Fast and accurate hand pose detection for human-robot interaction

[EN]Enabling natural human-robot interaction using computer vision based applications requires fast and accurate hand detection. However, previous works in this field assume different constraints, like a limitation in the number of detected gestures, because hands are highly complex objects difficult to locate. This paper presents an approach which integrates temporal coherence cues and hand detection based on wrists using a cascade classifier. With this approach, we introduce three main contributions: (1) a transparent initialization mechanism without user participation for segmenting hands independently of their gesture, (2) a larger number of detected gestures as well as a faster training phase than previous cascade classifier based methods and (3) near real-time performance for hand pose detection in video streams.

Complex natural resonances of conducting planar objects buried in a dielectric half-space

A scheme is presented to incorporate a mixed potential integral equation (MPIE) using Michalski's formulation C with the method of moments (MoM) for analyzing the scattering of a plane wave from conducting planar objects buried in a dielectric half-space. The robust complex image method with a two-level approximation is used for the calculation of the Green's functions for the half-space. To further speed up the computation, an interpolation technique for filling the matrix is employed. While the induced current distributions on the object's surface are obtained in the frequency domain, the corresponding time domain responses are calculated via the inverse fast Fourier transform (FFT), The complex natural resonances of targets are then extracted from the late time response using the generalized pencil-of-function (GPOF) method. We investigate the pole trajectories as we vary the distance between strips and the depth and orientation of single, buried strips, The variation from the pole position of a single strip in a homogeneous dielectric medium was only a few percent for most of these parameter variations.

Development of Procedures of Recognition of Objects with Usage Multisensor Ontology Controlled Instrumental Complex

The ontological approach to structuring knowledge and the description of data domain of knowledge is considered. It is described tool ontology-controlled complex for research and developments of sensor systems. Some approaches to solution most frequently meeting tasks are considered for creation of the recognition procedures.

On cluster analysis of complex and heterogeneous data

3rd SMTDA Conference Proceedings, 11-14 June 2014, Lisbon Portugal.

Complex evolution of a multi-particle system

This paper studies a discrete dynamical system of interacting particles that evolve by interacting among them. The computational model is an abstraction of the natural world, and real systems can range from the huge cosmological scale down to the scale of biological cell, or even molecules. Different conditions for the system evolution are tested. The emerging patterns are analysed by means of fractal dimension and entropy measures. It is observed that the population of particles evolves towards geometrical objects with a fractal nature. Moreover, the time signature of the entropy can be interpreted at the light of complex dynamical systems.

Embracing transience and subjectivity in the conservation of complex contemporary artworks: contributions from ethnographic and psychological paradigms

Dissertação para obtenção do Grau de Mestre em Conservação e Restauro, Perfil Ciências da Conservação Especialização em Arte Contemporânea

Benefits & drawbacks of different means of interaction for placing objects above a video footage

Public Display Systems (PDS) increasingly have a greater presence in our cities. These systems provide information and advertising specifically tailored to audiences in spaces such as airports, train stations, and shopping centers. A large number of public displays are also being deployed for entertainment reasons. Sometimes designing and prototyping PDS come to be a laborious, complex and a costly task. This dissertation focuses on the design and evaluation of PDS at early development phases with the aim of facilitating low-effort, rapid design and the evaluation of interactive PDS. This study focuses on the IPED Toolkit. This tool proposes the design, prototype, and evaluation of public display systems, replicating real-world scenes in the lab. This research aims at identifying benefits and drawbacks on the use of different means to place overlays/virtual displays above a panoramic video footage, recorded at real-world locations. The means of interaction studied in this work are on the one hand the keyboard and mouse, and on the other hand the tablet with two different techniques of use. To carry out this study, an android application has been developed whose function is to allow users to interact with the IPED Toolkit using the tablet. Additionally, the toolkit has been modified and adapted to tablets by using different web technologies. Finally the users study makes a comparison about the different means of interaction.

