Mazurkiewicz, Bartosz; Giannopoulos, Ioannis
In: Krisp, Jukka; Meng, Liqiu; Kumke, Holger; Huang, Haosheng (Ed.): 17th International Conference on Location Based Services (LBS 2022), pp. 68–77, 2022.
Replication of real-world wayfinding studies is not a trivial task. Even less if it is to be replicated in a different geographic environment. The selection of one or several routes is one of many decisions to be made. Only recently (2021), a reproducible, systematic and score-based approach for route selection for wayfinding experiments was published. Besides allowing for selecting a route within a selected experimental area, it claims to be able to find similar routes in different geographic areas. However, it remains unclear if similar, according to this route selection framework, routes lead to similar study results. In order to answer this question, an agent-based simulation comparing Turn-byTurn and Free Choice Navigation approaches (between-subject design) is run in one European (Vienna) and one African (Djibouti City) city. First, a route in Vienna is selected and, second, the 5 most and the 5 least similar routes in Djibouti City are found. These routes are used in the simulation in order to scrutinize if more similar routes lead to more similar results regarding the arrival rate as a metric. The results suggest that the route selection framework is suitable for replication studies for the Turn-By-Turn navigation approach but needs further improvement for the Free Choice Navigation approach by adding features describing the neighborhood of the route.
Alinaghi, Negar; Kattenbeck, Markus; Giannopoulos, Ioannis
In: pp. 2:1–2:13, Schloss Dagstuhl -- Leibniz-Zentrum für Informatik, 2022, ISBN: 978-3-95977-257-0.
Spatial familiarity plays an essential role in the wayfinding decision-making process. Recent findings in wayfinding activity recognition domain suggest that wayfinders' turning behavior at junctions is strongly influenced by their spatial familiarity. By continuously monitoring wayfinders' turning behavior as reflected in their eye movements during the decision-making period (i.e., immediately after an instruction is received until reaching the corresponding junction for which the instruction was given), we provide evidence that familiar and unfamiliar wayfinders can be distinguished. By applying a pre-trained XGBoost turning activity classifier on gaze data collected in a real-world wayfinding task with 33 participants, our results suggest that familiar and unfamiliar wayfinders show different onset and intensity of turning behavior. These variations are not only present between the two classes -familiar vs. unfamiliar- but also within each class. The differences in turning-behavior within each class may stem from multiple sources, including different levels of familiarity with the environment.
Alinaghi, Negar; Giannopoulos, Ioannis
In: 2022 Symposium on Eye Tracking Research and Applications, Association for Computing Machinery, Seattle, WA, USA, 2022, ISBN: 9781450392525.
Saccadic eye movements are known to serve as a suitable proxy for tasks prediction. In mobile eye-tracking, saccadic events are strongly influenced by head movements. Common attempts to compensate for head-movement effects either neglect saccadic events altogether or fuse gaze and head-movement signals measured by IMUs in order to simulate the gaze signal at head-level. Using image processing techniques, we propose a solution for computing saccades based on frames of the scene-camera video. In this method, fixations are first detected based on gaze positions specified in the coordinate system of each frame, and then respective frames are merged. Lastly, pairs of consecutive fixations –forming a saccade- are projected into the coordinate system of the stitched image using the homography matrices computed by the stitching algorithm. The results show a significant difference in length between projected and original saccades, and approximately 37% of error introduced by employing saccades without head-movement consideration.
Cutchan, Marvin Mc; Giannopoulos, Ioannis
Encoding Geospatial Vector Data for Deep Learning: LULC as a Use Case (Journal Article)
In: Remote Sensing, vol. 14, no. 12, 2022, ISSN: 2072-4292.
