Publications

2021

Journal: Safety Science

Authors: Achilleas Mina, Antreas Lanitis, Pavlos Alexandros Dimitrioua, Harris Partaourides, Pericles Pericleous

Published: January 2021

Abstract: The proper use of high-visibility safety apparel (HVSA) increases conspicuity and reduces accident rates. The main factor affecting daytime conspicuity is the color contrast between HVSA and the ambient background environment. Selecting HVSA without considering their contrast to the worksite environment may result in unsafe situations where HVSA not only fail to provide the desired conspicuity but also act as camouflage. One such situation is the use of red HVSA on oil tankers with brown decks. This paper presents a methodology for selecting the most effective HVSA color for a particular worksite. Using image analysis techniques, we can assess the contrast between a set of high-visibility colors and the colors present at a worksite in order to determine the most effective HVSA color for the particular site. The methodology was experimentally validated with the help of 50 volunteers and the use of a purpose-built validation software. Results showed a 27% reduction in the time required to detect workers when the color of their HVSA was changed to match the color determined as per the proposed methodology.

DOI: 10.1016/j.ssci.2020.104978

2020

Conference: EAI International Conference on Cognitive Computing and Cyber Physical Systems

Authors: M. Thoma, Z. Theodosiou, H. Partaourides, C.Tylliros, D. Antoniades, and A. Lanitis

Published: November 2020

Abstract: 2020

Conference: 8th International Euro-Mediterranean Conference

Authors: E. Ioannou, A. Lanitis, AK.Vionis, G. Papantoniou, N. Savvides

Published: November 2020

Abstract: Landscape studies have evolved into a significant branch of historical archaeological research, by placing emphasis on the ecological, economic, political and cultural values of pre-modern settled and sacred landscapes. The aim of our work is to support the systematic exploration of landscape archaeology in the Xeros River valley in Cyprus, through time, from prehistory to today, through the development of an Augmented Reality (AR) application. The AR application supports the exploration of pre-modern monuments and archaeological sites in the Xeros River valley, serving as a guided tour for visitors of the area. By employing image recognition and utilizing a location-based practice, the application provides the users with an immersive and educational experience, enabling the narration of the historicity of the landscape and the fate of religious and other monuments of the past 1500 years.

Conference: 8th International Euro-Mediterranean Conference

Authors: Andreas Lanitis, Zenonas Theodosiou, Harris Partaourides

Published: November 2020

Abstract: The ability to identify the artifacts that a museum visitor is looking at, using first-person images seamlessly captured by a wearable camera can be used as a means for invoking applications that provide information about the exhibits, and at the same time, it allows the analysis of visitors` activities. In this paper, a system utilizing a deep network for identifying paintings in a museum environment is presented. As part of the efforts to optimize the performance of the system, an investigation aiming to determine the effect of different conditions on the artwork recognition accuracy in a gallery/exhibition environment is presented. Through the controlled introduction of different distractors in the virtual environment, it is feasible that we assess the effect on the recognition performance in different conditions. The results of the experiment are important for improving the robustness of artwork recognition systems, and at the same time the conclusions of this work can provide specific guidelines to curators, museum professionals and visitors, that will enable the efficient use of wearable cameras in museums.

Conference: 13th Cyprus Workshop on Signal Processing and Informatics

Authors: Marios Thoma, Zenonas Theodosiou, Harris Partaourides, Charalambos Tylliros, Demetris Antoniades, Andreas Lanitis

Published: September 2020

Conference: Encyclopedia of Cryptography, Security and Privacy

Authors: Andreas Lanitis

Published: 2020

Conference: International Conference on Emerging Technologies and the Digital Transformation of Museums and Heritage Sites

Authors: A. Papadopoulou, C. Englezou, G. Neonakis, N. Mavrou, A. Lanitis. 

