Aurélien Cord

Vision Enhancement in Homogeneous and Heterogeneous Fog

One source of accidents when driving a vehicle is the presence of fog. Fog fades the colors and reduces the contrasts in the scene with respect to their distances from the driver. Various camera-based Advanced Driver Assistance Systems (ADAS) can be improved if efficient algorithms are designed for visibility enhancement in road images. The visibility enhancement algorithm proposed in [1] is not optimized for road images. In this paper, we reformulate the problem as the inference of the local atmospheric veil from constraints. The algorithm in [1] thus becomes a particular case. From this new derivation, we propose to better handle road images by introducing an extra constraint taking into account that a large part of the image can be assumed to be a planar road. The advantages of the proposed local algorithm are the speed, the possibility to handle both color and gray-level images, and the small number of parameters. A new scheme is proposed for rating visibility enhancement algorithms based on the addition of several types of generated fog on synthetic and camera images. A comparative study and quantitative evaluation with other state-of-the-art algorithms is thus proposed. This evaluation demonstrates that the new algorithm produces better results with homogeneous fog and that it is able to deal better with the presence of heterogeneous fog. Finally, we also propose a model allowing to evaluate the potential safety benefit of an ADAS based on the display of defogged images.

Improved visibility of road scene images under heterogeneous fog

One source of accidents when driving a vehicle is the presence of homogeneous and heterogeneous fog. Fog fades the colors and reduces the contrast of the observed objects with respect to their distances. Various camera-based Advanced Driver Assistance Systems (ADAS) can be improved if efficient algorithms are designed for visibility enhancement of road images. The visibility enhancement algorithm proposed in [1] is not dedicated to road images and thus it leads to limited quality results on images of this kind. In this paper, we interpret the algorithm in [1] as the inference of the local atmospheric veil subject to two constraints. From this interpretation, we propose an extended algorithm which better handles road images by taking into account that a large part of the image can be assumed to be a planar road. The advantages of the proposed local algorithm are its speed, the possibility to handle both color images or gray-level images, and its small number of parameters. A comparative study and quantitative evaluation with other state-of-the-art algorithms is proposed on synthetic images with several types of generated fog. This evaluation demonstrates that the new algorithm produces similar quality results with homogeneous fog and that it is able to better deal with the presence of heterogeneous fog.

Automatic Road Defect Detection by Textural Pattern Recognition Based on AdaBoost

Road surface conditions are continuously degrading due to meteorological conditions, ground movements and traffic that leads to the formation of defects, such as grabbing, holes, and cracks. This article presents a method to automatically distinguish images of road surfaces with defects from road surfaces without defects. This method, based on supervised learning, is generic and may be applied to all type of defects present in the images. They typically present strong textural information with patterns that show fluctuations at small scales and some uniformity at larger scales. The textural information is described by applying a large set of linear and nonlinear filters. To select the most pertinent ones for the current application, a supervised learning based on AdaBoost is performed. The whole process is tested both on a textural recognition task based on the VisTex image database and on road images collected by a dedicated road imaging system. A comparison with a recent crack detection algorithm from Oliveira and Correia demonstrates the proposed methods efficiency.

Lane marking extraction with combination strategy and comparative evaluation on synthetic and camera images

Lane detections and tracking are crucial stages for a great number of Advanced Driving Assistance Systems (ADAS), for instance for road lane following or robust ego localization. In these applications, the most important module is probably the lane marking primitives extraction algorithm. For several decades, a lot of approaches have been proposed in order to achieve this task. Unfortunately, it is yet difficult to guarantee robust results from these extraction algorithms in case of bad weather conditions, degraded lane markings, or due to intrinsic limitations of cameras. In this paper we propose an approach in order to improve the quality of the lane marking extraction. By extraction, we mean the classification of the image pixels into two classes: marking and non-marking. The extraction is generally the first step of a marking detection system, so its efficiency has a strong impact on the performances of the whole system. The proposed algorithm is based on the combination of two different extraction algorithms. In order to validate the quality of this work, some tests and evaluations are provided and allow proving the efficiency of such an approach. The evaluation is performed on camera images and then on synthetic images. The results with camera and synthetic images are compared and discussed.