Geospatial vector data with semantic annotations are a promising but complex data source for spatial prediction tasks such as land use and land cover (LULC) classification. These data describe the geometries and the types (i.e., semantics) of geo-objects, such as a Shop or an Amenity. Unlike raster data, which are commonly used for such prediction tasks, geospatial vector data are irregular and heterogenous, making it challenging for deep neural networks to learn based on them. This work tackles this problem by introducing novel encodings which quantify the geospatial vector data allowing deep neural networks to learn based on them, and to spatially predict. These encodings were evaluated in this work based on a specific use case, namely LULC classification. We therefore classified LULC based on the different encodings as input and an attention-based deep neural network (called Perceiver). Based on the accuracy assessments, the potential of these encodings is compared. Furthermore, the influence of the object semantics on the classification performance is analyzed. This is performed by pruning the ontology, describing the semantics and repeating the LULC classification. The results of this work suggest that the encoding of the geography and the semantic granularity of geospatial vector data influences the classification performance overall and on a LULC class level. Nevertheless, the proposed encodings are not restricted to LULC classification but can be applied to other spatial prediction tasks too. In general, this work highlights that geospatial vector data with semantic annotations is a rich data source unlocking new potential for spatial predictions. However, we also show that this potential depends on how much is known about the semantics, and how the geography is presented to the deep neural network.
Mazurkiewicz, Bartosz; Kattenbeck, Markus; Giannopoulos, Ioannis
In: Ishikawa, Toru; Fabrikant, Sara Irina; Winter, Stephan (Ed.): 15th International Conference on Spatial Information Theory (COSIT 2022), pp. 6:1–6:13, Schloss Dagstuhl -- Leibniz-Zentrum für Informatik, Dagstuhl, Germany, 2022, ISSN: 1868-8969.
Route selection for a wayfinding experiment is not a trivial task and is often made in an undocumented way. Only recently (2021), a systematic, reproducible and score-based approach for route selection for wayfinding experiments was published. However, it is still unclear how robust study results are across all potential routes in a particular experimental area. An important share of routes might lead to different conclusions than most routes. This share would distort and/or invert the study outcome. If so, the question of selecting routes that are unlikely to distort the results of our wayfinding experiments remains unanswered. In order to answer these questions, an agent-based simulation study with four different sample sizes (N = 15, 25, 50, 3000 agents) comparing Turn-by-Turn and Free Choice Navigation approaches (between-subject design) regarding their arrival rates on more than 11000 routes in the city center of Vienna, Austria, was run. The results of our study indicate that with decreasing sample size, there is an increase in the share of routes which lead to contradictory results regarding the arrival rate, i.e., the results become less robust. Therefore, based on simulation results, we present an approach for selecting suitable routes even for small-scale in-situ studies.
Mazurkiewicz, Bartosz; Kattenbeck, Markus; Giannopoulos, Ioannis
In: Janowicz, Krzysztof; Verstegen, Judith A. (Ed.): 11th International Conference on Geographic Information Science (GIScience 2021) - Part II, pp. 9:1–9:16, Schloss Dagstuhl -- Leibniz-Zentrum für Informatik, Dagstuhl, Germany, 2021, ISSN: 1868-8969.
Using navigation assistance systems has become widespread and scholars have tried to mitigate potentially adverse effects on spatial cognition these systems may have due to the division of attention they require. In order to nudge the user to engage more with the environment, we propose a novel navigation paradigm called Free Choice Navigation balancing the number of free choices, route length and number of instructions given. We test the viability of this approach by means of an agent-based simulation for three different cities. Environmental spatial abilities and spatial confidence are the two most important modeled features of our agents. Our results are very promising: Agents could decide freely at more than 50% of all junctions. More than 90% of the agents reached their destination within an average distance of about 125% shortest path length.
Mazurkiewicz, Bartosz; Giannopoulos, Ioannis
2021, (Cycling@CHI: Towards a Research Agenda for HCI in the Bike Lane at CHI ’21, May 8–13, 2021, Yokohama, Japan. ACM, New York, NY, USA, 5 pages).
The choice of a route from an origin to a destination depends on several criteria. These criteria can range from route length to
environment type. In several situations, we are not only interested in finding a route between two points, but to find a route between all possible origin-destination points in a specific geographic area. This is very common during experimental design, when one is seeking for a generalizable route to evaluate a navigation system. For this case, the selected route should be representative for the area, and not an exception with peculiarities. In this work we demonstrate (1) how to choose an average route for a bike navigation study in Vienna, Austria and (2) how to find similar routes in Florence, Italy and Bremen, Germany in order to replicate the study. The selection is based on route features and associated weights. They can be highly customized according to the needs. We demonstrate our approach and introduce four application scenarios to exemplify the benefits of a systematic route selection.
