Jean-Philippe Tarel

• Phd
• Researcher at Gustave Eiffel University

Transports of people and goods contribute to the ongoing 6th mass extinction of species. They impact species viability by reducing the availability of suitable habitat, by limiting connectivity between suitable patches, and by increasing direct mortality due to collisions with vehicles. Not only does it represent a threat for some species conservat...

Intersections have been known as hazardous points of the road networks for over a century. A diversity of solutions have been developed to reduce the number of accidents at intersections, such as traffic lights, pedestrian crossings, as well as roundabouts. In the past decade, many cities have had to deal with a growing number of alternate means of...

Transports of people and goods contribute to the ongoing 6th mass extinction of species. They impact species viability by reducing the availability of suitable habitat, by limiting connectivity between suitable patches, and by increasing direct mortality due to collisions with vehicles. Not only does it represent a threat for some species conservat...

Poster about the conference paper : A New Real-World Video Dataset for the Comparison of Defogging Algorithms

Video restoration for noise removal, deblurring or super-resolution is attracting more and more attention in the fields of image processing and computer vision. Works on video restoration with data-driven approaches for fog removal are rare however, due to the lack of datasets containing videos in both clear and foggy conditions which are required...

Le projet OCAPI, porté par TerrOïko en partenariat avec l'Université Gustave Eiffel et le CNRS, vise à développer des solutions de suivis de la biodiversité basées sur des capteurs visuels (caméras et appareils photographiques) aujourd'hui communément déployés sur les infrastructures de transport existantes. À partir du couplage de méthodes de comp...

This technical reports presents the results of the OCAPI project granted by the FEREC fundation. Thus, it presents: 1) How the OCAPI plateform dedicated to deep learning algorithm development has been developed. 2) How the project trained YOLOv5 to recognise the main European Mammals 3) How the project used data coming from automated recognition o...

From an analysis of the priors used in previous algorithms for single image defogging, a new prior is proposed to obtain a better atmospheric veil removal. The Naka-Rushton function is used to modulate the atmospheric veil according to empirical observations on synthetic foggy images. The parameters of this function are set from features of the inp...

From an analysis of the priors used in state-of-the-art algorithms for single image defogging, a new prior is proposed to obtain a better atmospheric veil removal. Our hypothesis is based on a physical model, considering that the fog appears denser near the horizon rather than close to the camera. It leads to more restoration when the fog depth is...

Dear colleagues, Atmosphere is an international peer-reviewed open access monthly journal published by MDPI. Artificial vision systems, whether active or passive, are increasingly used for applications ranging from intelligent visual surveillance to automated driving. These systems are largely disrupted by adverse weather conditions such as fog, ra...

Atmosphere is an international peer-reviewed open access monthly journal published by MDPI. Artificial vision systems, whether active or passive, are increasingly used for applications ranging from intelligent visual surveillance to automated driving. These systems are largely disrupted by adverse weather conditions such as fog, rain, or snow. Sev...

The AWARE (All Weather All Roads Enhanced vision) French public funded project is aiming at the development of a low cost sensor fitting to automotive and aviation requirements, and enabling a vision in all poor visibility conditions, such as night, fog, rain and snow. In order to identify the technologies providing the best all-weather vision, we...

The AWARE (All Weather All Roads Enhanced vision) French public funded project is aiming at the development of a low cost sensor fitting to automotive and aviation requirements, and enabling a vision in all poor visibility conditions, such as night, fog, rain and snow. In order to identify the technologies providing the best all-weather vision, we...

Les contours actifs sont des courbes déformables que l'on vient positionner dans les images pour y capturer des structures d'intérêt : on parle de segmentation d'images. La plupart du temps, cet ajustement est formulé comme l'optimisation d'une fonctionnelle d'énergie, caractérisée par la présence de nombreux minima locaux, correspondant à des solu...

Une approche pour faire du traitement d'image consiste à poser les problèmes comme la minimisation d'une énergie sur l'espace des images qui sont représentées par des fonctions 2D. L'optimisation de ce type d'énergie passe par le développement de schémas numériques et donc par la nécessaire discrétisation de l'espace des fonctions choisies et de l'...

