Abstract

Co-encadrement de la thèse : Bogdan Stanciulescu; Pedestrian Detection and Traffic Sign Recognition (TSR) are important components of an Advanced Driver Assistance System (ADAS). This thesis presents two methods for eliminating false alarms in pedestrian detection applications and a novel three stage approach for TSR. Our TSR approch consists of a color segmentation, a shape detection and a content classification phase. The red color enhancement is improved by using an adaptive threshold. The performance of the K-d tree is augmented by introducing a spatial weighting. The Random Forests yield a classification accuracy of 97% on the German Traffic Sign Recognition Benchmark. Moreover, the processing and memory requirements are reduced by employing a feature space reduction. The classifiers attain an equally high classification rate using only a fraction of the feature dimension, selected using the Random Forest or Fisher's Criterion. This technique is also validated on two different multiclass benchmarks: ETH80 and Caltech 101. Further, in a static camera video surveillance application, the immobile false positives, such as trees and poles, are eliminated using the correlation measure over several frames. The recurring false alarms in the pedestrian detection in the scope of an embedded ADAS application are removed using a complementary tree filter.; La détection de piétons et la reconnaissance des panneaux routiers sont des fonctions importantes des systèmes d'aide à la conduite (anglais : Advanced Driver Assistance System - ADAS). Une nouvelle approche pour la reconnaissance des panneaux et deux méthodes d'élimination de fausses alarmes dans des applications de détection de piétons sont présentées dans cette thèse. Notre approche de reconnaissance de panneaux consiste en trois phases: une segmentation de couleurs, une détection de formes et une classification du contenu. Le color enhancement des régions rouges est amélioré en introduisant un seuil adaptatif. Dans la phase de classification, la performance du K-d tree est augmentée en utilisant un poids spatial. Les Random Forests obtiennent un taux de classification de 97% sur le benchmark allemand de la reconnaissance des panneaux routiers (German Traffic Sign Recognition Benchmark). Les besoins en mémoire et calcul sont réduits en employant une réduction de la dimension des caractéristiques. Les classifieurs atteignent un taux de classification aussi haut qu'avec une fraction de la dimension des caractéristiques, selectionée en utilisant des Random Forests ou Fisher's Crtierion. Cette technique est validée sur deux benchmarks d'images multiclasses : ETH80 et Caltech 101. Dans une application de vidéo surveillance avec des caméras statiques, les fausses alarmes des objets fixes, comme les arbres et les lampadaires, sont éliminées avec la corrélation sur plusieurs trames. Les fausses alarmes récurrentes sont supprimées par un filtre complémentaire en forme d'arbre.

Abstract

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.

Abstract

dvanced Driver Assistance Systems (ADAS) based on video camera tends to be generalized in today's automotive. However, if most of these systems perform nicely in good weather conditions, they perform very poorly under adverse weather particularly under rain. We present a novel approach that aims at detecting raindrops on a car windshield using only images from an in-vehicle camera. Based on the photometric properties of raindrops, the algorithm relies on image processing technics to highlight raindrops. Its results can be further used for image restoration and vision enhancement and hence it is a valuable tool for ADAS.

Abstract

ITSC 2011 : International IEEE Conference on Intelligent Transportation Systems, WASHINGTON, ETATS-UNIS, 05-/10/2011 - 07/10/2011; This paper presents the implementation of a highly automated driving system on automotive Electronic Control Units (ECUs). It integrates a perception component, which uses the combination of high-level sensors to map the environment, a co-pilot, which finds an optimal trajectory in this environment and a control component, which guides the vehicle on this trajectory. The cooperation between human and automation is managed by the driving Mode Selection and arbitration Unit (MSU) and Human-Machine Interface (HMI) components. The co-pilot and control components have been implemented on AUTOSAR-based ECUs, the other components in the RTMaps environment on a standard PC. It has been first been tested on the simulation tool SiVIC and was then transferred to a physical vehicle on test track.

Abstract

Over the past decade, a lot of researches have been done on the development of advanced driver assistance systems (ADAS). Most of these ADAS are now active and need to be tested and evaluated before large deployment. In these ADAS, the prototyping and the implementation of the control stages are risky stages and not so easy to carry out. Indeed, the prototyping and the test of such reactive algorithms need heavy hardware and software supports (dedicated vehicle, actuators, hardware architecture, software architecture, sensors). To achieve such active devices, additional developments and implementation of numerous expensive embedded devices are required. Therefore, in order to reduce both time and risk, in early design stage, it becomes necessary to have a very realistic simulation environment dedicated to the development and to the evaluation of these ADAS. For such virtual platform, it is mandatory to provide physics-driven road environments, virtual embedded sensors, and physics-based vehicle models. In this publication, we present a dedicated couple of platforms with their efficient interconnection for the prototyping of such ADAS. Initially, the SiVIC simulation platform has been developed to generate the virtual world (environments, sensors, actuators, vehicles). In order to improve the real time prototyping capabilities of SiVIC, an efficient interconnection of this first platform has been done with RTMaps platform. This second one is mainly dedicated to the multi-sensors data processing (data management, fusion, flow recording and replaying). In this paper we will show the interest of such bi-directionnal interconnected platforms to prototype complex and real time embedded ADAS. This interconnection can be done as well on an only one computeur than on a distributed and distant computers architecture. The relevance of this approach will be illustrated with an automatic parking application.

Abstract

International audience; This paper presents a new radar sensor modeling for Advanced Driver Assistance Systems (ADAS) prototyping. This virtual model is embedded in the SiVIC platform dedicated to the simulation of vehicles, infrastructure and sensors. Lots of simulators already exist addressing radar simulation, but none of them is designed to address in the same time the following objectives: real-time computation, highly sampled signal generation, multiple radar technologies, and, hardware and software platform integration for ADAS prototyping. In this paper, we proposed such a solution solving this issue and a focus will be done on the radar sensor modeling, from material modeling to implemented technology and associated signal processing. First results of this radar sensor modeling is carried out in motorway scenario.

Abstract

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 of advanced driver assistance systems, as well as for asset management along itineraries. An algorithm is proposed which is based on the following processing steps: marking pixel extraction, detection using connected components before Inverse Perspective Mapping and recognition based on the comparison with a single pattern or with repetitive rectangular patterns. The proposed algorithm is able to detect and recognize repetitive markings (such as crosswalks) as well as single patterns (such as arrows). We believe that the proposed algorithm can be extended easily to solve the problem of the identification of all types of markings.

Abstract

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 driving proves that this computational evaluation of the saliency fits well with human perception, and demonstrates the applicability of the proposed estimator for improved ADAS.