Published: 2020

Conference: International Conference on Emerging Technologies and the Digital Transformation of Museums and Heritage Sites

Authors: Z. Theodosiou, H. Partaourides, A. Lanitis

Published: 2020

Journal: Safety Science

Authors: Zenonas Theodosiou, Nicolas Tsapatsoulis

Published: March 2020

Abstract: Image annotation is the process of assigning metadata to images, allowing effective retrieval by text-based search techniques. Despite the lots of efforts in automatic multimedia analysis, automatic semantic annotation of multimedia is still inefficient due to the problems in modeling high-level semantic terms. In this paper, we examine the factors affecting the quality of annotations collected through crowdsourcing platforms. An image dataset was manually annotated utilizing: (1) a vocabulary consists of preselected set of keywords, (2) an hierarchical vocabulary and (3) free keywords. The results show that the annotation quality is affected by the image content itself and the used lexicon. As we expected while annotation using the hierarchical vocabulary is more representative, the use of free keywords leads to increased invalid annotation. Finally, it is shown that images requiring annotations that are not directly related to their content (i.e., annotation using abstract concepts) lead to accrue annotator inconsistency revealing in that way the difficulty in annotating such kind of images is not limited to automatic annotation, but it is a generic problem of annotation.

DOI: 10.1007/s13735-020-00193-z

Conference: Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

Authors: Zenonas Theodosiou, Harris Partaourides, Tolga Atun, Simoni Panayi, Andreas Lanitis

Published: January 2020

Abstract: Image annotation is the process of assigning metadata to images, allowing effective retrieval by text-based search techniques. Despite the lots of efforts in automatic multimedia analysis, automatic semantic annotation of multimedia is still inefficient due to the problems in modeling high-level semantic terms. In this paper, we examine the factors affecting the quality of annotations collected through crowdsourcing platforms. An image dataset was manually annotated utilizing: (1) a vocabulary consists of preselected set of keywords, (2) an hierarchical vocabulary and (3) free keywords. The results show that the annotation quality is affected by the image content itself and the used lexicon. As we expected while annotation using the hierarchical vocabulary is more representative, the use of free keywords leads to increased invalid annotation. Finally, it is shown that images requiring annotations that are not directly related to their content (i.e., annotation using abstract concepts) lead to accrue annotator inconsistency revealing in that way the difficulty in annotating such kind of images is not limited to automatic annotation, but it is a generic problem of annotation.

DOI: 10.5220/0009107506600666

2019

Journal: Education and Information Technologies

Authors: Eleni Demitriadou, Kalliopi-Evangelia Stavroulia, Andreas Lanitis

Published: July 2019

Abstract: Primary school students often find it difficult to understand the differences between two dimensional and three-dimensional geometric shapes. Taking advantage of the ability of virtual and augmented reality to visualize 3D objects, we investigate the potential of using virtual and augmented reality technologies for teaching the lesson of geometric solids to primary school children. As part of the study 30 fourth, fifth and sixth class primary school students were divided into three groups that include a control group and two experimental groups. The first and second experimental groups used dedicated virtual and augmented reality applications to learn about geometric solids, while students from the control group used traditional printed material as part of the learning process. The results indicate that the implementation of new technologies in education of virtual and augmented reality improve interactivity and student interest in mathematics education, contributing to more efficient learning and understanding of mathematical concepts when compared to traditional teaching methods. No significant difference was found between virtual and augmented reality technologies with regard to the efficiency of the methods that contribute to the learning of mathematics, suggesting that both virtual and augmented reality display similar potential for educational activities in Mathematics.

DOI: 10.1007/s10639-019-09973-5

Conference:  Advances in Intelligent Systems and Computing

Authors: Christina Zavlanou, Andreas Lanitis

Published: July 2019

Abstract: Age-related changes significantly affect elderly users’ interaction with specific products and services. Nevertheless, the challenges experienced by elderly users are difficult to be perceived and understood, especially by younger people. Inspired by the concept of aging suits, we propose a Virtual Reality-based approach, where age-related visual impairments are simulated in virtual environments. The aim is to provide an approximation of the experience of viewing and interacting with a product, from the perspective of elderly persons with specific age-related visual problems. The effectiveness of the proposed approach is examined through an experiment involving package design evaluation. The experimental results demonstrate that Virtual Reality can play an important role on understanding the challenges that elderly users face, thus support the design of elderly-friendly products.

