Ricardo Veiga

Follower

Following

Public Views

James Elkins

School of the Art Institute of Chicago

Christine Hendon (Fleming)

Columbia University

daniel stoekl

Ecole Pratique des Hautes Etudes

Maria Papademetriou

University College London

Mario E Giardini

University of Strathclyde, Glasgow

Tim Young

Auckland University of Technology

Vassilis M Papadakis

Foundation for Research and Technology - Hellas

Florence ReSeT

Università degli Studi di Firenze (University of Florence)

Prithwiraj Jha

Raiganj Surendranath Mahavidyalaya

Sana Ullah

University of Education Lahore

Interests

Uploads

Papers by Ricardo Veiga

A Route Planner Supported on Recommender Systems Suggestions

Proceedings of the 8th International Conference on Software Development and Technologies for Enhancing Accessibility and Fighting Info-exclusion

A cultural heritage planner has the purpose of assisting users in their visits around cultural he... more A cultural heritage planner has the purpose of assisting users in their visits around cultural heritage places. The planners can address multiple aspects of a visit, such as users' preferences when choosing the objects to be visited, routes between those objects, visit scheduling, or user's limitations and impairments. This paper addresses the combination of a Recommender System (RS) with a route planner. The RS takes information from the users actions, acquired from the operation of a mobile application, to compute estimated preferences relative to objects / points of interest (PoI). Then, taking into account the users' preferred PoI, the preferences returned by the RS and a certain time window, a route planner produces solutions bearing in mind three objectives to be maximized: the number of PoI visited, the estimated preference of the PoI, and the number of PoI visited from a set of fixed ones. The contribution of this work is the combination of a RS with a route optimizer, as a relatively simple computational process to enhance the visit to cultural places, including buildings (e.g., museums), cities or regions.

Paragens de autocarro inteligentes e inclusivas

Apresentam-se diferentes conceitos que determinam uma paragem inteligente e inclusiva, criando-se... more Apresentam-se diferentes conceitos que determinam uma paragem inteligente e inclusiva, criando-se assim uma paragem de autocarros inovadora desde à geração da sua própria energia, tornando-a autossuficiente e sustentável, à integração na rede de autocarros para comunicação da quantidade de utilizadores à espera, até à criação de um ecrã interativo que se adapta às necessidades de qualquer utilizador através de uma inovadora framework desenvolvida no âmbito do projeto ACCES4ALL.info:eu-repo/semantics/publishedVersio

Download

Autonomous Temporal Pseudo-Labeling for Fish Detection

Applied Sciences

The first major step in training an object detection model to different classes from the availabl... more The first major step in training an object detection model to different classes from the available datasets is the gathering of meaningful and properly annotated data. This recurring task will determine the length of any project, and, more importantly, the quality of the resulting models. This obstacle is amplified when the data available for the new classes are scarce or incompatible, as in the case of fish detection in the open sea. This issue was tackled using a mixed and reversed approach: a network is initiated with a noisy dataset of the same species as our classes (fish), although in different scenarios and conditions (fish from Australian marine fauna), and we gathered the target footage (fish from Portuguese marine fauna; Atlantic Ocean) for the application without annotations. Using the temporal information of the detected objects and augmented techniques during later training, it was possible to generate highly accurate labels from our targeted footage. Furthermore, the d...

Download

AR Contents Superimposition on Walls and Persons

Lecture Notes in Computer Science, 2019

When it comes to visitors’ experiences at museums and heritage attractions, objects speak for the... more When it comes to visitors’ experiences at museums and heritage attractions, objects speak for themselves. With the aim of enhancing a traditional museum visit, a mobile Augmented Reality (AR) framework was developed during the M5SAR project. This paper presents two modules, the wall and human shape segmentation with AR content superimposition. The first, wall segmentation, is achieved by using a BRISK descriptor and geometric information, having the wall delimited, and the AR contents superposed over the detected wall contours. The second module, person segmentation, is achieved by using an OpenPose model, which computes the body joints. These joints are then combined with volumes to achieve AR clothes content superimposition. This paper shows the usage of both methods in a real museum environment.

Efficient Small-Scale Network for Room Layout Estimation

Universal Access in Human-Computer Interaction. Applications and Practice, 2020

Retrieving the layout of different cluttered indoor scenes from monocular images is a challenging... more Retrieving the layout of different cluttered indoor scenes from monocular images is a challenging task, using a smaller deep neural network than the existing proposals. Previous geometric solutions are prone to failure in the presence of cluttered scenes because they depend strongly on hand-engineering features and the expectation of the possibility of the vanishing points’ calculation. With the growth of neural networks, the geometric methods were either replaced or fused within the emerging area of deep learning. The more recent solutions rely on dense neural networks with additional adjustments, either by the calculation of the vanishing points, position based, or by layout ranking. All these methods presented valid solutions to this challenge with the flaw of being computationally demanding. Here, we present a more lightweight solution, running the segmentation on a smaller neural network and introducing a discriminative classifier for the posterior layout ranking and optimization. Our proposed method is evaluated by two standard dataset benchmarks, achieving near state of the art results even with a fraction of the required parameters than the available state of the art methods.

