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: In order to deal with the huge amount of content generated by social media, especially for indexing and retrieval purposes, the focus shifted from single object recognition to multi-observation object recognition. Of particular interest is the problem of face recognition (used as primary cue for persons’ identity assessment), since it is highly required by popular social media search engines like Facebook and Youtube. Recently, several approaches for graph-based label propagation were proposed. However, the associated graphs were constructed in an ad-hoc manner (e.g., using the KNN graph) that cannot cope properly with the rapid and frequent changes in data appearance, a phenomenon intrinsically related with video sequences. In this paper, we
propose a novel approach for efficient and adaptive graph construction, based on a two-phase scheme: (i) the first phase is used to adaptively find the neighbors of a sample and also to find the adequate weights for the minimization function of the second phase; (ii) in the second phase, the
selected neighbors along with their corresponding weights are used to locally and collaboratively estimate the sparse affinity matrix weights. Experimental results performed on Honda Video Database (HVDB) and a subset of video
sequences extracted from the popular TV-series ’Friends’ show a distinct advantage of the proposed method over the existing standard graph construction methods.

Abstract: In two previous experiments [Parraga et al, 2009 J. of Im. Sci. and Tech 53(3) 031106; Benavente et al,2009 Perception 38 ECVP Supplement, 36] the boundaries of basic colour categories were measured.
In the first experiment, samples were presented in isolation (ie on a dark background) and boundaries were measured using a yes/no paradigm. In the second, subjects adjusted the chromaticity of a sample presented on a random Mondrian background to find the boundary between pairs of adjacent colours.
Results from these experiments showed significant dierences but it was not possible to conclude whether this discrepancy was due to the absence/presence of a colourful background or to the dierences in the paradigms used. In this work, we settle this question by repeating the first experiment (ie samples presented on a dark background) using the second paradigm. A comparison of results shows that
although boundary locations are very similar, boundaries measured in context are significantly dierent(more diuse) than those measured in isolation (confirmed by a Student’s t-test analysis on the subject’s answers statistical distributions). In addition, we completed the mapping of colour name space by measuring the boundaries between chromatic colours and the achromatic centre. With these results we
completed our parametric fuzzy-sets model of colour naming space.

Abstract: This paper investigates the role of saliency to improve the classification accuracy of a Convolutional Neural Network (CNN) for the case when scarce training data is available. Our approach consists in adding a saliency branch to an existing CNN architecture which is used to modulate the standard bottom-up visual features from the original image input, acting as an attentional mechanism that guides the feature extraction process. The main aim of the proposed approach is to enable the effective training of a fine-grained recognition model with limited training samples and to improve the performance on the task, thereby alleviating the need to annotate a large dataset. The vast majority of saliency methods are evaluated on their ability to generate saliency maps, and not on their functionality in a complete vision pipeline. Our proposed pipeline allows to evaluate saliency methods for the high-level task of object recognition. We perform extensive experiments on various fine-grained datasets (Flowers, Birds, Cars, and Dogs) under different conditions and show that saliency can considerably improve the network’s performance, especially for the case of scarce training data. Furthermore, our experiments show that saliency methods that obtain improved saliency maps (as measured by traditional saliency benchmarks) also translate to saliency methods that yield improved performance gains when applied in an object recognition pipeline.

Abstract: We investigate the problem of incremental learning for object counting, where a method must learn to count a variety of object classes from a sequence of datasets. A naïve approach to incremental object counting would suffer from catastrophic forgetting, where it would suffer from a dramatic performance drop on previous tasks. In this paper, we propose a new exemplar-free functional regularization method, called Density Map Distillation (DMD). During training, we introduce a new counter head for each task and introduce a distillation loss to prevent forgetting of previous tasks. Additionally, we introduce a cross-task adaptor that projects the features of the current backbone to the previous backbone. This projector allows for the learning of new features while the backbone retains the relevant features for previous tasks. Finally, we set up experiments of incremental learning for counting new objects. Results confirm that our method greatly reduces catastrophic forgetting and outperforms existing methods.