Abstract: In this paper, we argue that only using behavioural motion information, we are able to predict the interest of observers when looking at face-to-face interactions. We propose a set of movement-related features from body, face, and mouth activity in order to define a set of higher level interaction features, such as stress, activity, speaking engagement, and corporal engagement. Error-Correcting Output Codes framework with an Adaboost base classifier is used to learn to rank the perceived observer's interest in face-to-face interactions. The automatic system shows good correlation between the automatic categorization results and the manual ranking made by the observers. In particular, the learning system shows that stress features have a high predictive power for ranking interest of observers when looking at of face-to-face interactions.

Abstract: Symbol spotting problem requires feature extraction strategies able to generalize from training samples and to localize the target object while discarding most part of the image. In the case of document analysis, symbol spotting techniques have to deal with a high variability of symbols' appearance. In this paper, we propose the Circular Blurred Shape Model descriptor. Feature extraction is performed capturing the spatial arrangement of significant object characteristics in a correlogram structure. Shape information from objects is shared among correlogram regions, being tolerant to the irregular deformations. Descriptors are learnt using a cascade of classifiers and Abadoost as the base classifier. Finally, symbol spotting is performed by means of a windowing strategy using the learnt cascade over plan and old musical score documents. Spotting and multi-class categorization results show better performance comparing with the state-of-the-art descriptors.

Abstract: 38(Suppl.)ECVP Abstract Supplement
We developed a new psychophysical method to compare different colour appearance models when applied to natural scenes. The method was as follows: two images (processed by different algorithms) were displayed on a CRT monitor and observers were asked to select the most natural of them. The original images were gathered by means of a calibrated trichromatic digital camera and presented one on top of the other on a calibrated screen. The selection was made by pressing on a 6-button IR box, which allowed observers to consider not only the most natural but to rate their selection. The rating system allowed observers to register how much more natural was their chosen image (eg, much more, definitely more, slightly more), which gave us valuable extra information on the selection process. The results were analysed considering both the selection as a binary choice (using Thurstone's law of comparative judgement) and using Bradley-Terry method for ordinal comparison. Our results show a significant difference in the rating scales obtained. Although this method has been used in colour constancy algorithm comparisons, its uses are much wider, eg to compare algorithms of image compression, rendering, recolouring, etc.

Abstract: We generated a new dataset of digital natural images where each colour plane corresponds to the human LMS (long-, medium-, short-wavelength) cone activations. The images were chosen to represent five different visual environments (eg forest, seaside, mountain snow, urban, motorways) and were taken under natural illumination at different times of day. At the bottom-left corner of each picture there was a matte grey ball of approximately constant spectral reflectance (across the camera's response spectrum,) and nearly Lambertian reflective properties, which allows to compute (and remove, if necessary) the illuminant's colour and intensity. The camera (Sigma Foveon SD10) was calibrated by measuring its sensor's spectral responses using a set of 31 spectrally narrowband interference filters. This allowed conversion of the final camera-dependent RGB colour space into the Smith and Pokorny (1975) cone activation space by means of a polynomial transformation, optimised for a set of 1269 Munsell chip reflectances. This new method is an improvement over the usual 3 × 3 matrix transformation which is only accurate for spectrally-narrowband colours. The camera-to-LMS transformation can be recalculated to consider other non-human visual systems. The dataset is available to download from our website.

Abstract: En este artículo se presenta Caronte, entorno LMS (Learning Management System) basado en Moodle. Una característica importante del entorno es la gestión flexible de grupos en una asignatura. Entendemos por grupo un conjunto de alumnos que realizan un trabajo y uno de ellos entrega la actividad propuesta (práctica, encuesta, etc.) en representación del grupo. Hemos trabajado en la confección de estos grupos, implementando un sistema de inscripción por contraseña.
Caronte ofrece un conjunto de actividades basadas en este concepto de grupo: encuestas, tareas (entrega de trabajos o prácticas), encuestas de autoevaluación y cuestionarios, entre otras.
Basada en nuestra actividad de encuesta, hemos definido una actividad de Control, que permite un cierto feedback electrónico del profesor sobre la actividad de los alumnos.
Finalmente, se presenta un resumen de las experiencias de uso de Caronte sobre asignaturas de Ingeniería Informática en el curso 2007-08.

Abstract: We describe an architecture for a multi-camera, multi-resolution surveillance system. The aim is to support a set of distributed static and pan-tilt-zoom (PTZ) cameras and visual tracking algorithms, together with a central supervisor unit. Each camera (and possibly pan-tilt device) has a dedicated process and processor. Asynchronous interprocess communications and archiving of data are achieved in a simple and effective way via a central repository, implemented using an SQL database. Visual tracking data from static views are stored dynamically into tables in the database via client calls to the SQL server. A supervisor process running on the SQL server determines if active zoom cameras should be dispatched to observe a particular target, and this message is effected via writing demands into another database table. We show results from a real implementation of the system comprising one static camera overviewing the environment under consideration and a PTZ camera operating under closed-loop velocity control, which uses a fast and robust level-set-based region tracker. Experiments demonstrate the effectiveness of our approach and its feasibility to multi-camera systems for intelligent surveillance.

Abstract: The comprehension of animal behavior, especially human behavior, is one of the most ancient and studied problems since the beginning of civilization. The big list of factors that interact to determine a person action require the collaboration of different disciplines, such as psichology, biology, or sociology. In the last years the analysis of human behavior has received great attention also from the computer vision community, given the latest advances in the acquisition of human motion data from image sequences.
Despite the increasing availability of that data, there still exists a gap towards obtaining a conceptual representation of the obtained observations. Human behavior analysis is based on a qualitative interpretation of the results, and therefore the assignment of concepts to quantitative data is linked to a certain ambiguity.
This Thesis tackles the problem of obtaining a proper representation of human behavior in the contexts of computer vision and animation. On the one hand, a good behavior model should permit the recognition and explanation the observed activity in image sequences. On the other hand, such a model must allow the generation of new synthetic instances, which model the behavior of virtual agents.
First, we propose methods to automatically learn the models from observations. Given a set of quantitative results output by a vision system, a normal behavior model is learnt. This results provides a tool to determine the normality or abnormality of future observations. However, machine learning methods are unable to provide a richer description of the observations. We confront this problem by means of a new method that incorporates prior knowledge about the enviornment and about the expected behaviors. This framework, formed by the reasoning engine FMTL and the modeling tool SGT allows the generation of conceptual descriptions of activity in new image sequences. Finally, we demonstrate the suitability of the proposed framework to simulate behavior of virtual agents, which are introduced into real image sequences and interact with observed real agents, thereby easing the generation of augmented reality sequences.
The set of approaches presented in this Thesis has a growing set of potential applications. The analysis and description of behavior in image sequences has its principal application in the domain of smart video--surveillance, in order to detect suspicious or dangerous behaviors. Other applications include automatic sport commentaries, elderly monitoring, road traffic analysis, and the development of semantic video search engines. Alternatively, behavioral virtual agents allow to simulate accurate real situations, such as fires or crowds. Moreover, the inclusion of virtual agents into real image sequences has been widely deployed in the games and cinema industries.