Javier Portillo

Universidad Politécnica de Madrid | UPM · Departamento de Señales, Sistemas y Radiocomunicaciones

This paper describes two systems that can be used to obtain realistic random traffic samples in a terminal area: a real traffic analyser and a synthetic traffic generator. These two systems allow the air traffic management (ATM) engineer to gain insight on the traffic structure of the area under analysis, and allow obtaining realistic traffic sampl...

This paper presents a mobile-instrumented Platform to interact with smart objects by using gestures. The system relies on a Dynamic Time Warping algorithm, which serve to train personalized gestures and also to recognize them real-time. The trained set of gestures is available for consumer applications to include this type of interaction in their f...

Background: Quite often, magnetoencephalography (MEG) measurements are contaminated by a series of artifacts that degrade the quality of the various source localization methods applied to them. In particular, eye blinking, minor head movement and related activities are a constant source of measurement contamination. In order to solve this problem,...

The convenience and effectiveness of using case and project-based learning in undergraduate courses in engineering degrees is currently a subject of debate in many academic forums. While some lecturers support the advantages of these constructive learner-centred methods independently of the topic, others are sceptical about their use, mainly when a...

This paper describes a pair of systems which can be used to obtain realistic traffic samples in a Sector/TMA from a given real traffic database. Those are a traffic analyzer and a traffic pattern generator. These two systems allow the ATM engineer to both gain insight on the traffic structure of the area under analysis and to obtain statistically s...

Remote sensing images often present a hierarchical structure, composed of a variety of nested regions each of which represents a different area: water basins, agricultural fields, urban regions... In several applications such as cadastre information retrieval it is important to identify and distinguish these regions in an easy and automatic way. Re...

This paper describes the design and implementation of a bias estimation system for airport surveillance. If not correctly calibrated, systematic errors may lead to track instability, and even to track splitting. Airport safety demands for very stable and accurate tracking, and so addressing this problem is mandatory if a data fusion system is to be...

In this correspondence the design of an airport surface surveillance system based on TV cameras and low-cost processing hardware is described. The work presented here focuses on the single-sensor multiple-target tracking part of the system, giving a description of a prototype of this key system component and some quantitative and qualitative assess...

This paper addresses the problem of finding matching points in stereo image pairs, i.e., the problem of correspondence. Even though this topic is well-known, a complete probabilistic formulation of it using psychovisual cues is still missing. We propose a novel Bayesian model based on Markov Random Fields (MRFs); the prior energy function is built...

A video aircraft identification algorithm, based on tail number recognition, is proposed as part of a global airport surveillance video system. The recognition procedure searches and detects the presence of the tail number in the image and then recognizes the tail number using pattern matching techniques. The identification system has been designed...

Advanced surface movement guidance and control systems need the identification of aircraft and vehicles in airport movement areas. In this work, a video identification algorithm based on tail number recognition is proposed as a part of a global surveillance video system. The aircraft identification problem has to deal with three fundamental aspects...

This paper describes the optimisation of some parameters of an Optical Character Recognition System (OCR). The optimisation is performed by means of an Evolution Strategies (ES) in order to maximize the pattern discrimination. The patterns set is a vectorial representation of the characters set. The OCR is applied to identify the tail number of an...

This paper explores the use of breadth-first graph traversal for the processing of digital images. It presents efficient algorithms for eroding, dilating, skeletonizing, and distance-transforming regions. These algorithms work by traversing regions in a breadth-first manner using a queue for storage of unprocessed pixels. They use memory efficientl...

In this paper we describe an innovative airport surface surveillance system based on CCTV cameras and low-cost processing hardware. The system will fulfill (at least partially) Advanced Surface Movement Guidance and Control Systems needs for tracking, identification and target classification, and it will in conjunction with current (mainly radar ba...

The Advanced Surface Movement Guidance and Control Systems require the unambiguous identification and accurate determination of the position of all aircraft and vehicles in the airport movement area. Several types of sensors, based on different technologies, are currently used for this task. Every single kind of sensor provides specific benefits an...

We address the problem of stereo matching in the context of Markov random fields (MRFs) and the Bayesian approach. Although MRFs are used as a tool intended to formulate the problem in a way that allows the application of a powerful optimization technique called simulated annealing, the bases for the formulation of the stereo matching problem from...

Two new probability density functions (PDFs) closely related to the beta PDF are derived. The first PDF generalises the well-known relation about gamma and beta random variables (RVs). The second enables the modelling of uncertainty in one of the parameters of the beta RV. Both functions have a number of interesting applications in image processing...

A complete, low computational cost method is presented for multispectral textured image segmentation. The procedure performs a tesselation of the image into non-overlapped rectangular regions and decides about the homogeneity of each region, using statistical hypothesis testing. Regions labelled as homogeneous are used to estimate the parameters th...

In this paper we show the benefits of applying hypothesis testing to the problem of texture segmentation. In our approach, hypothesis testing is used at two different stages that help to reduce the computational burden associated to iterative methods commonly used in image processing. Specifically, hypothesis testing is used to initially estimate t...

In this contribution we present a design procedure, based on Evolutionary Strategies Optimisation, to parametrize Interacting Multiple Model tracking structures for Air Traffic Control Applications. The objective, not addressed in the available bibliography on IMM filters, is to find the most suitable parameters (including transition probabilities...

This paper describes the optimisation of some parameters of an Optical Character Recognition System (OCR). The optimisation is performed by means of an Evolution Strategies (ES) in order to maximize the pattern discrimination. The patterns set is a vectorial representation of the characters set. The OCR is applied to identify the tail number of an...

En este trabajo se presentan avances en la aplicación de la lógica borrosa en sistemas de seguimiento utilizando visión activa. A lo largo del artículo se incluyen referencias a diversos trabajos llevados a cabo en la aplicación de la lógica borrosa en el terreno de la asociación para el seguimiento de blancos mediante cámaras. En particular se det...