Entorn de programació pel robot Stäubli mitjantçant MatLab, aplicació a un sistema de recol·lecció de peces basat en visió artificial

Els objectius del projecte són: realitzar un intèrpret de comandes en VAL3 que rebi les ordres a través d’una connexió TCP/IP; realitzar una toolbox de Matlab per enviar diferents ordres mitjançant una connexió TCP/IP; adquirir i processar mitjançant Matlab imatges de la càmera en temps real i detectar la posició d’objectes artificials mitjançant la segmentació per color i dissenyar i realitzar una aplicació amb Matlab que reculli peces detectades amb la càmera. L’abast del projecte inclou: l’estudi del llenguatge de programació VAL3 i disseny de l’ intèrpret de comandes, l’estudi de les llibreries de Matlab per comunicació mitjançant TCP/IP, per l’adquisició d’imatges, pel processament d’imatges i per la programació en C; el disseny de la aplicació recol·lectora de peces i la implementació de: un intèrpret de comandes en VAL3, la toolbox pel control del robot STAUBLI en Matlab i la aplicació recol·lectora de peces mitjançant el processament d’imatges en temps real també en Matlab

Stereological analysis of the rat and monkey amygdala

The amygdala is part of a neural network that contributes to the regulation of emotional behaviors. Rodents, especially rats, are used extensively as model organisms to decipher the functions of specific amygdala nuclei, in particular in relation to fear and emotional learning. Analysis of the role of the nonhuman primate amygdala in these functions has lagged work in the rodent but provides evidence for conservation of basic functions across species. Here we provide quantitative information regarding the morphological characteristics of the main amygdala nuclei in rats and monkeys, including neuron and glial cell numbers, neuronal soma size, and individual nuclei volumes. The volumes of the lateral, basal, and accessory basal nuclei were, respectively, 32, 39, and 39 times larger in monkeys than in rats. In contrast, the central and medial nuclei were only 8 and 4 times larger in monkeys than in rats. The numbers of neurons in the lateral, basal, and accessory basal nuclei were 14, 11, and 16 times greater in monkeys than in rats, whereas the numbers of neurons in the central and medial nuclei were only 2.3 and 1.5 times greater in monkeys than in rats. Neuron density was between 2.4 and 3.7 times lower in monkeys than in rats, whereas glial density was only between 1.1 and 1.7 times lower in monkeys than in rats. We compare our data in rats and monkeys with those previously published in humans and discuss the theoretical and functional implications that derive from our quantitative structural findings.

Hippocampal volume predicts fluid intelligence in musically trained people.

Recently, age-related hippocampal (HP) volume loss could be associated with a decrease in general fluid intelligence (gF). In the present study we investigated whether and how extensive musical training modulates human HP volume and gF performance. Previously, some studies demonstrated positive effects of musical training on higher cognitive functions such as learning and memory, associated with neural adaptations beyond the auditory domain. In order to detect possible associations between musical training and gF, we bilaterally segmented the HP formation and assessed the individual gF performance of people with different levels of musical expertise. Multiple regression analyses revealed that HP volume predicts gF in musicians but not in nonmusicians; in particular, bilaterally enhanced HP volume is associated with increased gF exclusively in musically trained people (amateurs and experts). This result suggests that musical training facilitates the recruitment of cognitive resources, which are essential for gF and linked to HP functioning. Musical training, even at a moderate level of intensity, can thus be considered as a potential strategy to decelerate age-related effects of cognitive decline. © 2013 Wiley Periodicals, Inc.

