Catálogo de publicaciones - libros

This paper presents a comparative study between two road approximation techniques—planar surfaces—from stereo vision data. The first approach is carried out in the -disparity space and is based on a voting scheme, the Hough transform. The second one consists in computing the best fitting plane for the whole 3D road data points, directly in the Euclidean space, by using least squares fitting. The comparative study is initially performed over a set of different synthetic surfaces (e.g., plane, quadratic surface, cubic surface) digitized by a virtual stereo head; then real data obtained with a commercial stereo head are used. The comparative study is intended to be used as a criterion for fining the best technique according to the road geometry. Additionally, it highlights common problems driven from a wrong assumption about the scene’s prior knowledge.

This paper describes a vision-based system for blind spot detection in intelligent vehicle applications. A camera is mounted in the lateral mirror of a car with the intention of visually detecting cars that can not be perceived by the vehicle driver since they are located in the so-called blind spot. The detection of cars in the blind spot is carried out using computer vision techniques, based on optical flow and data clustering, as described in the following lines.

In this paper, we present a method for computing velocity using a single camera onboard a road vehicle, i.e. an automobile. The use of computer vision provides a reliable method to measure vehicle velocity based on ego-motion computation. By doing so, cumulative errors inherent to odometry-based systems can be reduced to some extent. Road lane markings are the basic features used by the algorithm. They are detected in the image plane and grouped in couples in order to provide geometrically constrained vectors that make viable the computation of vehicle motion in a sequence of images. The applications of this method can be mainly found in the domains of Robotics and Intelligent Vehicles.

During the last two years we have been working on the optimisation of traffic lights cycles. We designed an evolutionary, distributed architecture to do this. This architecture includes a Genetic Algorithm for the optimisation. So far we have performed a single criterion optimisation – the total volume of vehicles that left the network once the simulation finishes. Our aim is to extend our architecture towards a multicriteria optimisation. We are considering Network Occupancy and Greenhouse Emissions as suitable candidates for our purpose. Throughout this work we will share a statistical based study about the two new criteria that will help us to decide whether to include them or not in the fitness function of our system. To do so we have used data from two real world traffic networks.

This research studies the overtaking maneuver in some representative situations. A simulator using Matlab Simulink connecting its outputs to a Virtual Reality module to show the complete overtaking performance from all points of view has been made. With this useful tool the parameters of the car controllers and decision making systems can be set up, and unforeseen new features of the overtaking maneuver can also be taken into account.

In this paper the Vehicle Ad Hoc Network (VANET) is examined. As widely agreed VANETs must rely heavily on node-to-node communication while ease of access has to be assured at the same time. Beside the performance ensuring data authentication is another concern in VANETs.

In our paper we focus on security aspects for the VANETs that aim to ensure data authentication and allow to ensure data secrecy. Ensuring data secrecy is not a standard feature of the VANETs since usually it is assumed that nodes in the network has to be able to receive all information send over the channel. However we think that it is necessary to ensure security against data eavesdrop and message forgery in some applications (e.g. police pursuits or military convoys).

This paper presents an efficient technique for real time estimation of on-board stereo vision system pose. The whole process is performed in the Euclidean space and consists of two stages. Initially, a compact representation of the original 3D data points is computed. Then, a RANSAC based least squares approach is used for fitting a plane to the 3D road points. Fast RANSAC fitting is obtained by selecting points according to a probability distribution function that takes into account the density of points at a given depth. Finally, stereo camera position and orientation—pose—is computed relative to the road plane. The proposed technique is intended to be used on driver assistance systems for applications such as obstacle or pedestrian detection. A real time performance is reached. Experimental results on several environments and comparisons with a previous work are presented.

Studies have shown that a large number of medium to large scale software intensive system development are cancelled. The primary reasons include the loss, lack or mis-understanding the problem to be “solved” – from customer to engineers and even amongst the engineers themselves. The Object Boundary/Context modelling process is key to immediate “system” understanding of the problem space at the highest level, enabling a “context” for formulating plans and requirements elicitation. Furthermore, it provides a communication point between all stakeholders and enables the correction of misunderstandings at the earlier stages of a software intensive system development. The model does not seek to supplant conventional formal analysis/architecture/design but acts as the earliest model to ensure that complex software problems do not turn “wicked”.

In this paper we show our work related to an approach for monitoring web sources on the World Wide Web using its temporal properties in order to integrate them in a temporal Data Warehouse. We use these temporal properties obtained for integrating data more efficiently from different data sources according to the requirements of the Data Warehouse administrator. For this integration process we proposed a parallel fuzzy temporal semantic algorithm based on a flexible query language called FSQL in order to obtain more precise data in the Data Warehouse. In addition, we show an application applied to tourism area where data integrated into Data Warehouse can be used to schedule personalized travel as a value-added service for electronic commerce.

This paper explores and discusses the application of Software Agent in pattern layout design. First we introduce Pattern Decomposition Representation Model (PDM). By combining Agent technology with the PDM, we also propose and analyze an Agent-Based Pattern Design Model (ABPDM) and present the implementation of the Agents and their cooperation mechanism. Results show that ABPDM is an effective approach for the design of serial and regular pattern.