Gerasimos Arvanitis

Assessing machine learning algorithms for self-management of asthma

Control and monitoring of asthma progress is highly important for patients quality of life and healthcare management. Emerging tools for self-management of various chronic diseases have the potential to support personalized patient guidance. This work presents the design aspects of the myAirCoach decision support system, with focus on the assessment of three machine learning approaches as support tools the first prototype implementation.

Block based Spectral Processing of Dense 3D Meshes using Orthogonal Iterations

Spectral methods are widely used in geometry processing of 3D models. They rely on the projection of the mesh geometry on the basis defined by the eigenvectors of the graph Laplacian operator, becoming computationally prohibitive as the density of the models increases. In this paper, we propose a novel approach for supporting fast and efficient spectral processing of dense 3D meshes, ideally suited for real time compression and denoising scenarios. To achieve that, we apply the problem of tracking graph Laplacian eigenspaces via orthogonal iterations, exploiting potential spectral coherences between adjacent parts. To avoid perceptual distortions when a fixed number of eigenvectors is used for all the individual parts, we propose a flexible solution that automatically identifies the optimal subspace size for satisfying a given reconstruction quality constraint. Extensive simulations carried out with different 3D meshes in compression and denoising setups, showed that the proposed schemes are very fast alternatives of SVD based spectral processing while achieving at the same time similar or even better reconstruction quality. More importantly, the proposed approach can be employed by several other state of the art denoising methods as a preprocessing step, optimizing both their reconstruction quality and their computational complexity.

Generation and Authoring of Augmented Reality Terrains Through Real-Time Analysis of Map Images

In this paper we present a novel method for real time 3D terrain creation and augmented reality rendering based on contour map images. Initially, terrain information is extracted from the contour images and a flat Delaunay triangulated terrain is generated. Then elevation information is added and remedying is performed so as to maintain smooth local surface representation. Then augmented reality rendering is performed in real time using the 2D contour map as a marker to manipulate the 3D terrain. The proposed framework also demonstrates potential editing applications like manual design of auxiliary information on the contour map, like roads, that can be automatically converted into 3D information and rendered on the 3D terrain, thus resulting in a more immersive and intuitive design experience.

Real-Time Removing of Outliers and Noise in 3D Point Clouds Applied in Robotic Applications

Nowadays, robots are able to carry out a complex series of actions, to take decisions, to interact with their environment and generally to perform plausible reactions. Robots’ visual ability plays an important role to their behavior, helping them to efficiently manage the received information. In this paper, we present a real time method for removing outliers and noise of 3D point clouds which are captured by the optical system of robots having depth camera at their disposal. Using our method, the final result of the created 3D object is smoothed providing an ideal form for using it in further processing techniques; namely navigation, object recognition and segmentation. In our experiments, we investigate real scenarios where the robot moves while it acquires the point cloud in natural light environment, so that unpleasant noise and outliers become apparent.

Online Biometric Identification with Face Analysis in Web Applications

Internet security is an important issue that concerns everyone who uses it without exception. Over the past few years, there has been a significant improvement in internet security but little attention has been paid to protect careless users. This paper introduces a user-based security application that could replace the classic login frame on websites in order to offer an extra security level that allows a biometric identification of the user that prevents unauthorized login to his personal page.

Real-Time Context Aware Audio Augmented Reality

The purpose of this paper is to present a method for real time augmented reality sound production from virtual sources, which are located in a real environment. In the performed experiments, we will initially emphasize on augmenting audio information, beyond the existing environmental sounds, using headphones. The main goal of the approach is to produce a virtual sound that has a natural result so that the user gets immersed and senses a context aware synthetic sound. The necessary data, such as spatial coordinates of source and listener, relative distance and relative velocity between them, room dimensions and potential obstacles between virtual source and listener are given as input to the proposed framework. Real time techniques are used for data processing. These techniques are fast and effective in order to achieve high performance requirements. The resulted sound gives the impression to the listener that the virtual source is part of the real environment. Any dynamic change of the parameters will have as a result the simultaneous real time change of the produced sound.