One source of difficulties when processing outdoor images is the presence of haze, fog or smoke which fades the colors and reduces the contrast of the observed objects. We introduce a novel algorithm and variants for visibility restoration from a single image. The main advantage of the proposed algorithm compared with other is its speed: its complexity is a linear function of the number of image pixels only. This speed allows visibility restoration to be applied for the first time within real-time processing applications such as sign, lane-marking and obstacle detection from an in-vehicle camera. Another advantage is the possibility to handle both color images or gray level images since the ambiguity between the presence of fog and the objects with low color saturation is solved by assuming only small objects can have colors with low saturation. The algorithm is controlled only by a few parameters and consists in: atmospheric veil inference, image restoration and smoothing, tone mapping. A comparative study and quantitative evaluation is proposed with a few other state of the art algorithms which demonstrates that similar or better quality results are obtained. Finally, an application is presented to lane-marking extraction in gray level images, illustrating the interest of the approach.

Fast visibility restoration from a single color or gray level image

Image enhancement plays an important role in image processing and analysis. Among various enhancement algorithms, Retinex-based algorithms can efficiently enhance details and have been widely adopted. Since Retinex-based algorithms regard illumination removal as a default preference and fail to limit the range of reflectance, the naturalness of non-uniform illumination images cannot be effectively preserved. However, naturalness is essential for image enhancement to achieve pleasing perceptual quality. In order to preserve naturalness while enhancing details, we propose an enhancement algorithm for non-uniform illumination images. In general, this paper makes the following three major contributions. First, a lightness-order-error measure is proposed to access naturalness preservation objectively. Second, a bright-pass filter is proposed to decompose an image into reflectance and illumination, which, respectively, determine the details and the naturalness of the image. Third, we propose a bi-log transformation, which is utilized to map the illumination to make a balance between details and naturalness. Experimental results demonstrate that the proposed algorithm can not only enhance the details but also preserve the naturalness for non-uniform illumination images.

Naturalness Preserved Enhancement Algorithm for Non-Uniform Illumination Images

Underwater image enhancement has been attracting much attention due to its significance in marine engineering and aquatic robotics. Numerous underwater image enhancement algorithms have been proposed in the last few years. However, these algorithms are mainly evaluated using either synthetic datasets or few selected real-world images. It is thus unclear how these algorithms would perform on images acquired in the wild and how we could gauge the progress in the field. To bridge this gap, we present the first comprehensive perceptual study and analysis of underwater image enhancement using large-scale real-world images. In this paper, we construct an Underwater Image Enhancement Benchmark (UIEB) including 950 real-world underwater images, 890 of which have the corresponding reference images. We treat the rest 60 underwater images which cannot obtain satisfactory reference images as challenging data. Using this dataset, we conduct a comprehensive study of the state-of-the-art underwater image enhancement algorithms qualitatively and quantitatively. In addition, we propose an underwater image enhancement network (called Water-Net) trained on this benchmark as a baseline, which indicates the generalization of the proposed UIEB for training Convolutional Neural Networks (CNNs). The benchmark evaluations and the proposed Water-Net demonstrate the performance and limitations of state-of-the-art algorithms, which shed light on future research in underwater image enhancement. The dataset and code are available at https://li-chongyi.github.io/proj_benchmark.html .

An Underwater Image Enhancement Benchmark Dataset and Beyond

Automatic Red-Channel underwater image restoration

Haze is an atmospheric phenomenon that significantly degrades the visibility of outdoor scenes. This is mainly due to the atmosphere particles that absorb and scatter the light. This paper introduces a novel single image approach that enhances the visibility of such degraded images. Our method is a fusion-based strategy that derives from two original hazy image inputs by applying a white balance and a contrast enhancing procedure. To blend effectively the information of the derived inputs to preserve the regions with good visibility, we filter their important features by computing three measures (weight maps): luminance, chromaticity, and saliency. To minimize artifacts introduced by the weight maps, our approach is designed in a multiscale fashion, using a Laplacian pyramid representation. We are the first to demonstrate the utility and effectiveness of a fusion-based technique for dehazing based on a single degraded image. The method performs in a per-pixel fashion, which is straightforward to implement. The experimental results demonstrate that the method yields results comparative to and even better than the more complex state-of-the-art techniques, having the advantage of being appropriate for real-time applications.

