Estimación del movimiento de objetos en secuencias de imágenes de intensidad y profundidad

Máster Universitario en Sistemas Inteligentes y Aplicaciones Numéricas en Ingeniería (SIANI)

Desarrollo de una aplicación web para la gestión de rutas en sistemas georreferenciados

[ES] El objetivo que se pretendía alcanzar con la realización de este proyecto era desarrollar una aplicación web 2.0 capaz de gestionar rutas independientemente de su tipología u otro tipo de características. El usuario de la aplicación construida tras analizar este proyecto puede crear rutas y modificarlas. Para su visualización se ha optado por un entorno 3D que muestra el globo terráqueo de manera realista: Google Earth en su versión como complemento para navegadores. La variedad de rutas creadas puede ser muy amplia, como por ejemplo: las etapas de la Vuelta Ciclista a España, la travesía de una competición náutica, el recorrido que siguió Colón en su primer viaje a América o los caminos reales de Canarias. Las rutas se crean desplazando el ratón y haciendo clic sobre la superficie del globo terráqueo. La aplicación muestra una línea que pasa por los puntos indicados con la representación de la ruta. Para las rutas creadas el usuario puede añadir una serie de elementos multimedia que permitan obtener un mayor conocimiento de dichas rutas. La aplicación permite añadir fotos, vídeos web, documentos y elementos 3D. Cuando el usuario seleccione mostrar una ruta creada previamente a la que le ha añadido alguno de los elementos indicados previamente, éste se visualizará en el navegador. Además de la posibilidad de gestionar rutas, el usuario también puede gestionar sitios de su interés de manera sencilla. El usuario puede incorporar localizaciones de diversa índole a su biblioteca de elementos para disponer de una mejor accesibilidad de sus lugares predilectos. Los sitios de interés creados aparecen en el globo como un icono junto con su nombre.

A video database for facial behavior understanding

[EN]The use of new technologies in order to step up the inter- action between humans and machines is the main proof that faces are important in videos. Therefore we suggest a novel Face Video Database for development, testing and veri cation of algorithms related to face- based applications and to facial recognition applications. In addition of facial expression videos, the database includes body videos. The videos are taken by three di erent cameras, working in real time, without vary- ing illumination conditions.

Teaching and learning english phonetics and phonology in the EHEA through design and creation of audiovisual material at the ULPGC

[ES]In this paper we describe the procedure followed in the design and recording of a set of videos for teaching and learning ‘English phonetics and phonology’, a second-year undergraduate course at Universidad de Las Palmas de Gran Canaria. The student’s L1 is Spanish. Two different types of technological support were used: screencast and Powerpoint® presentations. The traditional whiteboard together with the lecturer’s presence also contributed both to the integrated learning of certain acoustic/articulatory aspects of the course contents and to the use of specific software for speech analysis. This video production owns the advantage of being an interactive and autonomous tool which favours a continuous learning process on the student’s side.

Exploring the use of local descriptors for fish recognition in LifeCLEF 2015

[EN]This paper summarizes the proposal made by the SIANI team for the LifeCLEF 2015 Fish task. The approach makes use of standard detection techniques, applying a multiclass SVM based classifier on large enough Regions Of Interest (ROIs) automatically extracted from the provided video frames. The selection of the detection and classification modules is based on the best performance achieved for the validation dataset consisting of 20 annotated videos. For that dataset, the best classification achieved for an ideal detection module, reaches an accuracy around 40%.

Study accompaniment with E-Assessments

[EN]In this paper we present our concept of a virtual classroom for mathematics lectures in the study beginning phase. It describes the two main elements the course uses within our Learning Management System. The first element is the dynamic e-tests-method and the second interactive teaching videos. The tests are already in active use. Therefore, initial experience and feedback are described. The videos are in the prototype status. Therefore here only the evaluation approaches are described.

