Abstract: Ground-truth data is essential for the objective evaluation of object detection methods in computer vision. Many works claim their method is robust but they support it with experiments which are not quantitatively assessed with regard some ground-truth. This is one of the main obstacles to properly evaluate and compare such methods. One of the main reasons is that creating an extensive and representative ground-truth is very time consuming, specially in the case of video sequences, where thousands of frames have to be labelled. Could such a ground-truth be generated, at least in part, automatically? Though it may seem a contradictory question, we show that this is possible for the case of video sequences recorded from a moving camera. The key idea is transferring existing frame segmentations from a reference sequence into another video sequence recorded at a different time on the same track, possibly under a different ambient lighting. We have carried out experiments on several video sequence pairs and quantitatively assessed the precision of the transformed ground-truth, which prove that our approach is not only feasible but also quite accurate.

Abstract: The design and the validation of an automatic plaque characterization technique based on Intravascular Ultrasound (IVUS) usually requires a data ground-truth. The histological analysis of post-mortem coronary arteries is commonly assumed as the state-of-the-art process for the extraction of a reliable data-set of atherosclerotic plaques. Unfortunately, the amount of data provided by this technique is usually few, due to the difficulties in collecting post-mortem cases and phenomena of tissue spoiling during histological analysis. In this paper we tackle the process of fusing in-vivo and in-vitro IVUS data starting with the analysis of recently proposed approaches for the creation of an enhanced IVUS data-set; furthermore, we propose a new approach, named pLDS, based on semi-supervised learning with a data selection criterion. The enhanced data-set obtained by each one of the analyzed approaches is used to train a classifier for tissue characterization purposes. Finally, the discriminative power of each classifier is quantitatively assessed and compared by classifying a data-set of validated in-vitro IVUS data.

Abstract: In this paper we propose a method that smartly improves occlusion handling in stereo matching using trinocular stereo. The main idea is based on the assumption that any occluded region in a matched stereo pair (middle-left images) in general is not occluded in the opposite matched pair (middle-right images). Then two disparity space images (DSI) can be merged in one composite DSI. The proposed integration differs from the known approach that uses a cumulative cost. A dense disparity map is obtained with a global optimization algorithm using the proposed composite DSI. The experimental results are evaluated on the Middlebury data set, showing high performance of the proposed algorithm especially in the occluded regions. One of the top positions in the rank of the Middlebury website confirms the performance of our method to be competitive with the best stereo matching.

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.

Abstract: This paper addresses the novel problem of characterizing conversational group dynamics. It is well documented in social psychology that depending on the objectives a group, the dynamics are different. For example, a competitive meeting has a different objective from that of a collaborative meeting. We propose a method to characterize group dynamics based on the joint description of a group members' aggregated acoustical nonverbal behaviour to classify two meeting datasets (one being cooperative-type and the other being competitive-type). We use 4.5 hours of real behavioural multi-party data and show that our methodology can achieve a classification rate of upto 100%.

Abstract: The combination of the output of classifiers has been one of the strategies used to improve classification rates in general purpose classification systems. Some of the most common approaches can be explained using the Bayes' formula. In this paper, we tackle the problem of the combination of classifiers using a non-Bayesian probabilistic framework. This approach permits us to derive two linear combination rules that minimize misclassification rates under some constraints on the distribution of classifiers. In order to show the validity of this approach we have compared it with other popular combination rules from a theoretical viewpoint using a synthetic data set, and experimentally using two standard databases: the MNIST handwritten digit database and the GREC symbol database. Results on the synthetic data set show the validity of the theoretical approach. Indeed, results on real data show that the proposed methods outperform other common combination schemes.