Schmidl, Martin; Navratil, Gerhard; Giannopoulos, Ioannis
In: Partsinevelos, Panagiotis; Kyriakidis, Phaedon; Kavouras, Marinos (Ed.): Proceedings of the 24th AGILE Conference on Geographic Information Science, Copernikus Publications, 2021, (talk: 24th AGILE Conference on Geographic Information Science, Chania, Greece, Online; 2021-06-08 -- 2021-06-11).
During spatial decision making, the quality of the utilized data is of high importance. During navigation these decisions are crucial for being routed to the desired destination (usually going by the shortest or fastest route). Road networks, the main data source for routing, are prone to changes which can have a big impact on the computed route and therefore on travel time. For instance, routes computed using an outdated street network can result in longer travel times, in longer distance, as well in cases where the desired destination might not be anymore reachable via the computed route. Data from OpenStreetMap with different timestamps allows us to download road network snapshots from different years, i.e., from 2014 to 2020. On each of those datasets the fastest route between 500 randomly chosen point pairs in Vienna, Austria, was computed. Ŧhese routes were also reconstructed on the most recent dataset for evaluation reasons. Ŧhe resulting travel times, travel length as well as feasibility of the route were compared with the most recent dataset. Ŧhe results provide a first assessment of temporal quality based on the currentness of a dataset.
Stähli, Lisa; Giannopoulos, Ioannis; Raubal, Martin
Evaluation of pedestrian navigation in Smart Cities (Journal Article)
In: Environment and Planning B: Urban Analytics and City Science, vol. 48, no. 6, pp. 1728–1745, 2021.
This work addresses recent research in the area of pedestrian navigation aids that aims at finding alternatives to the widely used map-based turn-by-turn navigation systems in the context of Smart City environments. Four different approaches of pedestrian navigation systems were compared to each other in a user experiment that was conducted in a virtual environment: (1) map-based, (2) landmark-based, (3) augmented reality, and (4) public display navigation. The results of the experiment with 45 participants conducted in a virtual environment suggest that the augmented reality navigation performs best concerning efficiency and effectiveness and the landmark-based navigation performs worst in the context of Smart Cities.
Golab, Antonia; Kattenbeck, Markus; Sarlas, Georgios; Giannopoulos, Ioannis
In: Spatial Cognition & Computation, vol. 0, no. 0, pp. 1-33, 2021.
Despite the increased research interest in wayfinding assistance systems, research on the appropriate point in time or space to automatically present a route instruction remains a desideratum. We address this research gap by reporting on the results of an outdoor, within-subject design wayfinding study (N=52). Participants walked two different routes for which they requested spoken, landmark-based turn-by-turn route instructions. By means of a survival analysis, we model the points in space at which participants issue such requests, considering personal, environmental, route- and trial-related variables. We reveal different landcover classes (e.g., densely built-up areas) and personal variables (e.g., egocentric orientation and age) to be important, discuss potential reasons for their impact and derive open research questions.
Gedefaw, Abebaw Andarge
Land Cover Change Monitoring, Land Certification and Land Consolidation: Towards Sustainable Rural Land Administration in Ethiopia referring to Gozamin District (PhD Thesis)
Universität für Bodenkultur/Institut für Geomatik, 2021.
Preliminary remarks: 1. Information on land cover changes as well as the driving forces behind such changes underpin a proper understanding of the dynamics of land cover. 2. Tenure security is an important factor for land investment and for agricultural productivity. 3. Land consolidation is a proper tool to solve inefficiencies in agricultural production.
This study aims to examine the magnitude and rate of land cover change and to identify its major determinants. It aims to highlight effects of land certification on tenure security, land investment, crop productivity, and land dispute. Finally, it aims to assess the determinants, which influence the willingness of farmers to participate in voluntary land consolidation processes. The investigations were outlined in the Ethiopian Gozamin District and they are based on survey data collected from 343 randomly selected farm households, structured interviews, focus group discussions with farmers and expert panels. The collected data were analyzed quantitatively by using descriptive statistics and logistic regression models and they were complemented by qualitative data.
