The gait patterns of an elite athlete with low vision: a case study

Presentación Póster en ESMAC 2012

Magnificador basado en teléfono móvil: prototipo funcional

Enmarcado en un proyecto más amplio, en este TFG se ha realizado un prototipo funcional de una aplicación Android para realizar una función de magnificador digital de documentos en papel. Para llevarlo a cabo se ha realizado un estudio de los TFG anteriores incluidos en este proyecto, así como un estudio del desarrollo en Android. Posteriormente se ha diseñado la interfaz de usuario del prototipo funcional, partiendo de los resultados de la evaluación del prototipo de baja fidelidad realizado en un TFG anterior. Tras este diseño se ha Implementado el prototipo funcional, usando las librerías desarrolladas en TFG anteriores. Por último, se ha realizado una evaluación de la usabilidad y accesibilidad del prototipo funcional y se han definido una serie de recomendaciones de cambio a partir de esta evaluación de cara al desarrollo del sistema definitivo. ---ABSTRACT---As a part of a larger project, this TFG develops a functional prototype of an Android application to perform a magnifier function to paper documents. This application is aimed at people with low vision problems. To get it done, a study of the previous TFG included in this project as well as a study of Android developing has been made. After that, the user interface of the functional prototype has been designed, starting from the results of the low-fidelity prototype evaluation made in a previous TFG. In this design, several changes have been made regarding the low-fidelity prototype, applying the results of the usability evaluation. After this design, the functional prototype has been implemented using the libraries developed in the previous TFG. In this process some modifications over these libraries have been required. Finally, a usability and accessibility evaluation about the prototype with real users has been made, and there have been defined several change recommendations from this evaluation having in mind the development of the final system.

Magnificador basado en teléfono móvil: función de magnificación

En este Trabajo fin de Grado se ha creado la parte funcional de una aplicación móvil dejando la parte de la interfaz libre para su futura implementación. La aplicación es un magnificador y está destinada a aquellas personas con baja visión, permitiéndoles hacer aumento de imágenes y textos capturados por la cámara del dispositivo, con la posibilidad de que puedan cambiar algunos parámetros de la magnificación para poderlo ver mejor. La parte funcional de la aplicación fue nombrada como librería magnificador, ya que se compone de métodos implementados en Java que permiten hacer diferentes modificaciones de la imagen o del video visualizado. Se cubrieron todas las fases de desarrollo más significativas de un sistema software: análisis, diseño, implementación y pruebas. La aplicación se desarrolló para Android. Se trabajó en Eclipse con Android SDK. Para el procesamiento de las imágenes se aprovechó una librería externa, OpenCV, para evitar “inventar la rueda”, es decir, no escribir algoritmos de transformación de las imágenes que seguramente no podrían ser tan eficientes como los implementados en dicha librería creada por Intel. ---ABSTRACT---In this Final Project, the functional part of mobile phone application was created, leaving the interface parte for future implementation. The application is a magnifier and is oriented to people with very low vision allowing them to enlarge images of printed documents captured by the camera of the mobile phone device, with the possibility that they can change some parameters of magnification so that it can see better. The functional part of this application was named magnifier library because it composes of methods, implemented in Java, that allows changing between different modes of the preview of the image or video. All of the most significant phases of software development were satisfied: analysis, design, implementation and tests. The application was created for Android. The work was done in Eclipse with Android SDK plugin. For the image processing, an external library, OpenCv, was used, to avoid the unreachable intent of creation of effective algorithms that would never be so potent like the implemented in this library created by Intel.

A computer vision approach for weeds identification through Support Vector Machines

This paper outlines an automatic computervision system for the identification of avena sterilis which is a special weed seed growing in cereal crops. The final goal is to reduce the quantity of herbicide to be sprayed as an important and necessary step for precision agriculture. So, only areas where the presence of weeds is important should be sprayed. The main problems for the identification of this kind of weed are its similar spectral signature with respect the crops and also its irregular distribution in the field. It has been designed a new strategy involving two processes: image segmentation and decision making. The image segmentation combines basic suitable image processing techniques in order to extract cells from the image as the low level units. Each cell is described by two area-based attributes measuring the relations among the crops and weeds. The decision making is based on the SupportVectorMachines and determines if a cell must be sprayed. The main findings of this paper are reflected in the combination of the segmentation and the SupportVectorMachines decision processes. Another important contribution of this approach is the minimum requirements of the system in terms of memory and computation power if compared with other previous works. The performance of the method is illustrated by comparative analysis against some existing strategies.

Vibration reduction for vision systems on board unmanned aerial vehicles using a neuro-fuzzy controller

In this paper, an intelligent control approach based on neuro-fuzzy systems performance is presented, with the objective of counteracting the vibrations that affect the low-cost vision platform onboard an unmanned aerial system of rotating nature. A scaled dynamical model of a helicopter is used to simulate vibrations on its fuselage. The impact of these vibrations on the low-cost vision system will be assessed and an intelligent control approach will be derived in order to reduce its detrimental influence. Different trials that consider a neuro-fuzzy approach as a fundamental part of an intelligent semi-active control strategy have been carried out. Satisfactory results have been achieved compared to those obtained by means of vibration reduction passive techniques.

Robust Real-time Vision-based Aircraft Tracking From Unmanned Aerial Vehicles.

Aircraft tracking plays a key and important role in the Sense-and-Avoid system of Unmanned Aerial Vehicles (UAVs). This paper presents a novel robust visual tracking algorithm for UAVs in the midair to track an arbitrary aircraft at real-time frame rates, together with a unique evaluation system. This visual algorithm mainly consists of adaptive discriminative visual tracking method, Multiple-Instance (MI) learning approach, Multiple-Classifier (MC) voting mechanism and Multiple-Resolution (MR) representation strategy, that is called Adaptive M3 tracker, i.e. AM3. In this tracker, the importance of test sample has been integrated to improve the tracking stability, accuracy and real-time performances. The experimental results show that this algorithm is more robust, efficient and accurate against the existing state-of-art trackers, overcoming the problems generated by the challenging situations such as obvious appearance change, variant surrounding illumination, partial aircraft occlusion, blur motion, rapid pose variation and onboard mechanical vibration, low computation capacity and delayed information communication between UAVs and Ground Station (GS). To our best knowledge, this is the first work to present this tracker for solving online learning and tracking freewill aircraft/intruder in the UAVs.