Recounts the career and contributions of Dr. Didier Aubert.

The AWARE (All Weather All Roads Enhanced vision) French public funded project is aiming at the development of a low cost sensor fitting to automotive and aviation requirements, and enabling a vision in all poor visibility conditions, such as night, fog, rain and snow. In order to identify the technologies providing the best all-weather vision, we...

Ground-penetrating radar (GPR) is a mature geophysical technique that is used to map utility pipelines buried within 1.5 m of the ground surface in the urban landscape. In this work, the template-matching algorithm has been originally applied to the detection and localization of pipe signatures in two perpendicular antenna polarizations. The proces...

ISPACS'15 - IEEE International Symposium on Intelligent Signal Processing and Communication Systems, BALI, INDONESIE, 09-/11/2015 - 12/11/2015

IEEE International Conference on Image Processing, QUEBEC, CANADA, 27-/09/2015 - 30/09/2015

This paper investigates visibility in daytime fog as estimated optically with a visibility sensor and computationally with an image sensor. We use a database collected on a weather observation site equipped with both a forward scatter visibility meter and a CCTV camera. We implement a computer vision method based on the contrast sensitivity functio...

CIE 2015 - International Conference of the 28th session, MANCHESTER, ROYAUME-UNI, 28-/06/2015 - 04/07/2015

47èmes Journées de Statistique de la SFdS, LILLE, FRANCE, 01-/06/2015 - 05/06/2015

European Geosciences Union General Assembly, VIENNE, AUTRICHE, 12-/04/2015 - 17/04/2015

The bilateral filter and its variants such as the Joint/Cross bilateral filter are well known edge-preserving image smoothing tools used in many applications. The reason of this success is its simple definition and the possibility of many adaptations. The bilateral filter is known to be related to robust estimation. This link is lost by the ad hoc...

The fog disturbs the proper image processing of many outdoor observation tools. For instance, fog reduces the obstacle visibility in vehicle driving applications. Usually, the estimation of the amount of fog in the scene image allows to greatly improve the image processing, and thus to better perform the observation task. One possibility is to rest...

A bi-static Ground Penetrating Radar (GPR) has been developed for the detection of cracks and buried pipes in urban grounds. It is made of two shielded Ultra Wide Band (UWB) bowtie-slot antennas operating in the frequency band [0.3;4] GHz. GPR signals contain not only responses of targets, but also unwanted effects from antenna coupling in air and...

In civil engineering, ground penetrating radar (GPR) is used to survey pavement thickness at traffic speed, detect and localize buried objects (pipes, cables, voids, cavities), zones of cracks and discontinuities in concrete or soils. In this work, a ground-coupled radar made of a pair of transmitting and receiving bowtie-slot antennas is moved lin...

This paper reviews a cluster of recent and current researches in the field of visual attention conducted at the LEPSIS Lab (IFSTTAR). Taking advantage of the multidisciplinary structure of the research team, contributions have been proposed in the fields of image processing, artificial intelligence, virtual reality, cognitive psychology and etholog...

L’Ifsttar mène des recherches avec le Réseau Scientifique et Technique du Ministère français des Transports pour favoriser l’émergence de solutions innovantes exploitant les caméras pour évaluer et améliorer la visibilité routière. Cet article passe en revue les méthodes de vision par ordinateur qui ont été développées dans le cadre de ce travail....

Free space detection is a primary task for car nav-igation. Unfortunately, classical approaches have difficulties in adverse weather conditions, in particular in daytime fog. In this paper, a solution is proposed thanks to a contrast restoration approach on images grabbed by an in-vehicle camera. The proposed method improves the state of the art in...

Stereo reconstruction serves many outdoor applications, and thus sometimes faces foggy weather. The quality of the reconstruction by state of the art algorithms is then degraded as contrast is reduced with the distance because of scattering. However, as shown by defogging algorithms from a single image, fog provides an extra depth cue in the gray l...

Fog reduces contrast and thus the visibility of vehicles and obstacles for drivers. Each year, this causes traffic accidents. Fog is caused by a high concentration of very fine water droplets in the air. When light hits these droplets, it is scattered and this results in a dense white background, called the atmospheric veil. As pointed in [1], Adva...