Contrast restoration of road images taken in foggy weather

Driver assistance systems based on camera are strongly disturbed by the presence of foggy weather. The restoration of images, as pre-processing, would improve the performances of such systems. In this paper, we propose a method to restore the image contrast of foggy road scenes combining a physical approach, based on Koschmieders model and a signals approach, based on local histogram equalization. Then we optimize the parameters of our method using a simulated annealing. This method, evaluated on a reference image database, presents a significant improvement compared to other methods and gives consistent results for both homogeneous and inhomogeneous fog.

Supporting Drivers in Keeping Safe Speed in Adverse Weather Conditions by Mitigating the Risk Level

Overspeeding is both a cause and an aggravation factor of traffic accidents. Consequently, much effort is devoted to limiting overspeeding and, consequently, to increasing the safety of road networks. In this paper, a novel approach to computing a safe speed profile to be used in an adaptive intelligent speed adaptation (ISA) system is proposed. The method presents two main novelties. First, the 85th percentile of observed speeds (V85), estimated along a road section, is used as a reference speed, which is practiced and practicable in ideal conditions. Second, this reference speed is modulated in adverse weather conditions to account for reduced friction and reduced visibility distance. The risk is thus mitigated by modulating the potential severity of crashes by means of a generic scenario of accidents. Within this scenario, the difference in speed that should be applied in adverse conditions is estimated so that the highway risk is the same as in ideal conditions. The system has been tested on actual data collected on a French secondary road and implemented on a test track and a fleet of vehicles. The performed tests and the experiments of acceptability show a great interest for the deployment of such a system.

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

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.

Vehicle detection and tracking by collaborative fusion between laser scanner and camera

This paper presents a new approach to fuse 3D and 2D information in a driver assistance setup, in particular to perform obstacle detection and tracking. We propose a new cooperative fusion method between two exteroceptive sensors: it is able to address highly non linear dynamic configuration without any assumption on the driving maneuver. Information are provided by a mono-layer laser scanner and a monocular camera which are unsynchronized. The initial detection stage is performed using the 1D laser data, which computes clusters of points which might correspond to vehicles present on the road. These clusters are projected to the image to define targets, which will be tracked using image registration techniques. This multi-object association and tracking scheme is implemented using belief theory integrating temporal and spatial information, which allows the estimation of the dynamic state of the tracks and to monitor appearance and disappearance of obstacles. Accuracy of the method is evaluated on a database made publicly available, focus is cast on the relative localization of the vehicle ahead: estimations of its longitudinal and lateral distances are analysed.

Detecting Unfocused Raindrops: In-Vehicle Multipurpose Cameras

Advanced driver assistance systems (ADASs) based on video cameras are becoming pervasive in todays automotive industry. However, while most of these systems perform nicely in clear weather conditions, their performances fail drastically in adverse weather and particularly in the rain. We present two novel approaches that aim to detect unfocused raindrops on a car windshield using only images from an in-vehicle camera. Based on the photometric properties of raindrops, the algorithms rely on image processing techniques to highlight them. The results will be used to improve ADAS behavior under rainy conditions. Both approaches are compared with each other and the techniques from the literature.

Target-to-track collaborative association combining a laser scanner and a camera

Advance Driver Assistance Systems designed to enhance safety require a perception module that should be reliable, robust and affordable. We propose a new cooperative fusion method between two exteroceptive sensors for the detection and tracking of obstacles. Focus is cast on the issue of data association of asynchronous measurements from multiple sensors of different nature. This perception and detection module is applied to local perception embedded on a host vehicle (the ego-vehicle) with two types of complementary sensors (laser scanner and mono-camera). The first detection stage is performed by the mono-layer laser scanner which provides a set of clustered impact points. Those clusters are filtered and projected into the image to define targets. Detected vehicles are tracked using an image registration algorithm. A multi-objects association and tracking algorithm based on belief theory is implemented to estimate the dynamic state of the tracks and to monitor appearance and disappearance of obstacles. Our approach does not make any assumption on the type of driving maneuver and is able to address highly non linear dynamic configuration. The method is applied on both real data and in simulated environment for the validation stage.