Multisensorial Portable Device for Augmented Reality Experiences in Museums

International Journal of Education, 2018

This paper presents a portable device capable of enhancing the augmented reality (AR) experience ... more This paper presents a portable device capable of enhancing the augmented reality (AR) experience to the full five senses through the stimulus of touch, taste, and smell. While most of the existing solutions for this type of devices lack portability or fail to explore all the five senses at once, in this work we introduce a new portable device that adapts to the users’ smartphone or tablet to provide a full five senses experience. This is part of a mobile five senses augmented reality system for Museums (M5SAR) project, which aims at developing an AR system to be a guide in cultural and historical events and museums, complementing or replacing the traditional orientation given by a guide, by directional signs or maps, while enhancing the users’ experience adding by new senses to the museums’ objects. The proposed device communicates via Bluetooth with an App (out of the scope of this paper) and is responsible for generating the stimuli that reproduces three senses: touch, taste, and ...

Download

MIRAR: Mobile Image Recognition Based Augmented Reality Framework

The application of the most recent technologies is fundamental to achieve sustainability in touri... more The application of the most recent technologies is fundamental to achieve sustainability in tourism, as well as in other economic sectors. This paper presents the initial architecture of MIRAR, a Mobile Image Recognition based Augmented Reality framework, which aims the development of Augmented Reality applications for mobile devices. The MIRAR framework allows the development of a system which uses mobile devices to interact with museum’s objects. By using the mobile device’s camera the system recognises and tracks on-the-fly, on the client side (mobile), museum’s objects. In addition, the initial discussion on how the MIRAR framework detects environments allowing the superimposition of information over those is presented.

Augmented Reality Indoor Environment Detection: Proof-of-Concept

The conventional museum experience offers the visitors glimpses of the past with the narrative li... more The conventional museum experience offers the visitors glimpses of the past with the narrative limited to the static art that garnishes it. Through technology we already can mix the past with the future, immersing the visitors in a true dynamic journey across the same walls that guard our history. One of these technologies is the Augmented Reality, which aims to enhance our surroundings into a new era of creativity and discovery. This paper presents the proof-of-concept of an indoor portable environment pose estimation module (PEPE) present inside M5SAR, a project that aims to develop a five senses augmented reality system for museums. The current state of development of this module shows that is already achievable real-world wall(s) detection and a new environment superimposition over the detection, i.e., it is now possible to have a dynamic museum experience with the ability of transforming rooms into historic live stages.

Download

Mobile Human Shape Superimposition: An Initial Approach using OpenPose

When it comes to visitors at museums and heritage attractions objects speak for themselves. Never... more When it comes to visitors at museums and heritage attractions objects speak for themselves. Nevertheless, it is important to give those visitors the best experience possible as, this will lead to an increase in the visits number, enhance the perception and value of an organisation, and boost the sales. With the aim of enhancing a traditional museum visit, a mobile Augmented Reality (AR) framework is being developed as part of the Mobile Five Senses Augmented Reality (M5SAR) system for museums project. This paper presents an initial approach to human shape detection and AR content superimposition, achieved by combining information of human body joints with shape segmentation or texture overlapping. The OpenPose model was used to compute the body joints and the GrabCut algorithm for person segmentation, allowing to fit clothes segments to persons moving in real environments. The initial results and proof-of-concept are shown.

Download

A Portable Device for Five Sense Augmented Reality Experiences in Museums

Augmented reality (AR) nowadays is focused in two senses, sight and hearing. The work presented h... more Augmented reality (AR) nowadays is focused in two senses, sight and hearing. The work presented here is part of the Mobile Five Senses Augmented Reality system for Museums (M5SAR) project, which has the goal of developing an AR system to be a guide in cultural and historical events and museums, complementing or replacing traditional guides, directional signs or maps, while enhancing the user’s experience by adding multisensorial information to multiple museum objects. The existing solutions for this type of devices either lack portability or fail to implement all the human senses at the same time. This paper presents a new device capable of extending augmented reality experiences to all five human senses, through the use of a portable device that can reproduce stimulus of touch, taste and smell. The proposed apparatus is meant to be paired with a mobile application that controls which sensorial interface is activated and when, relaying that information to the portable device. The ap...

Download

Mobile Augmented Reality Framework - MIRAR

Universal Access in Human-Computer Interaction. Virtual, Augmented, and Intelligent Environments, 2018

The increasing immersion of technology on our daily lives demands for additional investments in v... more The increasing immersion of technology on our daily lives demands for additional investments in various areas, including, as in the present case, the enhancement of museums’ experiences. One of the technologies that improves our relationship with everything that surrounds us is Augmented Reality. This paper presents the architecture of MIRAR, a Mobile Image Recognition based Augmented Reality framework. The MIRAR framework allows the development of a system that uses mobile devices to interact with the museum’s environment, by: (a) recognizing and tracking on-the-fly, on the client side (mobile), museum’s objects, (b) detecting and recognizing where the walls and respective boundaries are localized, as well as (c) do person detection and segmentation. These objects, wall and person segmentation will allow the projection of different contents (text, images, videos, clothes, etc.). Promising results are presented in these topics, nevertheless, some of them are still in a development stage.