Stereo reconstruction serves many outdoor applications, and thus sometimes faces foggy weather. The quality of the reconstruction by state of the art algorithms is then degraded as contrast is reduced with the distance because of scattering. However, as shown by defogging algorithms from a single image, fog provides an extra depth cue in the gray l...

Sight distance along the pathway plays a significant role in road safety and in particular, has a clear impact on the choice of speed limits. Mapping visibility distance is thus of importance for road engineers and authorities. While visibility distance criteria are routinely taken into account in road design, few systems exist for evaluating them...

Various interest point and corner definitions were proposed in the past with associated detection algorithms. We propose an intuitive and novel detection algorithm for finding the location of such features in an image. The detection is based on the edges in the original image. Interest points are detected as accumulation points where several edge t...

Les applications du traitement d'images au domaine routier sont nombreuses. La diversité des perturbations dues aux conditions météorologiques dégradées complique généralement l'analyse des images routières. Le filtre bilatéral est un filtre maintenant bien connu en imagerie numérique. Il est beaucoup utilisé pour éliminer le bruit et autres pertur...

While road lane markings detection was extensively studied, in particular for intelligent vehicle applications, the detection and recognition of all kind of marking such as arrows, crosswalks, zebras, words, pictograms, continuous and discontinuous lane markings was drastically less studied. However, it has many potential applications in the design...

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...

We investigate the scenario of a vehicle equipped with a camera and a GPS driving on a road whose 3D map is known. We focus on the case of a road under fog or/and snow conditions. The GPS is used to estimate the vehicle pose and yaw and then the 3D road map is projected onto the camera image. The vehicle pitch and roll angles are then refined by fi...

The detection of bad weather conditions is crucial for meteorological centers, specially with demand for air, sea and ground traffic management. In this article, a system based on computer vision is presented which detects the presence of rain or snow. To separate the foreground from the background in image sequences, a classical Gaussian Mixture M...

We consider the problem of fitting linearly parameterized models, that arises in many computer vision problems such as road scene analysis. Data extracted from images usually contain non-Gaussian noise and outliers, which makes non-robust estimation methods ineffective. In this paper, we propose an overview of a Lagrangian formulation of the Half-Q...

A number of image quality metrics are based on psychophysical models of the human visual system. We propose a new framework for image quality assessment, gathering three indexes describing the image quality in terms of visual performance, visual appearance, and visual attention. These indexes are built on three vision models grounded on psychophysi...

Par temps de brouillard, la conduite est problématique à cause de la distance de visibilité qui se trouve fortement réduite. Pour assister le conducteur, nous travaillons sur des méthodes d'estimation de la distance de visibilité météorologique par caméra embarquée. Cela permet d'adapter la vitesse du véhicule, mais également de construire des aide...

Road sign identification in images is an important issue, in particular for vehicle safety applications. It is usually tackled in three stages : detection, recognition and tracking, and evaluated as a whole. To progress towards better algorithms, we focus in this paper on the first stage of the process, namely road sign detection. More specifically...

Most road marking detection systems use image processing to extract potential marking elements in their first stage. Hence, the performances of extraction algorithms clearly impact the result of the whole process. In this paper, we address the problem of extracting road markings in high resolution environment images taken by inspection vehicles in...

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...

In adverse weather conditions, in particular, in daylight fog, the contrast of images grabbed by in-vehicle cameras in the visible light range is drastically degraded, which makes current driver assistance that relies on cameras very sensitive to weather conditions. An onboard vision system should take weather effects into account. The effects of d...

Road signs, the main communication media towards the drivers, play a significant role in road safety and traffic control through drivers" guidance, warning, and information. However, not all traffic signs are seen by all drivers, which sometimes lead to dangerous situations. In order to manage safer roads, the estimation of the legibility of the ro...

présentons une méthode géométrique utilisant l'orientation du gradient pour la détection de la signalisation verticale dans des images fixes, indépendamment de leur position et de leur orientation. La détection est réalisée par une transformation de type accumulateur de Hough bivariée, fondée sur l'utilisation de paires de points avec des contraint...

