Contrast-dependent saturation adjustment for outdoor image enhancement

Abstract

Outdoor images captured in bad-weather conditions usually have poor intensity contrast and color saturation since the light arriving at the camera is severely scattered or attenuated. The task of improving image quality in poor conditions remains a challenge. Existing methods of image quality improvement are usually effective for a small group of images but often fail to produce satisfactory results for a broader variety of images. In this paper, we propose an image enhancement method, which makes it applicable to enhance outdoor images by using content-adaptive contrast improvement as well as contrast-dependent saturation adjustment. The main contribution of this work is twofold: (1) we propose the content-adaptive histogram equalization based on the human visual system to improve the intensity contrast; and (2) we introduce a simple yet effective prior for adjusting the color saturation depending on the intensity contrast. The proposed method is tested with different kinds of images, compared with eight state-of-the-art methods: four enhancement methods and four haze removal methods. Experimental results show the proposed method can more effectively improve the visibility and preserve the naturalness of the images, as opposed to the compared methods.

Realtime dehazing using colour uniformity principle

“…Since, the estimated transmission map is a relative map, complete dehazing is not possible by using only (7). Besides that, the primary aim along with dehazing is also to increase the visibility range of the image and maximise the scene information content.…”

“…Metric Q g is defined as ratio of gradients ∇ f and ∇ b after and before the dehazing, respectively, at N v number of visible edges. These metrics are widely used by state of the art techniques [7,[32][33][34] for quantitative comparison of quality of dehazed outputs. Metric Q e measures the increases in visibility compared with input image, while metric Q g measures increase in mean strength of gradient due to dehazing.…”

“…Also, lower CUP metric values may result from smoother/saturated regions which in-turn may result in erroneous estimation of A. More advanced technique such as [7] can be used in place of CLAHE [16] to retain the colour fidelity of dehazed output at cost more processing time. The authors would like to address these limitations in the future.…”

“…From this model, it can be observed that the hazing/fogging introduces a scaled white light addition to scene radiance commonly known as tint. Thus, dehazing process can also be considered as contrast enhancement problem [7]. However, the scaling factor and the amount of white light added vary across the entire image and depend upon the distance of object from camera, the haze composition etc.…”

Image fusion dehazing algorithm based on multi-logarithmic transform

“…The main methods of image enhancement include traditional image enhancement methods, such as histogram equalization [1] and adaptive histogram equalization [2] . Wang et al [3] proposed adaptive histogram equalisation of content based on the human visual system to improve the contrast of hazy images.…”