DOI: 10.1007/978-3-030-25629-6_41

Conference: 14th International Workshop on Semantic and Social Media Adaptation and Personalization

Authors: Kalliopi-Evangelia Stavroulia, Maria Cheistofi, Telmo Zarraonandia, Despina Michael-Grigoriou, Andreas Lanitis

Published: June 2019

Abstract: The use of wearable cameras covers several areas of application nowadays, where the need for developing smart applications providing the sustainability and well-being of citizens it is more necessary than ever before. The tremendous amount of lifelogging data to extract valuable knowledge about the every day life of the wearers requires state of the art retrieval techniques to efficiently store, access, search and retrieve useful information. Several works have been proposed combining computer vision and machine learning techniques to analyze the content of the data captured from visual wearable devices on a daily basis. This paper presents an overview of the progress in visual lifelogging retrieval and indicates the current advances and future challenges, highlighting the prospects of incorporating visual lifelogging retrieval in social computing applications.

DOI: 10.1109/SMAP.2019.8864803

Journal: Smart Computing and Intelligence

Authors: Kalliopi-Evangelia Stavroulia, Maria Cheistofi, Telmo Zarraonandia, Despina Michael-Grigoriou, Andreas Lanitis

Published: June 2019

Abstract: VR technologies are gaining momentum in the field of education and particularly in the use of Virtual Reality (VR)-based learning. Within Virtual Reality Environments (VREs) realistic world situations are simulated, facilitating the transfer of the knowledge and skills gained within the virtual world to the real one. In this chapter, we provide a review of several advantages of using VR technology in education and training. In addition, we examine different challenges and potential problems that need to be considered in order to successfully integrate VR in training activities. We also exemplify the promising prospect of this technology in education by describing two novel VR applications. The first one aims to support educators in improving their teaching practice. Using VR technology, the teacher is given the opportunity to experience the student’s point of view during a classic room and cultivate their empathy skills. The second one aims to support teachers in creating VR serious games by lowering the difficulty of developing this type of educational artefact through intuitive interaction and eliminating the need for learning new design language.

DOI: 10.1007/978-981-13-8265-9_10

Journal: International Journal of Information and Learning Technology 

Authors: Kalliopi Evangelia Stavroulia, Maria Christofi, Evangelia Baka, Despina Michael-Grigoriou, Nadia Magnenat-Thalmann, Andreas Lanitis

Published: June 2019

Abstract: Purpose: The purpose of this paper is to propose the use of a virtual reality (VR)-based approach to improve teacher education and life-long professional development. Through constant training in real-life based situations but within a safe three-dimensional virtual school environment, teachers are given the opportunity to experience and learn how to react to different types of incidents that may take place in a school environment. Design/methodology/approach: The current paper presents the design cycle that was followed for the implementation of the VR teacher training system. The effectiveness of the proposed approach is demonstrated with a case study that aimed to promote teachers’ understanding of student’s problematic situations related to substance use. As part of the experimental investigation, the impact of the VR system on participants’ emotions and mood states is evaluated through Electroencephalogram (EEG) measurements, heart rate (HR) recordings and self-reported data. Findings: Results indicate significant changes to participant’s negative emotional and mood states, suggesting that the scenario and the VR experience had a strong impact on them. Moreover, participants’ HR was increased during the experiment, while the analysis of the EEG signal indicated that the participants experienced a stressful situation that could justify the change in their negative emotions and mood states. Originality/value: The proposed VR-based approach aims to provide an innovative framework to teacher education and the related training methodology. In the long-term, the proposed VR system aims to form a new paradigm of teacher training, an alternative safe method that will allow user-teachers to learn through trial and error techniques that reflect real-life situations within a three-dimensional school space and without the risk of harming real students. To the best of our knowledge this is one of the first systematic attempts to use a VR-based methodology to address real teachers’ needs. The development of the VR application is linked to both strong theoretical foundations in education derived from the literature but also from real teachers’ problems and requirements derived from an extensive literature analysis, survey and interviews with experts including teachers, school counselors and psychologists. The VR tool addresses specific teachers’ competences as outcome, after an extensive documentation of existing Teachers’ Competence Models and significant guidance by experts who pointed specific competencies of primary importance to teachers.

