preprocessing for images captured in bad weather is particularly important for computer vision system. One of the most common conditions is haze. Image dehazing, especially single image dehazing is a challenging topic since it’s an ill-posed problem and needs to rely on extra information or prior. In this paper, we discussed the shortcomings of existing algorithms and proposed a novel step called Local Adaptive Template. The template is used in transmission estimation and transmission refinement. Starting from the target pixel, the template is extracted under the guidance of the similarity function and only contains pixels related to the center point, thus avoids the influence of adjacent objects, even those with blur edges. We then used the template to improve the Dark Channel Prior(DCP) and the Guided Filter(GF) respectively, and effectively avoided the block effect in DCP and the blur in GF. The obtained transmission map is much more accurate, and free from the halo effect. The dehazing result is much clearer and still looks natural without haze residual. Experiments on natural images and synthetic images show that our method achieves better dehazing results than several state-of-art algorithms and can adapt to different situations.
Highlights
Under bad weather conditions, light will be scattered by suspended particles such as fog or haze
In this paper we focused on the halo effect, and proposed a Local Adaptive Template to improve both the transmission estimation and transmission refinement
Main contributions: Instead of estimating and refining the transmission map in a square region, we proposed a novel template extraction approach called ‘‘Local Adaptive Template’’:
Summary
Light will be scattered by suspended particles such as fog or haze. Images reconstructed by physical model are closer to the original scenes They can adapt to the depth change of complex scenes, and obtain more structure information. It’s based on the algorithm proposed by He who goes through lots of outdoor clear images, and finds out that in most of the natural images, most pixels other than the sky area have at least one color channel with very low intensity value [13] Such characteristic can be used to estimate the transmission map, and with the help of soft mapping algorithm, the haze free image can be achieved. To obtain better dehazing results, some improvements on the template of Guided Filter and Dark Channel Prior have been proposed. They aim to solve the block effect in DCP and the blur in GF. We use the template in DCP and GF, and manage to obtain clear images free from the halo effect
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
