Enhancement Methods for Low Visibility and Fog Degraded Images

The images captured in fog conditions have degraded contrast, that makes current image processing applications sensitive and error prone. We propose in this paper an efficient image enhancement algorithm suitable for daytime fog conditions and based on the Koschmieder's model. Using this mathematical model together with an original inference of the atmospheric veil induced by the fog we are able to recover the original fog-free image. A quantitative and qualitative evaluation is performed on both synthetic and real camera images. Our algorithm is suitable for both color and gray scale images and is able to perform image enhancement in real time.

Computer vision applications such as Object Detection, Outdoor Surveillance, Object Tracking, Segmentation, consumer electronics and many more require restoration of images captured in foggy environment. Fog/haze is formed as a result of environment attenuation and air light (scattering of light) resulting in image degradation since the contrast of the scene is reduced by attenuation while the whiteness in the scene is increased by airlight. Hence, the objective of fog removal algorithms is to recover the color and contrast of the scene. Also, formation of fog is the function of the depth and estimation of depth information requires assumptions or prior information of the single image. Hence, with various assumptions on the single image, fog removal algorithms estimate the depth information, which are discussed in this paper.

Fog is the natural phenomenon that causes severe difficulties in driving & results in major accidents. Fog degrades the view of an object and results in poor visibility. The poor visibility of an object becomes challenge to the driver to identify the object and monitor it. It creates lots of difficulties in driving and monitoring the vehicle. There is lots of research on the topic but still the problem has not solved to the desired result. There exist several kinds of environment variations that make the foggy image enhancement more difficult. Therefore an efficient algorithm is required to cope up with several challenges arising from the nature of visibility enhancement of foggy images.

2017

Images are very important parts of dat to day life. They plays very important role in analyzing traffic on roadways, railways and airways.Sometimes due to bad weather effect the analysis through these images becomes difficult. As weather effect degrade the quality of images and those images suffer low contrast, color alteration and shrink the resolution of the captured object in open-air. The reason behind this problem is that the light capture by the lens of the capturing device get spread by the atmosphere. So it was found that conventional techniques used for enhancing the images are not sufficient for removing foggy effect or any other weather effect from the captured images. In this work, we have analyzed the hand techniques employed for image processing. And through that analysis we propose a technique which is efficient technique for enhancing the quality of degraded images. This technique consists of two phases, the first phase is used to remove fog from an image using a Fog...

17th International IEEE Conference on Intelligent Transportation Systems (ITSC), 2014

The images captured in fog conditions have degraded contrast, that makes current image processing applications sensitive and error prone. We propose in this paper an efficient single image enhancement algorithm suitable for daytime fog conditions and based on an original mathematical model, for computing the atmospheric veil, that takes into account the variation in fog density to the distance. This model is inspired by the functions that appear in partition of unity in the differential geometry field. When observing images captured in fog conditions, usually the fog has a very low density in front of the camera and this density has a non-linear increase with the distance, such that objects are no longer visible at greater distances. By using our mathematical model we are able to obtain superior reconstructions of the original fog-free image, when comparing to traditional methods. Another advantage of our method is the ability to adapt the model in accordance to the density of the fog. A quantitative and qualitative evaluation is performed on both synthetic and real camera images. This evaluation proves that our mathematical model is more suitable for image enhancement in both homogeneous and heterogeneous fog conditions. Our algorithm is able to perform image enhancement in real time for both color and gray scale images.

2016

Image enhancement processes consist of a collection of techniques that inquire about to improve the visual appearance of degraded image. This paper introduces a multimodal enhancement technique for dense foggy images. The present available techniques don't work in low visibility like dense fog. The proposed methods changes the intensity component among the converted HIS components from the RGB components of the original foggy image. Again by converting back to RGB components, the foggy image tends to appear more clearly than the original image in terms of Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE).[2] Finally the enhanced foggy image is obtained and the results are presented [9].