Sight distance along the highway plays a significant role in road safety and in particular, has a clear impact on the choice of speed limits. Visibility distance is thus of importance for road engineers and authorities. While visibility distance criteria are routinely taken into account in road design, few systems exist for estimating it on existin...

La distance de visibilité de la route joue un rôle important pour la sécurité routière et en particulier, a un impact évident sur le choix des limites de vitesse. Alors que les critères de visibilité sont systématiquement pris en compte lors de la conception des routes, seuls quelques systèmes existent actuellement pour estimer la distance de visib...

Nous présentons une nouvelle transformation pour la détection du sommet et de la bissectrice d'angles des contours dans une image. Cette Transformation en Sommet et Bissectrice (TSB) a pour entrée les gradients d'une image et pour sortie deux tableaux accumulant les votes, respectivement, pour des sommets et des segments bissecteurs d'un angle. Cet...

We present a new transformation for angle vertex and bisector detection. The vertex and bisector transformation (VBT) takes the image gradient as input and outputs two arrays, accumulating evidence of respectively angle vertex and angle bisector. A geometric model of the gradient orientation is implemented using a pair-wise voting scheme: normal ve...

La prédiction de la dégradation temporelle des marquages routiers est un enjeu important de l'optimisation de la gestion des routes. Nous proposons une première étude visant à connaître les paramètres explicatifs de la dégradation des marquages routiers et à tester certains modèles. Une approche alternative consiste à observer très régulièrement le...

Visibility distance on the road pathway plays a significant role in road safety and in particular, has a clear impact on the choice of speed limits. Visibility distance is thus of importance for road engineers and authorities. While visibility distance criteria are routinely taken into account in road design, only a few systems exist for estimating...

Driving involves visual exploration of the road environment and one important driving subtask is to look for road signs. We propose a new computational model of visual search saliency in natural scenes, as current ones are limited to laboratory situations. Relying on statistical learning algorithms, our algorithm captures the priors a driver learns...

We present a real-time approach for circular and polygonal road signs detection in still images, regardless of their pose and orientation. Object detection is done using a pairwise gradient-based symmetry transform able to detect circles and polygons indistinctly. This symmetry transform of gradient orientation, the so-called Bilateral Chinese Tran...

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 comple...

La dégradation des conditions météorologiques peut altérer la sécurité des conducteurs. Un système de vidéo-surveillance est proposé afin de détecter la présence d'hydrométéores et de réagir en conséquence. Une approche probabiliste est introduite pour réaliser un histogramme d'orientation des segments en mouvement présents dans l'image. La méthode...

A number of computational models of visual attention have been proposed based on the concept of saliency map. Some of them have been validated as predictors of the visual scan-path of observers looking at images and videos, using oculometric data. They are widely used for Computer Graphics applications, mainly for image rendering, in order to avoid...

This paper proposes an improvement of advanced driver assistance system based on saliency estimation of road signs. After a road sign detection stage, its saliency is estimated using a SVM learning. A model of visual saliency linking the size of an object and a size-independent saliency is proposed. An eye tracking experiment in context close to dr...

Les difficultés techniques pour le suivi et la reconnaissance de lignes de marquages routiers sont engendrées par les conditions d'acquisition des images embarquées, subissant les ombres projetées, les éblouissements, les occlusions par des obstacles, etc. En général, la première phase de traitement d'image est la phase d'extraction. Une comparaiso...

Long-range detection of road surface in a sequence of images from a front camera aboard a vehicle is known as an unsolved problem. We propose an algorithm using a single camera and based on color segmentation which has interesting performance and which is stable along the sequence whatever its length. It is an off-line algorithm which makes good us...

Central to many problems in scene understanding based on using a network of tens, hundreds or even thousands of randomly distributed cameras with on-board processing and wireless communication capability is the ldquoefficientrdquo reconstruction of the 3D geometry structure in the scene. What is meant by ldquoefficientrdquo reconstruction? In this...

Free space detection is a primary task in au-tonomous navigation. Unfortunately, classical ap-proaches have diculties in adverse weather condi-tions, in particular in daytime fog. In this paper, a solution is proposed thanks to a contrast restoration ap-proach. Knowing the density of fog, the method restores the contrast of the road and, at the sam...

