Bad weather, such as fog and haze, can significantly degrade the visibility of a scene. Optically, this is due to the substantial presence of particles in the atmosphere that absorb and scatter light. In computer vision, the absorption and scattering processes are commonly modeled by a linear combination of the direct attenuation and the airlight. Based on this model, a few methods have been proposed, and most of them require multiple input images of a scene, which have either different degrees of polarization or different atmospheric conditions. This requirement is the main drawback of these methods, since in many situations, it is difficult to be fulfilled. To resolve the problem, we introduce an automated method that only requires a single input image. This method is based on two basic observations: first, images with enhanced visibility (or clear-day images) have more contrast than images plagued by bad weather; second, airlight whose variation mainly depends on the distance of objects to the viewer, tends to be smooth. Relying on these two observations, we develop a cost function in the framework of Markov random fields, which can be efficiently optimized by various techniques, such as graph-cuts or belief propagation. The method does not require the geometrical information of the input image, and is applicable for both color and gray images.

/pdf/visibility-in-bad-weather-from-a-single-image-wselp65qwy.pdf

Visibility in bad weather from a single image

A fully revised and expanded new edition of the authoritative text on the European Commission This major text based on extensive original research introduces and assesses the key factors involved in the Commission's evolution, organization, character, functioning and role

The European Commission

The performance of existing image dehazing methods is limited by hand-designed features, such as the dark channel, color disparity and maximum contrast, with complex fusion schemes. In this paper, we propose a multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps. The proposed algorithm consists of a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale net which refines results locally. To train the multi-scale deep network, we synthesize a dataset comprised of hazy images and corresponding transmission maps based on the NYU Depth dataset. Extensive experiments demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods on both synthetic and real-world images in terms of quality and speed.

/pdf/single-image-dehazing-via-multi-scale-convolutional-neural-3bsvlws9do.pdf

Single Image Dehazing via Multi-scale Convolutional Neural Networks

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

Advanced driver assistance systems (ADASs), and particularly pedestrian protection systems (PPSs), have become an active research area aimed at improving traffic safety. The major challenge of PPSs is the development of reliable on-board pedestrian detection systems. Due to the varying appearance of pedestrians (e.g., different clothes, changing size, aspect ratio, and dynamic shape) and the unstructured environment, it is very difficult to cope with the demanded robustness of this kind of system. Two problems arising in this research area are the lack of public benchmarks and the difficulty in reproducing many of the proposed methods, which makes it difficult to compare the approaches. As a result, surveying the literature by enumerating the proposals one--after-another is not the most useful way to provide a comparative point of view. Accordingly, we present a more convenient strategy to survey the different approaches. We divide the problem of detecting pedestrians from images into different processing steps, each with attached responsibilities. Then, the different proposed methods are analyzed and classified with respect to each processing stage, favoring a comparative viewpoint. Finally, discussion of the important topics is presented, putting special emphasis on the future needs and challenges.

http://www.cvc.uab.es/~asappa/publications/J__IEEE_PAMI_vol_32_Issue_7_July_2010.pdf

Survey of Pedestrian Detection for Advanced Driver Assistance Systems

Presents a road obstacle detection method able to cope with uphill and downhill gradients and dynamic pitching of the vehicle. Our approach is based on the construction and investigation of the "v-disparity" image which provides a good representation of the geometric content of the road scene. The advantage of this image is that it provides semi-global matching and is able to perform robust obstacle detection even in the case of partial occlusion or errors committed during the matching process. Furthermore, this detection is performed without any explicit extraction of coherent structures. This paper explains the construction of the "v-disparity" image, its main properties, and the obstacle detection method. The longitudinal profile of the road is estimated and the objects located above the road surface are then extracted as potential obstacles; subsequently, the accurate detection of road obstacles, in particular the position of tyre-road contact points is computed in a precise manner. The whole process is performed at frame rate with a current-day PC. Our experimental findings and comparisons with the results obtained using a flat geometry hypothesis show the benefits of our approach.

/pdf/real-time-obstacle-detection-in-stereovision-on-non-flat-b82kjjsnt1.pdf

Real time obstacle detection in stereovision on non flat road geometry through "v-disparity" representation

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

In this paper, we will present a technique for measuring visibility distances under foggy weather conditions using a camera mounted onboard a moving vehicle. Our research has focused in particular on the problem of detecting daytime fog and estimating visibility distances; thanks to these efforts, an original method has been developed, tested and patented. The approach consists of dynamically implementing Koschmieder's law. Our method enables computing the meteorological visibility distance, a measure defined by the International Commission on Illumination (CIE) as the distance beyond which a black object of an appropriate dimension is perceived with a contrast of less than 5%. Our proposed solution is an original one, featuring the advantage of utilizing a single camera and necessitating the presence of just the road and sky in the scene. As opposed to other methods that require the explicit extraction of the road, this method offers fewer constraints by virtue of being applicable with no more than the extraction of a homogeneous surface containing a portion of the road and sky within the image. This image preprocessing also serves to identify the level of compatibility of the processed image with the set of Koschmieder's model hypotheses.

Automatic fog detection and estimation of visibility distance through use of an onboard camera

In foggy weather, the contrast of images grabbed by in-vehicle cameras in the visible light range is drastically degraded, which makes the current applications very sensitive to weather conditions. An onboard vision system should take fog effects into account. The effects of fog varies across the scene and are exponential with respect to the depth of scene points. Because it is not possible in this context to compute the road scene structure beforehand contrary to fixed camera surveillance, a new scheme is proposed. Weather conditions are first estimated and then used to restore the contrast according to a scene structure which is inferred a priori and refined during the restoration process. Based on the aimed application, different algorithms with increasing complexities are proposed. Results are presented using sample road scenes under foggy weather and assessed by computing the contrast before and after restoration.

/pdf/towards-fog-free-in-vehicle-vision-systems-through-contrast-2gmkt8hbcz.pdf

Towards Fog-Free In-Vehicle Vision Systems through Contrast Restoration

We propose a new cooperative fusion approach between stereovision and laser scanner in order to take advantage of the best features and cope with the drawbacks of these two sensors to perform robust, accurate and real time-detection of multi-obstacles in the automotive context The proposed system is able to estimate the position and the height, width and depth of generic obstacles at video frame rate (25 frames per second) The vehicle pitch, estimated by stereovision, is used to filter laser scanner raw data Objects out of the road are removed using road lane information computed by stereovision Various fusion schemes are proposed and one is experimented Results of experiments in real driving situations (multi-pedestrians and multi-vehicles detection) are presented and stress the benefits of our approach

Didier Aubert

Papers

Real time obstacle detection in stereovision on non flat road geometry through "v-disparity" representation

Blind contrast enhancement assessment by gradient ratioing at visible edges

Automatic fog detection and estimation of visibility distance through use of an onboard camera

Towards Fog-Free In-Vehicle Vision Systems through Contrast Restoration

Cooperative Fusion for Multi-Obstacles Detection With Use of Stereovision and Laser Scanner