Anàlisi d'imatges estereoscòpiques utilitzant mètodes de baixa càrrega computacional

 Mitjançant imatges estereoscòpiques es poden detectar la posició respecte dela càmera dels objectes que apareixen en una escena. A partir de lesdiferències entre les imatges captades pels dos objectius es pot determinar laprofunditat dels objectes. Existeixen diversitat de tècniques de visió artificialque permeten calcular la localització dels objectes, habitualment amb l’objectiude reconstruir l’escena en 3D. Aquestes tècniques necessiten una gran càrregacomputacional, ja que utilitzen mètodes de comparació bidimensionals, i pertant, no es poden utilitzar per aplicacions en temps real.En aquest treball proposem un nou mètode d’anàlisi de les imatgesestereoscòpiques que ens permeti obtenir la profunditat dels objectes d’unaescena amb uns resultats acceptables. Aquest nou mètode es basa entransformar la informació bidimensional de la imatge en una informacióunidimensional per tal de poder fer la comparació de les imatges amb un baixcost computacional, i dels resultats de la comparació extreure’n la profunditatdels objectes dins l’escena. Això ha de permetre, per exemple, que aquestmètode es pugui implementar en un dispositiu autònom i li permeti realitzaroperacions de guiatge a través d’espais interiors i exteriors.

Reconeixement de gestos de la mà amb el sensor Kinect

El reconeixement dels gestos de la mà (HGR, Hand Gesture Recognition) és actualment un camp important de recerca degut a la varietat de situacions en les quals és necessari comunicar-se mitjançant signes, com pot ser la comunicació entre persones que utilitzen la llengua de signes i les que no. En aquest projecte es presenta un mètode de reconeixement de gestos de la mà a temps real utilitzant el sensor Kinect per Microsoft Xbox, implementat en un entorn Linux (Ubuntu) amb llenguatge de programació Python i utilitzant la llibreria de visió artifical OpenCV per a processar les dades sobre un ordinador portàtil convencional. Gràcies a la capacitat del sensor Kinect de capturar dades de profunditat d’una escena es poden determinar les posicions i trajectòries dels objectes en 3 dimensions, el que implica poder realitzar una anàlisi complerta a temps real d’una imatge o d’una seqüencia d’imatges. El procediment de reconeixement que es planteja es basa en la segmentació de la imatge per poder treballar únicament amb la mà, en la detecció dels contorns, per després obtenir l’envolupant convexa i els defectes convexos, que finalment han de servir per determinar el nombre de dits i concloure en la interpretació del gest; el resultat final és la transcripció del seu significat en una finestra que serveix d’interfície amb l’interlocutor. L’aplicació permet reconèixer els números del 0 al 5, ja que s’analitza únicament una mà, alguns gestos populars i algunes de les lletres de l’alfabet dactilològic de la llengua de signes catalana. El projecte és doncs, la porta d’entrada al camp del reconeixement de gestos i la base d’un futur sistema de reconeixement de la llengua de signes capaç de transcriure tant els signes dinàmics com l’alfabet dactilològic.

Planar homography: accuracy analysis and applications

Projective homography sits at the heart of many problems in image registration. In addition to many methods for estimating the homography parameters (R.I. Hartley and A. Zisserman, 2000), analytical expressions to assess the accuracy of the transformation parameters have been proposed (A. Criminisi et al., 1999). We show that these expressions provide less accurate bounds than those based on the earlier results of Weng et al. (1989). The discrepancy becomes more critical in applications involving the integration of frame-to-frame homographies and their uncertainties, as in the reconstruction of terrain mosaics and the camera trajectory from flyover imagery. We demonstrate these issues through selected examples

Trinocular System for 3D motion and Dense Stucture Estimation

The relief of the seafloor is an important source of data for many scientists. In this paper we present an optical system to deal with underwater 3D reconstruction. This system is formed by three cameras that take images synchronously in a constant frame rate scheme. We use the images taken by these cameras to compute dense 3D reconstructions. We use Bundle Adjustment to estimate the motion ofthe trinocular rig. Given the path followed by the system, we get a dense map of the observed scene by registering the different dense local reconstructions in a unique and bigger one

Small scale underwater change detection

In this paper, we present a method to deal with the constraints of the underwater medium for finding changes between sequences of underwater images. One of the main problems of underwater medium for automatically detecting changes is the low altitude of the camera when taking pictures. This emphasise the parallax effect between the images as they are not taken exactly at the same position. In order to solve this problem, we are geometrically registering the images together taking into account the relief of the scene