In this paper, we address the problem of robustly recovering several instances of a curve model from a single noisy data set with outliers. Using M-estimators revisited in a Lagrangian formalism, we derive an algorithm that we call Simultaneous Multiple Robust Fitting (SMRF), which extends the classical Iterative Reweighted Least Squares algorithm...

Schématiquement, résoudre un problème inverse revient à essayer de restituer la réalité à partir d'une image partielle et/ou brouillée. Les problèmes inverses constituent un domaine foisonnant; les applications sont multiples, les problématiques diverses et les méthodes utilisées forcément variées. Cet ouvrage collectif réalise un état de l'art sur...

Given the difficulty of setting up large-scale experiments with real users, the comparison of content-based image retrieval methods using relevance feedback usually relies on the emulation of the user, following a single, well-prescribed strategy. Since the behavior of real users cannot be expected to comply to strict specifications, it is very imp...

This paper proposes a systematic approach to evaluate algorithms for extracting road marking features from images. This specific topic is seldom addressed in the literature while many road marking detection algorithms have been proposed. Most of them can be decomposed into three steps: extracting road marking features, estimating a geometrical mark...

A ce jour, l'évaluation de la qualité des algorithmes de reproduction de tons (tone mapping operators, ou TMO) n'a été faite que pour des situations statiques, alors que l'essentiel des applications des images de synthèse (vidéo, télévision, cinéma, jeux vidéos) proposent des images dynamiques. Nous pensons que le problème de l'évaluation dynamique...

3D reconstruction techniques through use of stereovision have experienced considerable development over the past two decades. Their field of application extends from non-destructive control to augmented reality and includes remote sensing. Following a review of the basic principles behind these methods, this paper will present a summary of the most...

Les techniques de reconstruction 3D par stéréovision ont connu un développement considérable au cours des deux dernières décennies. Leur champ d'application s'étend du contrôle non destructif à la réalité augmentée, en passant par la télédétection. Après un rappel des principes de base de ces méthodes, on propose ici une présentation synthétique de...

In content-based image retrieval, relevance feedback (RF) is a prominent method for reducing the “semantic gap” between the low-level features describing the content and the usually higher-level meaning of user's target. Recent RF methods are able to identify complex target classes after relatively few feedback iterations. However, because the comp...

The contrast of outdoor images grabbed 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...

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...

The perception of the environment is a fundamental task for autonomous robots. Unfortunately, the performances of the vision systems are drastically altered in presence of bad weather, especially fog. Indeed, due to the scattering of light by atmospheric particles, the quality of the light signal is reduced, compared to what it is in clean air. Det...

We consider the problem of multiple fitting of linearly parametrized curves, that arises in many computer vision problems such as road scene analysis. Data extracted from images usually contain non-Gaussian noise and outliers, which makes classical estimation methods ineffective. In this paper, we first introduce a family of robust probability dens...

In this paper, the duality in differential form is developed between a 3D primal surface and its dual manifold formed by the surface's tangent planes, that is, each tangent plane of the primal surface is represented as a four-dimensional vector that constitutes a point on the dual manifold. The iterated dual theorem shows that each tangent plane of...

Traffic signs are designed to be clearly seen by drivers. Howe ver a little is known about the visual influence of the traffic sign environment on how it will be perceived. Comp uter estimation of the conspicuity from images using a camera mounted on a vehicle is thus of importance in order to be able to quickly make a diagnosis regarding conspicui...

Automatic road markings detection is a central point in road scene analysis from images. Its applications concern as well the inventory of lane marking types on a road network, as the design of driver assistance systems on-board vehicles. We here describe a model and an estimation algorithm which account for the geometric specificity and variabilit...

We present a new application of computer vision: continuous measurement of the geometrical visibility range on inter-urban roads, solely based on a monocular image acquisition system. To tackle this problem, we propose first a road segmentation scheme based on a Parzen-windowing of a color feature space with an original update that allows us to cop...

In content-based retrieval, relevance feedback (RF) is a noticeable method for reducing the "semantic gap" between the low-level features describing the content and the usually higher-level meaning of user's target. While recent RF methods based on active learning are able to identify complex target classes after relatively few iterations, they can...