Segmentation-based image defogging using modified dark channel prior

Abstract

Image acquisition under bad weather conditions is prone to yield image with low contrast, faded color, and overall poor visibility. Different computer vision applications including surveillance, object classification, tracking, and recognition get effected due to degraded hazy images. Dehazing can significantly improve contrast, balance luminance, correct distortion, remove unwanted visual effects/ and therefore enhance the image quality. As a result, image defogging is imperative pre-processing step in computer vision applications. Previously, dark channel prior-based algorithms have proven promising results over the available techniques. In this paper, we have proposed a modified dark channel prior that uses fog density and guided image-filtering technique to estimate and refine transmission map, respectively. Guided image filter speeds up the refinement of transmission map, hence reduces the overall computational complexity of algorithm. We have also incorporated segmentation of the foggy image into sky and non-sky regions, after which, the modified dark channel prior and atmospheric light is computed for each segment. Then, the average value of atmospheric light for each segment is used to estimate transmission map. We have performed quantitative and subjective comparison for effective evaluation of our proposed algorithm against the current state-of-the-art algorithms on natural and synthetic images. Different quality metrics, such as saturation, mean square error, fog density, peak signal to noise ratio, structural similarity index metric, dehazing algorithm index (DHQI), full-reference image quality assessmen (FR-IQA), and naturalness of dehazed images have shown the proposed algorithm to be better than existing techniques.

Image Defogging Framework Using Segmentation and the Dark Channel Prior

“…In this section, the benefits of our proposed method are evaluated in terms of computational complexity with respect to images of different sizes. Table 1 represents the comparative analysis of computational complexity with the G. Wang's method [43], W. Wang's method [37], two methods proposed by A. Sabir [44], S. Salazar-Colores's method [45] and our proposed method. Our proposed method requires much less processing time than other stated techniques under similar software and hardware conditions.…”

“…Thus, the value should be changed according to the image to get the best result. The first method proposed by A. Sabir [44] is a modified dark channel prior for image defogging. It is a slight modification of the original dark channel prior technique.…”

Advances in lane marking detection algorithms for all-weather conditions

“…An image pre-processing technique in foggy weather is presented in [30] based on segmentation. The proposed approach is developed based on the improved dark channel approach to better defogged the image captured in foggy weather.…”

A Single Image Dehazing Technique Using the Dual Transmission Maps Strategy and Gradient-Domain Guided Image Filtering

“…The former approach, somehow, improves the quality of resultant images but loses details, especially near edges. The latter approach -such as color attenuation prior [15] and dark channel prior [16] [17] -on the other hand, obtain quality haze-free images and retain the crucial information, by maximizing the local contrast of the input hazy image and enhances the visibility of degraded images.…”

“…Recently, a significant amount of research has been carried out on single image dehazing algorithms, which improves the efficiency, computational time, and quality of degraded images [16] [17] [18]. The algorithms improve several characteristics of hazy images, such as visibility, contrast, and produce the natural color of output images due to better assumptions and priors.…”