Quality of experience in skype video calls

Skype is one of the well-known applications that has guided the evolution of real-time video streaming and has become one of the most used software in everyday life. It provides VoIP audio/video calls as well as messaging chat and file transfer. Many versions are available covering all the principal operating systems like Windows, Macintosh and Linux but also mobile systems. Voice quality decreed Skype success since its birth in 2003 and peer-to-peer architecture has allowed worldwide diffusion. After video call introduction in 2006 Skype became a complete solution to communicate between two or more people. As a primarily video conferencing application, Skype assumes certain characteristics of the delivered video to optimize its perceived quality. However in the last years, and with the recent release of SkypeKit1, many new Skype video-enabled devices came out especially in the mobile world. This forced a change to the traditional recording, streaming and receiving settings allowing for a wide range of network and content dynamics. Video calls are not anymore based on static ‘chatting’ but mobile devices have opened new possibilities and can be used in several scenarios. For instance, lecture streaming or one-to-one mobile video conferences exhibit more dynamics as both caller and callee might be on move. Most of these cases are different from “head&shoulder” only content. Therefore, Skype needs to optimize its video streaming engine to cover more video types. Heterogeneous connections require different behaviors and solutions and Skype must face with this variety to maintain a certain quality independently from connection used. Part of the present work will be focused on analyzing Skype behavior depending on video content. Since Skype protocol is proprietary most of the studies so far have tried to characterize its traffic and to reverse engineer its protocol. However, questions related to the behavior of Skype, especially on quality as perceived by users, remain unanswered. We will study Skype video codecs capabilities and video quality assessment. Another motivation of our work is the design of a mechanism that estimates the perceived cost of network conditions on Skype video delivery. To this extent we will try to assess in an objective way the impact of network impairments on the perceived quality of a Skype video call. Traditional video streaming schemes lack the necessary flexibility and adaptivity that Skype tries to achieve at the edge of a network. Our contribution will lye on a testbed and consequent objective video quality analysis that we will carry out on input videos. We will stream raw video files with Skype via an impaired channel and then we will record it at the receiver side to analyze with objective quality of experience metrics.

"Romanzo criminale - la serie". Analisi del sottotitolaggio spagnolo amatoriale.

This dissertation focuses on the phenomenon of amateur subtitling, known as fansubbing. Although this phenomenon began in the late ‘80s, in recent years amateur subtitling has spread worldwide, thanks to both Internet and fan communities, also known as fandoms. At first, amateur subtitling was mainly centred on the translation of Japanese cartoons, but nowadays fandoms also tend to subtitle other kinds of audiovisual products, such as American TV series. Thanks to fansubbing, which is created by fans for other fans, fandoms claim that they would prefer to have subtitled rather than dubbed versions of audiovisual products, which is the norm in Italy and Spain. The dissertation provides a linguistic analysis of the fansubbing in Spanish of the Italian TV series Romanzo Criminale. The purpose of this dissertation is to analyse fansubbing from the linguistic point of view, as well as from the point of view of the translation. Furthermore, it aims to evaluate to what extent this translation can be compared to professional subtitling. The first chapter offers an introduction to the TV series and provides an overview of the main events and characters. The second chapter deals with an analysis of the strategies that fansubbers use to translate cultural elements from Italian into Spanish. The third chapter focuses on linguistic mistakes due to calques and linguistic interference between Italian and Spanish. The fourth chapter provides an analysis of some translation errors which occurred during the decoding of the original text. The aim is to understand if this kind of mistake might jeopardize the comprehension of the original message.

Reproducibility and validity of video screen measurements of gait in children with spastic cerebral palsy

PURPOSE: To determine the reproducibility and validity of video screen measurement (VSM) of sagittal plane joint angles during gait. METHODS: 17 children with spastic cerebral palsy walked on a 10m walkway. Videos were recorded and 3d-instrumented gait analysis was performed. Two investigators measured six sagittal joint/segment angles (shank, ankle, knee, hip, pelvis, and trunk) using a custom-made software package. The intra- and interrater reproducibility were expressed by the intraclass correlation coefficient (ICC), standard error of measurements (SEM) and smallest detectable difference (SDD). The agreement between VSM and 3d joint angles was illustrated by Bland-Altman plots and limits of agreement (LoA). RESULTS: Regarding the intrarater reproducibility of VSM, the ICC ranged from 0.99 (shank) to 0.58 (trunk), the SEM from 0.81 degrees (shank) to 5.97 degrees (trunk) and the SDD from 1.80 degrees (shank) to 16.55 degrees (trunk). Regarding the interrater reproducibility, the ICC ranged from 0.99 (shank) to 0.48 (trunk), the SEM from 0.70 degrees (shank) to 6.78 degrees (trunk) and the SDD from 1.95 degrees (shank) to 18.8 degrees (trunk). The LoA between VSM and 3d data ranged from 0.4+/-13.4 degrees (knee extension stance) to 12.0+/-14.6 degrees (ankle dorsiflexion swing). CONCLUSION: When performed by the same observer, VSM mostly allows the detection of relevant changes after an intervention. However, VSM angles differ from 3d-IGA and do not reflect the real sagittal joint position, probably due to the additional movements in the other planes.

