Paulo Martins

Obstacle Detection using Stereo Imaging to Assist the Navigation of Visually Impaired People

Abstract Assistive technology enables people to achieve independence when performing daily tasks and it enhances their overall quality of life. Visual information is the basis for most navigational tasks, so visually impaired individuals are at disadvantage due to the lack of sufficient information about their surrounding environment. With recent advances in inclusive technology it is possible to extend the support given to people with visual disabilities in terms of their mobility. In this context we propose and describe the Blavigator project, whose global objective is to assist visually impaired people in their navigation on indoor and outdoor environments. This paper is focused mainly on the Computer Vision module of the Blavigator prototype. We propose an object collision detection algorithm based on disparity images. The proposed algorithm uses a 2D Ensemble Empirical Mode Decomposition image optimization algorithm and a two layer disparity image segmentation to detect nearby objects.

Children as Active Partners: Strategies for Collaboration in Spatial Tasks through Virtual Worlds

This paper, referring to a work in progress, describes functional elements of the user interface of a Virtual World that may provide an important contribution to the process by which primary teachers and pupils collaborate in negotiating spatial configurations of educational spaces (classroom, playground, set for a theatre play, etc.). We have observed this process and some of its inherent difficulties and identified requirements or the functional elements of the interface. Finally, we reflect about factors impacting childrens feelings of lack of authorship and ownership of spatial configurations resulting from collaboration and how a computer system may help in this regard. This Virtual World is therefore configured to be applied in educational contexts where curricular models reflect the new childhood culture where children have an active role in the spaces where they spend most of their time, as schools that adopt the Portuguese Modern School Movement pedagogical model.

Integration of Technologies in Higher Education: Teachers’ Needs and Expectations at UTAD

Experiences with online learning in higher education are increasing in number. This is due to advancements in technology, technological savviness of teachers and students, evolution of teaching practices, and changes in student expectations. That is why understanding learners’ and teachers’ needs, expectations, and perceptions of their proficiency and use of information and communication technologies (ICTs) is critical to the success of the integration of technologies in higher education. The purpose of this paper is to reflect on teachers’ needs and expectations about ICT adoption in higher education, based on the results of a questionnaire, applied in a Portuguese university. The questionnaire explores what motivates teachers to use ICT tools in the context of teaching in higher education. It also intended to reveal which tools are most used from the ones available, as well as the needs and requirements that are not covered by the existing tools and services provided. The results allowed to analyze the usefulness of the measures implemented for teachers and consider new ones, more appropriate to the reality in permanent change by the constant evolution of the technologies used in the pedagogical practices.

Iterative Ontology Alignment Debugging Using a Scenario- and Strategy-Driven Approach

The automatic matching of entities between information repositories is essential for aligning and ontology mediation processes, but there is great ambiguity when adopting it. Data integration between repositories demands great quality of ontology alignments, and as such ambiguous correspondences must be identified and corrected beforehand. Debugging is even more relevant if the process is systematic and complete, thus allowing its formalisation and implementation and promoting its acceptance. In this paper we address the analysis and systematization of the ontology alignment debugging process, proposing the characterization of the ontology matching scenarios through ten dimensions. The resulting scenarios are categorized as Simple and Composed depending on the associated actions taken for solving the ambiguity. We suggest evolving the alignment process into an iterative matching-debugging process, where the resulting ambiguous scenarios and correction strategies are fed into the matching algorithms for supporting the resolution of the alignment problems.