Soil infiltration based on bp neural network and grey relational analysis

Soil infiltration is a key link of the natural water cycle process. Studies on soil permeability are conducive for water resources assessment and estimation, runoff regulation and management, soil erosion modeling, nonpoint and point source pollution of farmland, among other aspects. The unequal influence of rainfall duration, rainfall intensity, antecedent soil moisture, vegetation cover, vegetation type, and slope gradient on soil cumulative infiltration was studied under simulated rainfall and different underlying surfaces. We established a six factor-model of soil cumulative infiltration by the improved back propagation (BP)-based artificial neural network algorithm with a momentum term and self-adjusting learning rate. Compared to the multiple nonlinear regression method, the stability and accuracy of the improved BP algorithm was better. Based on the improved BP model, the sensitive index of these six factors on soil cumulative infiltration was investigated. Secondly, the grey relational analysis method was used to individually study grey correlations among these six factors and soil cumulative infiltration. The results of the two methods were very similar. Rainfall duration was the most influential factor, followed by vegetation cover, vegetation type, rainfall intensity and antecedent soil moisture. The effect of slope gradient on soil cumulative infiltration was not significant.

Artificial neural networks applied for soil class prediction in mountainous landscape of the Serra do Mar¹

Soil information is needed for managing the agricultural environment. The aim of this study was to apply artificial neural networks (ANNs) for the prediction of soil classes using orbital remote sensing products, terrain attributes derived from a digital elevation model and local geology information as data sources. This approach to digital soil mapping was evaluated in an area with a high degree of lithologic diversity in the Serra do Mar. The neural network simulator used in this study was JavaNNS and the backpropagation learning algorithm. For soil class prediction, different combinations of the selected discriminant variables were tested: elevation, declivity, aspect, curvature, curvature plan, curvature profile, topographic index, solar radiation, LS topographic factor, local geology information, and clay mineral indices, iron oxides and the normalized difference vegetation index (NDVI) derived from an image of a Landsat-7 Enhanced Thematic Mapper Plus (ETM+) sensor. With the tested sets, best results were obtained when all discriminant variables were associated with geological information (overall accuracy 93.2 - 95.6 %, Kappa index 0.924 - 0.951, for set 13). Excluding the variable profile curvature (set 12), overall accuracy ranged from 93.9 to 95.4 % and the Kappa index from 0.932 to 0.948. The maps based on the neural network classifier were consistent and similar to conventional soil maps drawn for the study area, although with more spatial details. The results show the potential of ANNs for soil class prediction in mountainous areas with lithological diversity.

Data-driven clustering : new methods and applications

Abstract : This work is concerned with the development and application of novel unsupervised learning methods, having in mind two target applications: the analysis of forensic case data and the classification of remote sensing images. First, a method based on a symbolic optimization of the inter-sample distance measure is proposed to improve the flexibility of spectral clustering algorithms, and applied to the problem of forensic case data. This distance is optimized using a loss function related to the preservation of neighborhood structure between the input space and the space of principal components, and solutions are found using genetic programming. Results are compared to a variety of state-of--the-art clustering algorithms. Subsequently, a new large-scale clustering method based on a joint optimization of feature extraction and classification is proposed and applied to various databases, including two hyperspectral remote sensing images. The algorithm makes uses of a functional model (e.g., a neural network) for clustering which is trained by stochastic gradient descent. Results indicate that such a technique can easily scale to huge databases, can avoid the so-called out-of-sample problem, and can compete with or even outperform existing clustering algorithms on both artificial data and real remote sensing images. This is verified on small databases as well as very large problems. Résumé : Ce travail de recherche porte sur le développement et l'application de méthodes d'apprentissage dites non supervisées. Les applications visées par ces méthodes sont l'analyse de données forensiques et la classification d'images hyperspectrales en télédétection. Dans un premier temps, une méthodologie de classification non supervisée fondée sur l'optimisation symbolique d'une mesure de distance inter-échantillons est proposée. Cette mesure est obtenue en optimisant une fonction de coût reliée à la préservation de la structure de voisinage d'un point entre l'espace des variables initiales et l'espace des composantes principales. Cette méthode est appliquée à l'analyse de données forensiques et comparée à un éventail de méthodes déjà existantes. En second lieu, une méthode fondée sur une optimisation conjointe des tâches de sélection de variables et de classification est implémentée dans un réseau de neurones et appliquée à diverses bases de données, dont deux images hyperspectrales. Le réseau de neurones est entraîné à l'aide d'un algorithme de gradient stochastique, ce qui rend cette technique applicable à des images de très haute résolution. Les résultats de l'application de cette dernière montrent que l'utilisation d'une telle technique permet de classifier de très grandes bases de données sans difficulté et donne des résultats avantageusement comparables aux méthodes existantes.

