Abstract: In this paper, we propose a novel way to perform top-down semantic feedback in convolutional deep networks for efficient and accurate image parsing. We also show how to add global appearance/semantic features, which have shown to improve image parsing performance in state-of-the-art methods, and was not present in previous convolutional approaches. The proposed method is characterised by an efficient training and a sufficiently fast testing. We use the well known SIFTflow dataset to numerically show the advantages provided by our contributions, and to compare with state-of-the-art image parsing convolutional based approaches.

Abstract: Recent advances in endoscopic devices have increased their use for minimal invasive diagnostic and intervention procedures. Among all endoscopic modalities, bronchoscopy is one of the most frequent with around 261 millions of procedures per year. Although the use of bronchoscopy is spread among clinical facilities it presents some drawbacks, being the visual inspection for the assessment of anatomical measurements the most prevalent of them. In
particular, inaccuracies in the estimation of the degree of stenosis (the percentage of obstructed airway) decreases its diagnostic yield and might lead to erroneous treatments. An objective computation of tracheal stenosis in bronchoscopy videos would constitute a breakthrough for this non-invasive technique and a reduction in treatment cost.
This thesis settles the first steps towards on-line reliable extraction of anatomical information from videobronchoscopy for computation of objective measures. In particular, we focus on the computation of the degree of stenosis, which is obtained by comparing the area delimited by a healthy tracheal ring and the stenosed lumen. Reliable extraction of airway structures in interventional videobronchoscopy is a challenging task. This is mainly due to the large variety of acquisition conditions (positions and illumination), devices (different digitalizations) and in videos acquired at the operating room the unpredicted presence of surgical devices (such as probe ends). This thesis contributes to on-line stenosis assessment in several ways. We
propose a parametric strategy for the extraction of lumen and tracheal rings regions based on the characterization of their geometry and appearance that guide a deformable model. The geometric and appearance characterization is based on a physical model describing the way bronchoscopy images are obtained and includes local and global descriptions. In order to ensure a systematic applicability we present a statistical framework to select the optimal
parameters of our method. Experiments perform on the first public annotated database, show that the performance of our method is comparable to the one provided by clinicians and its computation time allows for a on-line implementation in the operating room.

Abstract: The study of color vision has been aided by a whole battery of computational methods that attempt to describe the mechanisms that lead to our perception of colors in terms of the information-processing properties of the visual system. Their scope is highly interdisciplinary, linking apparently dissimilar disciplines such as mathematics, physics, computer science, neuroscience, cognitive science, and psychology. Since the sensation of color is a feature of our brains, computational approaches usually include biological features of neural systems in their descriptions, from retinal light-receptor interaction to subcortical color opponency, cortical signal decoding, and color categorization. They produce hypotheses that are usually tested by behavioral or psychophysical experiments.

Abstract: Human-robot interaction is a hot topic nowadays in the social robotics community. One crucial aspect is represented by the affective communication which comes encoded through the facial expressions. In this paper, we propose a novel approach for facial expression recognition, which exploits an efficient and adaptive graph-based label propagation (semi-supervised mode) in a multi-observation framework. The facial features are extracted using an appearance-based 3D face tracker, view- and texture independent. Our method has been extensively tested on the CMU dataset, and has been conveniently compared with other methods for graph construction. With the proposed approach, we developed an application for an AIBO robot, in which it mirrors the recognized facial
expression.

Abstract: Moving cast shadows are a major concern in today’s performance from broad range of many vision-based surveillance applications because they highly difficult the object classification task. Several shadow detection methods have been reported in the literature during the last years. They are mainly divided into two domains. One usually works with static images, whereas the second one uses image sequences, namely video content. In spite of the fact that both cases can be analogously analyzed, there is a difference in the application field. The first case, shadow detection methods can be exploited in order to obtain additional geometric and semantic cues about shape and position of its casting object (‘shape from shadows’) as well as the localization of the light source. While in the second one, the main purpose is usually change detection, scene matching or surveillance (usually in a background subtraction context). Shadows can in fact modify in a negative way the shape and color of the target object and therefore affect the performance of scene analysis and interpretation in many applications. This chapter wills mainly reviews shadow detection methods as well as their taxonomies related with the second case, thus aiming at those shadows which are associated with moving objects (moving shadows).