Comprehensive assessment of gesture production: a new test of upper limb apraxia (TULIA)

BACKGROUND: Only few standardized apraxia scales are available and they do not cover all domains and semantic features of gesture production. Therefore, the objective of the present study was to evaluate the reliability and validity of a newly developed test of upper limb apraxia (TULIA), which is comprehensive and still short to administer. METHODS: The TULIA consists of 48 items including imitation and pantomime domain of non-symbolic (meaningless), intransitive (communicative) and transitive (tool related) gestures corresponding to 6 subtests. A 6-point scoring method (0-5) was used (score range 0-240). Performance was assessed by blinded raters based on videos in 133 stroke patients, 84 with left hemisphere damage (LHD) and 49 with right hemisphere damage (RHD), as well as 50 healthy subjects (HS). RESULTS: The clinimetric findings demonstrated mostly good to excellent internal consistency, inter- and intra-rater (test-retest) reliability, both at the level of the six subtests and at individual item level. Criterion validity was evaluated by confirming hypotheses based on the literature. Construct validity was demonstrated by a high correlation (r = 0.82) with the De Renzi-test. CONCLUSION: These results show that the TULIA is both a reliable and valid test to systematically assess gesture production. The test can be easily applied and is therefore useful for both research purposes and clinical practice.

Differential activation of the lateral premotor cortex during action observation

Background Action observation leads to neural activation of the human premotor cortex. This study examined how the level of motor expertise (expert vs. novice) in ballroom dancing and the visual viewpoint (internal vs. external viewpoint) influence this activation within different parts of this area of the brain. Results Sixteen dance experts and 16 novices observed ballroom dance videos from internal or external viewpoints while lying in a functional magnetic resonance imaging scanner. A conjunction analysis of all observation conditions showed that action observation activated distinct networks of premotor, parietal, and cerebellar structures. Experts revealed increased activation in the ventral premotor cortex compared to novices. An internal viewpoint led to higher activation of the dorsal premotor cortex. Conclusions The present results suggest that the ventral and dorsal premotor cortex adopt differential roles during action observation depending on the level of motor expertise and the viewpoint.

Seeing Spaces: An Eye-Tracking Study Of Speech Segmentation

Speech is often a multimodal process, presented audiovisually through a talking face. One area of speech perception influenced by visual speech is speech segmentation, or the process of breaking a stream of speech into individual words. Mitchel and Weiss (2013) demonstrated that a talking face contains specific cues to word boundaries and that subjects can correctly segment a speech stream when given a silent video of a speaker. The current study expanded upon these results, using an eye tracker to identify highly attended facial features of the audiovisual display used in Mitchel and Weiss (2013). In Experiment 1, subjects were found to spend the most time watching the eyes and mouth, with a trend suggesting that the mouth was viewed more than the eyes. Although subjects displayed significant learning of word boundaries, performance was not correlated with gaze duration on any individual feature, nor was performance correlated with a behavioral measure of autistic-like traits. However, trends suggested that as autistic-like traits increased, gaze duration of the mouth increased and gaze duration of the eyes decreased, similar to significant trends seen in autistic populations (Boratston & Blakemore, 2007). In Experiment 2, the same video was modified so that a black bar covered the eyes or mouth. Both videos elicited learning of word boundaries that was equivalent to that seen in the first experiment. Again, no correlations were found between segmentation performance and SRS scores in either condition. These results, taken with those in Experiment, suggest that neither the eyes nor mouth are critical to speech segmentation and that perhaps more global head movements indicate word boundaries (see Graf, Cosatto, Strom, & Huang, 2002). Future work will elucidate the contribution of individual features relative to global head movements, as well as extend these results to additional types of speech tasks.

The Effect of Chronic Estrogen Administration on Same-Sex Social Behavior and Central Oxytocin Levels in Prairie Voles (Microtus ochrogaster)

