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 present and describe a wearable system (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 stereo vision. The proposed algorithm uses Peano-Hilbert Ensemble Empirical Mode Decomposition (PHEEMD) for disparity image processing and a two layer disparity image segmentation to detect nearby objects. Using the adaptive ensemble empirical mode decomposition (EEMD) image analysis real time is not achieved, with PH-EEMD results on a fast implementation suitable for real time applications.

Abstract
Computer programming courses in higher education tend to have high rates of academic failure and students struggle, particularly so in the transition from entry-level programming to advanced programming. Some of the reasons given in the literature relate to the type of teaching approach and the strategies used by students and their attitudes towards computer programming. The literature also mentions that educational approaches are not always appropriate to the needs of students and to the development of skills required in the job market. We developed a teaching approach to try to address some of these issues and support students learning computer programming in the transition from entry-level to advanced computer programming: the SimProgramming approach. This approach was introduced at the University of Tros-os-Montes e Alto Douro (Portugal), within the scope of the course " Programming Methodologies III", part of the second curricular year of the programmes of studies in Informatics Engineering and in Information & Communication Technologies. We present in detail the origins of the SimProgramming approach, starting from the first trials that introduced, in two iterations, learning activities based on problem-based learning, and up to the third iteration where the current SimProgramming approach was implemented. We describe the reasoning, design and implementation of these three iterations, to show how the approach evolved. The SimProgramming approach is based in four conceptual foundations: business-like learning environment, self-regulated learning, co-regulated learning and formative assessment. For each of these conceptual foundations, we explain the teaching strategies adopted. In SimProgramming, the learning activity process develops in four phases, and students have specific tasks in each phase. We analyse interview data regarding student perceptions about the SimProgramming approach, and registration grids data on team work dynamics and final assessment of the assignment, noting the impact of SimProgramming in student grades. The application of SimProgramming revealed promising evidences in the overall results of student learning in the activities proposed in this approach. The average grades improved, and did the number of students regularly submitting their tasks on schedule. The perceptions of students regarding the SimProgramming approach are very positive: they recommend using it in the following years, and provided some suggestions to improve the approach. We conclude with reflections and recommendations for subsequent development of the SimProgramming approach in its application to the teaching of computer programming and potential for using it in other educational contexts.

Abstract
A general concept on the use of computer vision in a way in which objects in the scene act as visual markers is presented, with special focus on its ability to increase the contextual awareness of a blind user with relation to its surroundings. A demonstration of the concept has been developed and is presented in this work. Having a rough estimation of user location and previous knowledge, from memory, of which visual features should be present in an environment, the recognition of visual elements in a scene validates and provides a trust indicator about the estimated spatial context of a blind user of an assistive orientation device, reducing the gap naturally imposed by his impairment. © 2016 ACM.

Abstract
This paper proposes a real-time system to provide location based guidance and obstacle avoidance of blind persons in indoor environments. The system integrates navigation features based on visual recognition of markers and the detection and classification of possible obstacles in front of the blind person. The system uses the Microsoft Kinect sensor to acquire RGB-D images of the scene. The RGB camera provides input for a real-time tracking algorithm which identifies a trained set of wall-mounted visual markers. The user's pose is estimated combining marker information with GIS data. Depth information is used to classify nearby obstacles. The results of experimental tests with two blind subjects are presented and discussed. © 2016 ACM.

Abstract

Abstract