Abstract: Motion perception is an amazing innate ability of the creatures on the planet. This adroitness entails a functional advantage that enables species to compete better in the wild. The motion perception ability is usually employed at different levels, allowing from the simplest interaction with the ’physis’ up to the most transcendental survival tasks. Among the five classical perception system , vision is the most widely used in the motion perception field. Millions years of evolution have led to a highly specialized visual system in humans, which is characterized by a tremendous accuracy as well as an extraordinary robustness. Although humans and an immense diversity of species can distinguish moving object with a seeming simplicity, it has proven to be a difficult and non trivial problem from a computational perspective. In the field of Computer Vision, the detection of moving objects is a challenging and fundamental research area. This can be referred to as the ’origin’ of vast and numerous vision-based research sub-areas. Nevertheless, from the bottom to the top of this hierarchical analysis, the foundations still relies on when and where motion has occurred in an image. Pixels corresponding to moving objects in image sequences can be identified by measuring changes in their values. However, a pixel’s value (representing a combination of color and brightness) could also vary due to other factors such as: variation in scene illumination, camera noise and nonlinear sensor responses among others. The challenge lies in detecting if the changes in pixels’ value are caused by a genuine object movement or not. An additional challenging aspect in motion detection is represented by moving cast shadows. The paradox arises because a moving object and its cast shadow share similar motion patterns. However, a moving cast shadow is not a moving object. In fact, a shadow represents a photometric illumination effect caused by the relative position of the object with respect to the light sources. Shadow detection methods are mainly divided in two domains depending on the application field. One normally consists of static images where shadows are casted by static objects, whereas the second one is referred to image sequences where shadows are casted by moving objects. For the first case, shadows can provide additional geometric and semantic cues about shape and position of its casting object as well as the localization of the light source. Although the previous information can be extracted from static images as well as video sequences, the main focus in the second area is usually change detection, scene matching or surveillance. In this context, a shadow can severely affect with the analysis and interpretation of the scene. The work done in the thesis is focused on the second case, thus it addresses the problem of detection and removal of moving cast shadows in video sequences in order to enhance the detection of moving object.

Abstract: PATREC5825
We present a methodology to address the problem of human gesture segmentation and recognition in video and depth image sequences. A Bag-of-Visual-and-Depth-Words (BoVDW) model is introduced as an extension of the Bag-of-Visual-Words (BoVW) model. State-of-the-art RGB and depth features, including a newly proposed depth descriptor, are analysed and combined in a late fusion form. The method is integrated in a Human Gesture Recognition pipeline, together with a novel probability-based Dynamic Time Warping (PDTW) algorithm which is used to perform prior segmentation of idle gestures. The proposed DTW variant uses samples of the same gesture category to build a Gaussian Mixture Model driven probabilistic model of that gesture class. Results of the whole Human Gesture Recognition pipeline in a public data set show better performance in comparison to both standard BoVW model and DTW approach.

Abstract: 5Y Impact Factor: 1.14 / 3rd (Computer Science, Artificial Intelligence)
We introduce a model of attentional eye guidance based on the rationale that the deployment of gaze is to be considered in the context of a general action-perception loop relying on two strictly intertwined processes: sensory processing, depending on current gaze position, identifies sources of information that are most valuable under the given task; motor processing links such information with the oculomotor act by sampling the next gaze position and thus performing the gaze shift. In such a framework, the choice of where to look next is task-dependent and oriented to classes of objects embedded within pictures of complex scenes. The dependence on task is taken into account by exploiting the value and the payoff of gazing at certain image patches or proto-objects that provide a sparse representation of the scene objects. The different levels of the action-perception loop are represented in probabilistic form and eventually give rise to a stochastic process that generates the gaze sequence. This way the model also accounts for statistical properties of gaze shifts such as individual scan path variability. Results of the simulations are compared either with experimental data derived from publicly available datasets and from our own experiments.