Satellite images of Landsat 5 (1986), Landsat 7 (2003), and Sentinel-2 (2018) were used to assess the dynamics of land cover. Focus group discussions, interviews, and farmers' lived experiences through a household survey were applied to identify the factors for land cover changes based on the DPSIR (Driver-Pressure-State-Impact-Response) Framework. Results of the investigations revealed that during the last three decades the study area has undergone an extensive land cover change, primarily a shift from cropland and grassland into forests and built-up areas. Thus, quantitative land cover change detection between 1986 and 2018 revealed that cropland, grassland, and bare areas declined by 10.53%, 5.7%, and 2.49%. Forest, built-up, shrub/scattered vegetation, and water bodies expanded by 13.47%, 4.02%, 0.98%, and 0.25%. Population growth, the rural land tenure system, the overuse of land, the climate change, and the scarcity of grazing land could be identified as key drivers of these land cover changes.
The assessment of land tenure security indicated that most farm households feel that their land use rights are secure after the certification process. Only 17% fear that the government at any time could take their land use rights. Most farm households identified a reduction of disputes after certification and land management practices improved from 70.3% before certification to 90.1% after certification. As key factors for the increase of terracing and the application of manure, the study determined total farm size, the average distance from farm to homestead, perception of degradation, access to credit, training to land resource management, fear about land take-over by the government and total livestock holdings. Crop productivity improved significantly after land certification.
Other results of the study documents that farmers are predominantly willing to participate in voluntary land consolidation (66.8%). Significant determinants influencing the willingness of farmers for voluntary land consolidation are the exchange of parcels with neighbors, the expectation of better arranged parcels, the nearness of plots to the farmstead, and the perception that land fragmentation reduces agricultural productivity. The majority of farmers believes that land consolidation could reduce land use conflicts.
The outputs from this study can be used to assure sustainability in resource utilization, to enable proper land use planning, and to support decision-making. The results also can encourage policy makers to minimize the sources of insecurity, such as frustrations of future land redistribution and land taking without proper land compensation. Voluntary land consolidation could be a policy instrument to address the challenges of subsistence agriculture in Ethiopia.
Mazurkiewicz, Bartosz; Kattenbeck, Markus; Kiefer, Peter; Giannopoulos, Ioannis
In: Janowicz, Krzysztof; Verstegen, Judith Anne (Ed.): 11th International Conference on Geographic Information Science, GIScience 2021, September 27-30, 2021, Poznań, Poland - Part I, pp. 8:1–8:16, Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2021.
Cutchan, Marvin Mc; Comber, Alexis J.; Giannopoulos, Ioannis; Canestrini, Manuela
Semantic Boosting: Enhancing Deep Learning Based LULC Classification (Journal Article)
In: Remote Sensing, vol. 13, no. 16, 2021, ISSN: 2072-4292.
The classification of land use and land cover (LULC) is a well-studied task within the domain of remote sensing and geographic information science. It traditionally relies on remotely sensed imagery and therefore models land cover classes with respect to their electromagnetic reflectances, aggregated in pixels. This paper introduces a methodology which enables the inclusion of geographical object semantics (from vector data) into the LULC classification procedure. As such, information on the types of geographic objects (e.g., Shop, Church, Peak, etc.) can improve LULC classification accuracy. In this paper, we demonstrate how semantics can be fused with imagery to classify LULC. Three experiments were performed to explore and highlight the impact and potential of semantics for this task. In each experiment CORINE LULC data was used as a ground truth and predicted using imagery from Sentinel-2 and semantics from LinkedGeoData using deep learning. Our results reveal that LULC can be classified from semantics only and that fusing semantics with imageryâ€”Semantic Boostingâ€”improved the classification with significantly higher LULC accuracies. The results show that some LULC classes are better predicted using only semantics, others with just imagery, and importantly much of the improvement was due to the ability to separate similar land use classes. A number of key considerations are discussed.
Alinaghi, Negar; Kattenbeck, Markus; Golab, Antonia; Giannopoulos, Ioannis
In: Janowicz, Krzysztof; Verstegen, Judith A. (Ed.): 11th International Conference on Geographic Information Science (GIScience 2021) - Part II, pp. 5:1–5:16, Schloss Dagstuhl -- Leibniz-Zentrum für Informatik, Dagstuhl, Germany, 2021, ISSN: 1868-8969.