Computers, Materials & Continua

In recent years, video surveillance application played a significant role in our daily lives. Images taken during foggy and haze weather conditions for video surveillance application lose their authenticity and hence reduces the visibility. The reason behind visibility enhancement of foggy and haze images is to help numerous computer and machine vision applications such as satellite imagery, object detection, target killing, and surveillance. To remove fog and enhance visibility, a number of visibility enhancement algorithms and methods have been proposed in the past. However, these techniques suffer from several limitations that place strong obstacles to the real world outdoor computer vision applications. The existing techniques do not perform well when images contain heavy fog, large white region and strong atmospheric light. This research work proposed a new framework to defog and dehaze the image in order to enhance the visibility of foggy and haze images. The proposed framework is based on a Conditional generative adversarial network (CGAN) with two networks; generator and discriminator, each having distinct properties. The generator network generates fog-free images from foggy images and discriminator network distinguishes between the restored image and the original fog-free image. Experiments are conducted on FRIDA dataset and haze images. To assess the performance of the proposed method on fog dataset, we use PSNR and SSIM, and for Haze dataset use e, r − , and σ as performance metrics. Experimental results shows that the proposed method achieved higher values of PSNR and SSIM which is 18.23, 0.823 and lower values produced by the compared method which are 13.94, 0.791 and so on. Experimental results This work is licensed under a Creative Commons Attribution 4.

2016

The visibility of outdoor images captured in inclement weather is often degraded due to the presence of haze, fog, sandstorms and so on. Poor visibility caused by atmospheric phenomena in turn causes failure in computer vision applications, such as obstacle detection systems, outdoor object recognition systems, and intelligent transportation systems and video surveillance systems. In order to solve this problem, visibility restoration techniques have been developed and play an important role in many computer vision applications that operate in various weather conditions. However, removing haze from a single image with a complex structure and color distortion is a difficult task for visibility restoration techniques. This paper proposes a novel visibility restoration method that uses a combination of three major modules: A depth estimation (DE) module, A color analysis (CA) module, and A visibility restoration (VR) module. The proposed depth estimation module takes advantage of the m...

IARJSET, 2016

This paper describes the problem of visibility of outdoor images under haze and poor light condition. Visibility is a very important issue in case of computer based surveillance, crime analysis, driver assistance system design etc. The most important challenge related to visibility is the atmospheric haze and poor lighting. The problem becomes more challenging if haze is too dense and lighting during night is extremely poor. The image processing is the vast emerging field in the era of technology of machine vision, machine intelligence and automation for real time processing or the post processing of the image captured in different atmospheric conditions. The image captured in the outdoor scene are highly degraded due to the poor lighting condition or over lighting condition or due to the presence of different suspension particle like the water droplets or dust particles. So due to these particles the irradiance coming from the object is scattered or absorbed. And hence the phenomena of haze, smoke and fog occurs. The haze removal is very essential in the field of image processing because the different computer vision algorithm assumes the input image as the original scene radiance or scene reflectance. But in most outdoor processing the images are degraded due to hazy, hence the input image is hazy image not the original radiance. In this paper we presented a technique Dark channel prior and Adaptive Histogram Equalization to improve visibility of outdoor images for different atmospheric condition.

International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2022

Haze removal is important for computer photography and computer vision applications. However, most of the existing methods for removing the ha-ziness are designed for daytime images and may not always work well at hazy night images. Unlike image conditions during the sunny day, images captured in winter night conditions can suffer from irregular lighting due to artificial light sources with varying colors and non-uniform illumination, which show low brightness, contrast and color distortion. In this paper, we propose a new framework for presenting night-time hazy imaging, which works on haze removal and low-illumination correction algorithm taking into consideration both the non-uniform illumination of artificial light sources and the effects of dispersion and at-tenuation of fog. Therefore, firstly, we will give a hazy low-illuminated image having low light as input and then apply a technique to clarify the visibility of the input image. Then, apply the contrast enhancement and after that apply the LIME technique and finally, apply the white balance technique and we will get our improved output image. The experimental results show that the proposed algorithm can achieve an illumination balance, results without haziness and good color correction capacity.