Iowa Communications Network - Fiscal Year 2012 Annual Report

The Iowa Communications Network (ICN) is the country’s premier distance learning and state government Network, committed to providing Iowans with convenient, equal access to education, government and healthcare. The Network makes it possible for Iowans, physically separated by location, to interact in an efficient, creative, and cost-effective manner. ICN provides high-speed Internet, data, video conferencing, and voice (phone) services to authorized users, under Code of Iowa, which includes: K-12 schools, higher education, hospitals, state and federal government, National Guard armories, and libraries.

Vulnerabilität und psychische Erkrankung

Vulnerability and psychic illness Based on a sample of 1701 college and university students from four different sites in Switzerland, the U.S., and Argentina, this study investigated the interrelationships between insufficient coping skills under chronic stress and impaired general health. We sought to develop standardised means for "early" identification of students at risk of mental health problems, as these students may benefit from "early" interventions before psychiatric symptoms develop and reach clinically relevant thresholds. All students completed two self-report questionnaires: the Coping Strategies Inventory "COPE" and the Zurich Health Questionnaire "ZHQ", with the latter assessing "regular exercises", "consumption behavior", "impaired physical health", "psychosomatic disturbances", and "impaired mental health". This data was subjected to structure analyses based on neural network approaches, using the different study sites' data subsets as independent "learning" and "test" samples. We found two highly stable COPE scales that quantified basic coping behaviour in terms of "activity-passivity" and "defeatism-resilience". The excellent reproducibility across study sites suggested that the new scales characterise socioculturally independent personality traits. Correlation analyses for external validation revealed a close relationship between high scores on the defeatism scale and impaired physical and mental health, hence underlining the scales' clinical relevance. Our results suggested in particular: (1.) the proposed method to be a powerful screening tool for early detection and prevention of psychiatric disorders; (2.) physical activity like regular exercises to play a critical role not only in preventing health problems but also in contributing to early intervention programs.

Mobile Robot Local Predictive Control under Perception Constraints

This research extends a previously developed work concerning about the use of local model predictive control in mobile robots. Hence, experimental results are presented as a way to improve the methodology by considering aspects as trajectory accuracy and time performance. In this sense, the cost function and the prediction horizon are important aspects to be considered. The platformused is a differential driven robot with a free rotating wheel. The aim of the present work is to test the control method by measuring trajectory tracking accuracy and time performance. Moreover, strategies for the integration with perception system and path planning are also introduced. In this sense, monocular image data provide an occupancy grid where safety trajectories are computed by using goal attraction potential fields

A knowledge based signal processing approach to tonic identification in indian classical music

In this paper, we describe several techniques for detecting tonic pitch value in Indian classical music. In Indian music, the raga is the basic melodic framework and it is built on the tonic. Tonic detection is therefore fundamental for any melodic analysis in Indian classical music. This workexplores detection of tonic by processing the pitch histograms of Indian classic music. Processing of pitch histograms using group delay functions and its ability to amplify certain traits of Indian music in the pitch histogram, is discussed. Three different strategies to detect tonic, namely, the concert method, the template matching and segmented histogram method are proposed. The concert method exploits the fact that the tonic is constant over a piece/concert.templatematchingmethod and segmented histogrammethodsuse the properties: (i) the tonic is always present in the background, (ii) some notes are less inflected and dominant, to detect the tonic of individual pieces. All the three methods yield good results for Carnatic music (90−100% accuracy), while for Hindustanimusic, the templatemethod works best, provided the v¯adi samv¯adi notes for a given piece are known (85%).