António Ramires Fernandes

Path planning for complex 3D multilevel environments

The continuous development of graphics hardware is contributing to the creation of 3D virtual worlds with high level of detail, from models of large urban areas, to complete infrastructures, such as residential buildings, stadiums, industrial settings or archaeological sites, to name just a few. Adding virtual humans or avatars adds an extra touch to the visualization providing an enhanced perception of the spaces, namely adding a sense of scale, and enabling simulations of crowds. Path planning for crowds in a meaningful way is still an open research field, particularly when it involves an unknown polygonal 3D world. Extracting the potential paths for navigation in a non automated fashion is no longer a feasible option due to the dimension and complexity of the virtual environments available nowadays. This implies that we must be able to automatically extract information from the geometry of the unknown virtual world to define potential paths, determine accessibilities, and prepare a navigation structure for real time path planning and path finding. A new image based method is proposed that deals with arbitrarily a priori unknown complex virtual worlds, namely those consisting of multilevel passages (e.g. over and below a bridge). The algorithm is capable of extracting all the information required for the actual navigation of avatars, creating a hierarchical data structure to help both high level path planning and low level path finding decisions. The algorithm is image based, hence it is tessellation independent, i.e. the algorithm does not rely on the underlying polygonal structure of the 3D world. Therefore, the number of polygons does not have a significant impact on the performance, and the topology has no weight on the results.

Accelerated epipolar geometry computation for 3D reconstruction using projective texturing

The process of <i>3D reconstruction,</i> or depth estimation, is a complex one, and many methods often have several parameters that may require fine tunning to adapt to the scene and improve reconstruction results. Usability of these methods is directly related to their response time. Epipolar geometry, a fundamental tool used in 3D reconstruction, is commonly computed on the CPU. We propose to take advantage of the advances of graphic cards, to accelerate this process. Projective texturing will be used to transfer a significant part of the computational load from the CPU into the GPU. The new approach will be illustrated in the context of a previously published work for 3D point reconstruction from a set of static images. Test results show that gains of up to two orders of magnitude in terms of computation times can be achieved, when comparing current CPUs and GPUs. We conclude that this leads to an increase in usability of 3D reconstruction methods.

STAR: Speech Therapy with Augmented Reality for Children with Autism Spectrum Disorders

Graphics based systems of Augmented and Alternative Communication are widely used to promote communication in people with Autism Spectrum Disorders. This study discusses an integration of Augmented Reality in communication interventions, by relating elements of Augmented and Alternative Communication and Applied Behaviour Analysis strategies. An architecture for an Augmented Reality based interactive system to assist interventions is proposed. STAR provides an Augmented Reality tool to assist interventions performed by therapists and support for parents to join in and participate in the child’s intervention. Finally we report on the usage of the Augmented Reality tool in interventions with children with Autism Spectrum Disorders.

0016 Evaluation of the Prevalence of Urinary Incontinence Symptoms in Adolescent Female Soccer Players and their Impact on Quality of Life

Objectives To evaluate the prevalence, reliability and severity of symptoms of urinary incontinence (UI) in adolescent female soccer players and the impact of those symptoms on quality of life. Method The present work is a cross-sectional study of 59 female adolescents divided into a group of athletes, which included 35 adolescent amateur soccer players aged between 12 and 19 years (15.6 ± 2.0), and a control group, which included 24 adolescents aged 11 to 19 years (14.8 ± 2.4) who did not practice any sports. The International Consultation on Incontinence Questionnaire - Short Form (ICIQ-SF), the pad test and King’s Health Questionnaire (KHQ) were used for evaluation. Results The athletes displayed 62.8% positivity the pad test and the ICIQ-SF, whereas the control group exhibited 25% positivity. A medium agreement of 0.45 was found between the applied evaluation scales, as assessed with Cohen’s kappa coefficient. In terms of quality of life (as assessed with the KHQ), the athletes exhibited a score of 35.2 in the General Health domain, 37.3 in the Emotions domain and 26.5 in the Sleep/Energy domain. Conclusions In the present study, a high prevalence of UI symptoms was found in soccer athletes, with moderate reliability between the pad test and the ICIQ-SF; mild UI was found in both groups. The athletes had the highest scores on the General Health, Emotions and Sleep/Energy domains, which are considered to have the highest impact on quality of life.