DOI: 10.1108/IJILT-11-2018-0127

Journal: International Journal of Emerging Technologies in Learning

Authors: Kalliopi Evangelia Stavroulia, Andreas Lanitis

Published: April 2019

Abstract: The last few years Virtual Reality (VR) based approaches have emerged lately as a new education paradigm. This paper addresses the possibility to cultivate reflection and empathy skills using a VR based framework targeting to maximize the professional development of teachers. Reflection and empathy are skills of paramount importance for teachers and an integral part of their professional development. The current research aims to investigate possible differences in cultivating reflection and empathy skills between participants who used a VR system and the control group who were trained in a real classroom environment. Experimental results indicate that the participants using the virtual classroom environment were able to better reflect and empathize with the students whereas participants from the control group tended to be more undecided. Moreover, the VR system gave the participants the opportunity to enter the students’ virtual body and understand the different perspectives affecting at a higher level the reflection process than the control group.

DOI:10.3991/ijet.v14i07.9946s

Journal: s

Authors: Fernando Loizides, Andreas Lanitis, Giorgos Papantoniou, Demetrios Michaelides

Published: s

Abstract: s

DOI: s

2018

Conference: International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments

Authors: Christofi, Maria and Baka, Evangelia and Stavroulia, Kalliopi Evangelia and Michael-Grigoriou, Despina and Lanitis, Andreas, Thalmann, Nadia-Magnenat

Published: November 2019

Abstract: This paper studies the aspect of presence in a Virtual Reality (VR) environment that can be used for training purposes in the education sector and more specifically for teacher training and professional development. During the VR experience trainees had the chance to view the world from different perspectives through the eyes of different characters appearing in the scene. The experimental evaluation conducted aims to examine the effect of viewing the experience from different perspectives and viewpoints in relation to the overall user experience and the level of presence achieved. To accomplish these objectives an experiment was performed investigating presence and the correlation between presence and different viewpoints/perspectives. To measure presence a combination of methods were used including two different questionnaires, the use of an eeg device, EMOTIV EPOC+ and the analysis of heart rates. The results indicate that high levels of presence were recorded and that increased levels of presence are associated with viewing the VE from a student rather than a teacher perspective.

DOI: 10.2312/egve.20181329

Conference: Lecture Notes in Computer Science

Authors: Christos Hadjipanayi, Eleni Demitriadou, Haris Frangou, Maria Papageorgiou, Christina Zavlanou, Andreas Lanitis

Published: October 2018

Abstract: The aim of our work is to investigate the applicability of Virtual Reality (VR) in raising awareness of users in relation to the destruction of important monuments. The proposed methodology involves the exposure of users to three virtual environments displaying the original state of a monument, the current state and the predicted future state of the same monument in the case that the monument is not maintained. The exposure to the three states of the same building allows the user to experience the “glorious days” of a monument and compare them to the current and future states in an attempt to realize the level of destruction that could occur to the building if the monument is not maintained properly. As part of a pilot case study, a number of volunteers were asked to navigate in virtual environments depicting the three chronological states of a landmark building. Preliminary results indicate a significant increase of the intensity of negative emotions of the users, indicating the applicability of VR in alerting the society toward the destruction of important monuments.

DOI: 10.1007/978-3-030-01765-1_17