The purpose of our study is to investigate the effects of chronic estrogen administration on same-sex interactions during exposure to a social stressor and on oxytocin (OT) levels in prairie voles (Microtus orchrogaster). Estrogen and OT are two hormones known to be involved with social behavior and stress. Estogen is involved in the transcription of OT and its receptor. Because of this, it is generally thought that estrogen upregulates OT, but evidence to support this assumption is weak. While estrogen has been shown to either increase or decrease stress, OT has been shown to have stress-dampening properties. The goal of our experiment is to determine how estrogen affects OT levels as well as behavior in a social stressor in the voles. In addition, estrogen is required for many opposite-sex interactions, but little is known about its influence on same-sex interactions. We hypothesized that prairie voles receiving chronic estrogen injections would show an increase in OT levels in the brain and alter behavior in response to a social stressor called the resident-intruder test. To test this hypothesis, 73 female prairie voles were ovariectomized and then administered daily injections of estrogen (0.05 ¿g in peanut oil, s.c.) or vehicle for 8 days. On the final day of injections, half of the voles were given the resident-intruder test, a stressful 5 min interaction with a same-sex stranger. Their behavior was video-recorded. These animals were then sacrificed either 10 minutes or 60 minutes after the conclusion of the test. Half of the animals (no stress group) were not given the resident-intruder test. After sacrifice, trunk blood and brains were collected from the animals. Videos of the resident-intruder tests were analyzed for pro-social and aggressive behavior. Density of OT-activated neurons in the brain was measured via pixel count using immunohistochemistry. No differences were found in pro-social behavior (focal sniffing, p = 0.242; focal initiated sniffing p = 0.142; focal initiated sniffing/focal sniffing, p = 0.884) or aggressive behavior (total time fighting, p= 0.763; number of fights, p= 0.148; number of strikes, p = 0.714). No differences were found in activation of OT neurons in the brain, neither in the anterior paraventricular nucleus (PVN) (pixel count p= 0.358; % area that contains pixelated neurons p = 0.443) nor in the medial PVN (pixel count p= 0.999; % area that contains pixelated neurons p = 0.916). These results suggest that estrogen most likely does not directly upregulate OT and that estrogen does not alter behavior in stressful social interactions with a same-sex stranger. Estrogen may prepare the animal to respond to OT, instead of increasing the production of the peptide itself, suggesting that we need to shift the framework in which we consider estrogen and OT interactions.

"Army of One" to "Army Strong" : visual media and U.S. Army recruitment during Bush"s "War on Terror"

From Bush’s September 20, 2001 “War on Terror” speech to Congress to President-Elect Barack Obama’s acceptance speech on November 4, 2008, the U.S. Army produced visual recruitment material that addressed the concerns of falling enlistment numbers—due to the prolonged and difficult war in Iraq—with quickly-evolving and compelling rhetorical appeals: from the introduction of an “Army of One” (2001) to “Army Strong” (2006); from messages focused on education and individual identity to high-energy adventure and simulated combat scenarios, distributed through everything from printed posters and music videos to first-person tactical-shooter video games. These highly polished, professional visual appeals introduced to the American public during a time of an unpopular war fought by volunteers provide rich subject matter for research and analysis. This dissertation takes a multidisciplinary approach to the visual media utilized as part of the Army’s recruitment efforts during the War on Terror, focusing on American myths—as defined by Barthes—and how these myths are both revealed and reinforced through design across media platforms. Placing each selection in its historical context, this dissertation analyzes how printed materials changed as the War on Terror continued. It examines the television ad that introduced “Army Strong” to the American public, considering how the combination of moving image, text, and music structure the message and the way we receive it. This dissertation also analyzes the video game America’s Army, focusing on how the interaction of the human player and the computer-generated player combine to enhance the persuasive qualities of the recruitment message. Each chapter discusses how the design of the particular medium facilitates engagement/interactivity of the viewer. The conclusion considers what recruitment material produced during this time period suggests about the persuasive strategies of different media and how they create distinct relationships with their spectators. It also addresses how theoretical frameworks and critical concepts used by a variety of disciplines can be combined to analyze recruitment media utilizing a Selber inspired three literacy framework (functional, critical, rhetorical) and how this framework can contribute to the multimodal classroom by allowing instructors and students to do a comparative analysis of multiple forms of visual media with similar content.

THE EFFECTS OF WEB-BASED TECHNOLOGICAL RESOURCES IN A RURAL SCIENCE CLASSROOM

Today’s technology is evolving at an exponential rate. Everyday technology is finding more inroads into our education system. This study seeks to determine if having access to technology, including iPad tablets and a teacher's physical science webpage resources (videos, PowerPoint® presentations, and audio podcasts), assists ninth grade high school students in attaining greater comprehension and improved scientific literacy. Comprehension of the science concepts was measured by comparing current student pretest and post test scores on a teacher-written assessment. The current student post test scores were compared with prior classes’ (2010-2011 and 2009-2010) to determine if there was a difference in outcomes between the technology interventions and traditional instruction. Students entered responses to a technology survey that measured intervention usage and their perception of helpfulness of each intervention. The current year class’ mean composite scores, between the pretest and post test increased by 6.9 points (32.5%). Student composite scores also demonstrated that the interventions were successful in helping a majority of students (64.7%) attain the curriculum goals. The interventions were also successful in increasing student scientific literacy by meeting all of Bloom's cognitive levels that were assessed. When compared with prior 2010-2011 and 2009-2010 classes, the current class received a higher mean post test score indicating a positive effect of the use of technological interventions. The survey showed a majority of students utilized at least some of the technology interventions and perceived them as helpful, especially the videos and PowerPoint® presentations.