Concepts and objects of awareness in Alzheimer’s disease: an updated systematic review

ABSTRACT Objectives To compare and discuss the objects of awareness in Alzheimer’s disease (AD): awareness of cognitive deficits, of functional activities, of social-emotional functioning and behavioral impairment. Methods A search in the PsycINFo, Pilots, PubMed/Medline and ISI electronic databases according to Prisma methodology was performed. We included studies about awareness in people with AD published between 2010 and 2015, with the combination of keywords: “Alzheimer AND awareness of deficits”, “Alzheimer AND anosognosia”, “Alzheimer AND insight”, “dementia AND awareness of deficits”, “dementia AND anosognosia”, “dementia AND insight”. The articles were categorized according to the specific object of awareness. Results Seven hundred and ten records were identified and, after application of the exclusion criteria, 191 studies were retrieved for potential use. After excluding the duplicates, 46 studies were included. Most studies assessed the cognitive domain of awareness, followed by the functional, social-emotional, and behavioral impairment domains. Memory deficits were not sufficient to explain impaired awareness in AD. Longitudinal studies did not find discrepancies between patients and caregivers’ reports, indicating that awareness is not related to cognition. Conflicting findings were observed, including the relation between awareness, mood, severity of disease, and personal characteristics. Conclusions The studies show lack of conceptual consensus and significant methodological differences. The inclusion of samples without differentiation of dementia etiology is associated to symptomatic differences, which affect awareness domains. Awareness in AD is a complex and multidimensional construct. Different objects elicit different levels of awareness.

Symptomatic complex partial status epilepticus manifesting as utilization behavior of a mobile phone.

Utilization behavior (UB) consists of reaching out and using objects in the environment in an automatic manner and out of context. This behavior has been correlated to frontal lobe dysfunction, especially of the right hemisphere. We describe a 60-year-old woman, affected by a glioblastoma located in the right frontal region, who presented with intermittent UB of the mobile phone as the main clinical manifestation of partial complex status epilepticus. Video/EEG studies showed a striking correlation between mobile phone utilization and ictal epileptic activity. Clinical and EEG findings were markedly reduced after the introduction of antiepileptic drugs. This case study suggests that UB may be added to the symptoms described for partial seizures originating from frontal areas.

Representation of Sound Objects within Early-Stage Auditory Areas: A Repetition Effect Study Using 7T fMRI.

Environmental sounds are highly complex stimuli whose recognition depends on the interaction of top-down and bottom-up processes in the brain. Their semantic representations were shown to yield repetition suppression effects, i. e. a decrease in activity during exposure to a sound that is perceived as belonging to the same source as a preceding sound. Making use of the high spatial resolution of 7T fMRI we have investigated the representations of sound objects within early-stage auditory areas on the supratemporal plane. The primary auditory cortex was identified by means of tonotopic mapping and the non-primary areas by comparison with previous histological studies. Repeated presentations of different exemplars of the same sound source, as compared to the presentation of different sound sources, yielded significant repetition suppression effects within a subset of early-stage areas. This effect was found within the right hemisphere in primary areas A1 and R as well as two non-primary areas on the antero-medial part of the planum temporale, and within the left hemisphere in A1 and a non-primary area on the medial part of Heschl's gyrus. Thus, several, but not all early-stage auditory areas encode the meaning of environmental sounds.

Incorporating complex cells into neural networks for pattern classification

Dans le domaine des neurosciences computationnelles, l'hypothèse a été émise que le système visuel, depuis la rétine et jusqu'au cortex visuel primaire au moins, ajuste continuellement un modèle probabiliste avec des variables latentes, à son flux de perceptions. Ni le modèle exact, ni la méthode exacte utilisée pour l'ajustement ne sont connus, mais les algorithmes existants qui permettent l'ajustement de tels modèles ont besoin de faire une estimation conditionnelle des variables latentes. Cela nous peut nous aider à comprendre pourquoi le système visuel pourrait ajuster un tel modèle; si le modèle est approprié, ces estimé conditionnels peuvent aussi former une excellente représentation, qui permettent d'analyser le contenu sémantique des images perçues. Le travail présenté ici utilise la performance en classification d'images (discrimination entre des types d'objets communs) comme base pour comparer des modèles du système visuel, et des algorithmes pour ajuster ces modèles (vus comme des densités de probabilité) à des images. Cette thèse (a) montre que des modèles basés sur les cellules complexes de l'aire visuelle V1 généralisent mieux à partir d'exemples d'entraînement étiquetés que les réseaux de neurones conventionnels, dont les unités cachées sont plus semblables aux cellules simples de V1; (b) présente une nouvelle interprétation des modèles du système visuels basés sur des cellules complexes, comme distributions de probabilités, ainsi que de nouveaux algorithmes pour les ajuster à des données; et (c) montre que ces modèles forment des représentations qui sont meilleures pour la classification d'images, après avoir été entraînés comme des modèles de probabilités. Deux innovations techniques additionnelles, qui ont rendu ce travail possible, sont également décrites : un algorithme de recherche aléatoire pour sélectionner des hyper-paramètres, et un compilateur pour des expressions mathématiques matricielles, qui peut optimiser ces expressions pour processeur central (CPU) et graphique (GPU).