Single Image Dehazing by Multi-Scale Fusion

The contrast of outdoor images acquired under adverse weather conditions, especially foggy weather, is altered by the scattering of daylight by atmospheric particles. As a consequence, different methods have been designed to restore the contrast of these images. However, there is a lack of methodology to assess the performances of the methods or to rate them. Unlike image quality assessment or image restoration areas, there is no easy way to have a reference image, which makes the problem not straightforward to solve. In this paper, an approach is proposed which consists in computing the ratio between the gradient of the visible edges between the image before and after contrast restoration. In this way, an indicator of visibility enhancement is provided based on the concept of visibility level, commonly used in lighting engineering. Finally, the methodology is applied to contrast enhancement assessment and to the comparison of tone-mapping operators.

/pdf/blind-contrast-enhancement-assessment-by-gradient-ratioing-33dklhnsr0.pdf

Blind contrast enhancement assessment by gradient ratioing at visible edges

The measurement of atmospheric visibility is an important element for road and air transportation safety. We propose in this paper a novel estimator of the atmospheric visibility by already existing conventional highway cameras, with a technique based on the gradient magnitude selected by applying Lambert's law with respect to changes in lighting conditions. The response of this estimator is calibrated by non-linear regression with data from a visibility meter installed in a test site which has been instrumented with a camera. Through our technique, atmospheric visibility estimates are obtained with an average error of 30% for images taken in the day, with sky luminance between 10 and 8000 cd m−2 and visibility distances up to 15 km. Our results allow us to envision practical implementation on roadsides in the near future to determine local visibility for the benefit of road safety, meteorological observation and air quality monitoring.

/pdf/visibility-monitoring-using-conventional-roadside-cameras-3ulbw6qddo.pdf

Visibility Monitoring using Conventional Roadside Cameras - Emerging Applications

Compared with daytime, a larger proportion of road accidents happens during nighttime. The altered visibility for drivers partially explains this situation. It becomes worse when dense fog is present. In this paper, we first define a standard night visibility index, which allows specifying the type of fog that an advanced driver assistance system should recognize. A methodology to detect the presence of night fog and characterize its density in images grabbed by an in-vehicle camera is then proposed. The detection method relies on the visual effects of night fog. A first approach evaluates the presence of fog around a vehicle due to the detection of the backscattered veil created by the headlamps. In this aim, a correlation index is computed between the current image and a reference image where the fog density is known. It works when the vehicle is alone on a highway without external light sources. A second approach evaluates the presence of fog due to the detection of halos around light sources ahead of the vehicle. It works with oncoming traffic and public lighting. Both approaches are illustrated with actual images of fog. Their complementarity makes it possible to envision a complete night-fog detection system. If fog is detected, its characterization is achieved by fitting the different correlation indexes with an empirical model. Experimental results show the efficiency of the proposed method. The main applications for such a system are, for instance, automation or adaptation of vehicle lights, contextual speed computation, and reliability improvement for camera-based systems.

/pdf/nighttime-visibility-analysis-and-estimation-method-in-the-3hnr1llasb.pdf

Nighttime Visibility Analysis and Estimation Method in the Presence of Dense Fog

http://perso.lcpc.fr/hautiere.nicolas/pdf/2011/hautiere-ae11.pdf

A Model-Driven Approach to Estimate Atmospheric Visibility with Ordinary Cameras

The visibility level (VL), a quality index in road lighting design, also serves to assess automotive lighting performance. Unlike illuminance levels, the VL provides a link between lighting design and driving performance. The reference performance of the VL is the detection of a small uniform target, standing on a uniform background (the road surface). Still, VL is subject to a number of caveats with regards to the driving task. We address the non-realistic nature of the reference target (a uniform square). A driving simulation experiment was conducted in a virtual night-time rural highway environment. The subjects drove along the road and came across different targets on the roadside. The detection distances were recorded and compared with the corresponding VL, showing rather good agreement.

/pdf/target-visibility-level-and-detection-distance-on-a-driving-13g1ypzyon.pdf

Eric Dumont

Papers

Blind contrast enhancement assessment by gradient ratioing at visible edges

Visibility Monitoring using Conventional Roadside Cameras - Emerging Applications

Nighttime Visibility Analysis and Estimation Method in the Presence of Dense Fog

A Model-Driven Approach to Estimate Atmospheric Visibility with Ordinary Cameras

Target visibility level and detection distance on a driving simulator