Assisting Speech Therapy for Autism Spectrum Disorders with an Augmented Reality Application

Graphics based systems of Augmented and Alternative Communication are widely used to promote communication of people with Autism Spectrum Disorders. However, studies indicate the inability of some of these people in understanding the used symbols. This study discusses an integration of Augmented Reality in communication interventions, by relating elements of Augmented and Alternative Communication and Applied Behaviour Analysis strategies. An Augmented Reality based interactive system to support interventions is discussed, and the report of its usage in interventions with children suffering from Autism Spectrum Disorders is presented.

Accessibility and Visually Impaired Users

Internet accessibility for the visually impaired community is still an open issue. Guidelines have been issued by the W3C consortium to help web designers to improve web site accessibility. However several studies show that a significant percentage of web page creators are still ignoring the proposed guidelines. Several tools are now available, general purpose, or web specific, to help visually impaired readers. But is reading a web page enough? Regular sighted users are able to scan a web page for a particular piece of information at high speeds. Shouldn’t visually impaired readers have the same chance? This paper discusses some features already implemented to improve accessibility and presents a user feedback report regarding the AudioBrowser, a talking browser. Based on the user feedback the paper also suggests some avenues for future work in order to make talking browsers and screen readers compatible.

From spatiotemporal curves to reconstructed depth

We present a novel approach for 3D reconstruction based on a set of images taken from a static scene. Our solution is inspired by the spatiotemporal analysis of video sequences. The method is based on a best fitting scheme for spatiotemporal curves that allows us to compute 3D world coordinates of points within the scene. As opposed to a large number of current methods, our technique deals with random camera movements in a transparent way, and even performs better in these cases than with restrained motion such as pure translation. Robustness against occlusion and aliasing is inherent to the method as well.

Community based repository for georeferenced traffic signs

Traffic sign maintenance requires periodic on-site inspection to determine if signs are in good conditions and visible, both day and night. However, periodic inspections are time and cost consuming. Another issue is related to the drivers awareness to the traffic signs on the road. Many factors may potentially contribute to a driver missing a sign, such as the sign being damaged or occluded, or distraction caused by the many gadgets inside the vehicle. We propose a dual purpose community based approach. On the one hand, each driver can use his mobile device to detect, recognize and geolocate traffic signs, contributing to the traffic sign central repository. Detection is performed using cascade classifiers, while a convolutional neural network support the recognition phase. The repository, based on the information received from the clients, can be used to provide reports about sign status, preventing the need for global inspections and providing the information required for more direct and timely inspections. On the other hand, the drivers would have access to the database of traffic signs therefore being able to receive real-time notifications regarding traffic signs such as speed limit signs, school proximity, or road construction signs.

Any object is a PC controller

Computer technology continuously evolves at an incredible pace, with todays machines being barely recognizable when compared to the first computers ever created. Despite this, and in spite of the many advances in human-machine interactions, the main method for interfacing with computers has remained the same for several decades. Tangible User Interfaces (TUI) are an interesting alternative to the classical Graphics User Interfaces (GUI) that dominate the field. This type of interface seeks to bridge the gap between the physical and virtual worlds by binding virtual data to physical objects. This allows users to directly manipulate digital information with more natural and intuitive gestures, simply by interacting with the corresponding objects. This concept provides a wide world of possibilities to create more engaging and immersive interfaces capable of greatly improving user experience. The work herein presented tackles this problem and proposes the creation of a framework, capable of enabling the activation of everyday objects as controllers for diverse applications. The framework should make use of an accessible sensor such as a camera, to detect objects and assign them tasks. Direct manipulation of objects by the users should generate an event. Events should be able to be communicated in a clear way to client applications connected to the system. A demo application is described to demonstrate practical applications for the proposed system.

MARS: Mobile augmented reality script framework

Augmented Reality has been successfully applied in training and maintenance scenarios. Previous work has been commonly targeted at industrial specific purposes, sometimes requiring hardware which is out of budget for small and micro enterprises, let alone the average user. Some systems are mobile based, and while these can be classified as accessible, the realm of application is determined by the authoring companies, the average user can only play the instructions, or scripts, provided by the software provider. We present a framework that provides the user with the ability to write their own scripts packages, upload these packages to mobile devices and play the scripts in an augmented reality setting. Besides requiring only widely available hardware, namely a PC and a mobile device, the framework does not require 3D models of the subject of intervention to define the scripts. Furthermore, this framework aims at being extensible, i.e. it allows new behaviours to be defined so it can theoretically adapt to a wide range of scenarios. In short, we provide an affordable and easy to use augmented reality based framework which is suitable for small and micro enterprises, and even hobbyists.