Computer Analysis of Visual Properties of Curved Objects

A method is presented for the visual analysis of objects by computer. It is particularly well suited for opaque objects with smoothly curved surfaces. The method extracts information about the object's surface properties, including measures of its specularity, texture, and regularity. It also aids in determining the object's shape. The application of this method to a simple recognition task ??e recognition of fruit ?? discussed. The results on a more complex smoothly curved object, a human face, are also considered.

Using a runway paradigm to assess the relative strength of rats' motivations for enrichment objects

Laboratory animals should be provided with enrichment objects in their cages; however, it is first necessary to test whether the proposed enrichment objects provide benefits that increase the animals’ welfare. The two main paradigms currently used to assess proposed enrichment objects are the choice test, which is limited to determining relative frequency of choice, and consumer demand studies, which can indicate the strength of a preference but are complex to design. Here, we propose a third methodology: a runway paradigm, which can be used to assess the strength of an animal’s motivation for enrichment objects, is simpler to use than consumer demand studies, and is faster to complete than typical choice tests. Time spent with objects in a standard choice test was used to rank several enrichment objects in order to compare with the ranking found in our runway paradigm. The rats ran significantly more times, ran faster, and interacted longer with objects with which they had previously spent the most time. It was concluded that this simple methodology is suitable for measuring rats’ motivation to reach enrichment objects. This can be used to assess the preference for different types of enrichment objects or to measure reward system processes.

A unified approach to the recognition of complex actions from sequences of zone-crossings

We present a method for the recognition of complex actions. Our method combines automatic learning of simple actions and manual definition of complex actions in a single grammar. Contrary to the general trend in complex action recognition that consists in dividing recognition into two stages, our method performs recognition of simple and complex actions in a unified way. This is performed by encoding simple action HMMs within the stochastic grammar that models complex actions. This unified approach enables a more effective influence of the higher activity layers into the recognition of simple actions which leads to a substantial improvement in the classification of complex actions. We consider the recognition of complex actions based on person transits between areas in the scene. As input, our method receives crossings of tracks along a set of zones which are derived using unsupervised learning of the movement patterns of the objects in the scene. We evaluate our method on a large dataset showing normal, suspicious and threat behaviour on a parking lot. Experiments show an improvement of ~ 30% in the recognition of both high-level scenarios and their composing simple actions with respect to a two-stage approach. Experiments with synthetic noise simulating the most common tracking failures show that our method only experiences a limited decrease in performance when moderate amounts of noise are added.

Ordinal judgements of depth in monocularly- and binocularly-viewed photographs of complex natural scenes

This study investigated the contribution of stereoscopic depth cues to the reliability of ordinal depth judgments in complex natural scenes. Participants viewed photographs of cluttered natural scenes, either monocularly or stereoscopically. On each trial, they judged which of two indicated points in the scene was closer in depth. We assessed the reliability of these judgments over repeated trials, and how well they correlated with the actual disparities of the points between the left and right eyes' views. The reliability of judgments increased as their depth separation increased, was higher when the points were on separate objects, and deteriorated for point pairs that were more widely separated in the image plane. Stereoscopic viewing improved sensitivity to depth for points on the same surface, but not for points on separate objects. Stereoscopic viewing thus provides depth information that is complementary to that available from monocular occlusion cues.