Decision making is an integral part of wayfinding and people progressively use navigation systems to facilitate this task. The primary decision, which is also the main source of navigation error, is about the turning activity, i.e., to decide either to turn left or right or continue straight forward. The fundamental step to deal with this error, before applying any preventive approaches, e.g., providing more information, or any compensatory solutions, e.g., pre-calculating alternative routes, could be to predict and recognize the potential turning activity. This paper aims to address this step by predicting the turning decision of pedestrian wayfinders, before the actual action takes place, using primarily gaze-based features. Applying Machine Learning methods, the results of the presented experiment demonstrate an overall accuracy of 91% within three seconds before arriving at a decision point. Beyond the application perspective, our findings also shed light on the cognitive processes of decision making as reflected by the wayfinder’s gaze behaviour: incorporating environmental and user-related factors to the model, results in a noticeable change with respect to the importance of visual search features in turn activity recognition.
Rudi, David; Kiefer, Peter; Giannopoulos, Ioannis; Raubal, Martin
Gaze-based interactions in the cockpit of the future: a survey (Journal Article)
In: Journal on Multimodal User Interfaces, vol. 14, no. 1, pp. 25–48, 2020.
Krieger, P; Kattenbeck, Markus; Ludwig, B; Helmbrecht, J; Giannopoulos, Ioannis
In: Partsinevelos, P.; Kyriakidis, P.; Kavouras, M. (Ed.): Proceedings of the 23rd AGILE Conference on Geographic Information Science, pp. 11, Copernicus Publications, 2020.
(Tags: )| |
Navratil, Gerhard; Konturek, Philip; Giannopoulos, Ioannis
Interacting with 3D Models - 3D-CAD vs. Holographic Models (Journal Article)
In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. VI-4/W1-2020, pp. 129–134, 2020.
A problem with 3D models is that devices used to display them are typically two-dimensional, i.e., computer monitors or printed maps. User interfaces of computer software are based on mouse, touchscreen, keyboards, etc. and are optimized for this dimensionality. However, this causes problems when working with 3D models and the user must adapt her actions by interpreting the missing third dimension. While this might not necessarily pose a problem for frequent users, infrequent users may find this quite challenging. Holographic models, on the other hand, float in front of the user, providing a 3D perspective. Interaction with this kind of models may thus be more intuitive than traditional interaction. In the paper we present the results from a first user test. 15 participants tested interaction with a holographic model visualized using Augmented Reality (AR) technology. The results were compared to those of 15 participants using a traditional 3D-CAD. It was found that the holographic approach is more intuitive leading to a lower frustration level although it is still restricted by technical limitations.
Cutchan, Marvin Mc; Özdal-Oktay, Simge; Giannopoulos, Ioannis
Semantic-based urban growth prediction (Journal Article)
In: Transactions in GIS, vol. n/a, no. n/a, 2020.
Abstract Urban growth is a spatial process which has a significant impact on the earth’s environment. Research on predicting this complex process makes it therefore especially fruitful for decision-making on a global scale, as it enables the introduction of more sustainable urban development. This article presents a novel method of urban growth prediction. The method utilizes geospatial semantics in order to predict urban growth for a set of random areas in Europe. For this purpose, a feature space representing geospatial configurations was introduced which embeds semantic information. Data in this feature space was then used to perform deep learning, which ultimately enables the prediction of urban growth with high accuracy. The final results reveal that geospatial semantics hold great potential for spatial prediction tasks.
Navratil, Gerhard; Giannopoulos, Ioannis; Kotzbek, Gilbert
Classification of Urban and Rural Routes based on Motorcycle Riding Behaviour (Inproceedings)
In: Kyriakidis, Phaedon; others, (Ed.): Geospatial Technologies for Local and Regional Development, pp. 95–108, Springer, 2019, ISBN: 978-3-030-14744-0, (Vortrag: 22nd AGILE Conference on Geographic Information Science, Limassol; 2019-06-17 -- 2019-06-20).
A basic problem in navigation is the selection of a suitable route. This requires a determination of costs or suitability. There are approaches for many standard situations, e.g., the shortest route for pedestrians, the fastest route for cars, a physically possible and legal route for trucks, or the safest route for bicycle riders. However, not much research has been done yet for motorcycle riders. Published approaches rely on interpretation of geometry, interviews, or user feedback. None of these approaches is precise and scalable. Since modern motorcycles have an increasing number of internal sensors (e.g., lean angle sensors for curve ABS), they could provide the data required for a classification of route segments. The combination with a navigational device allows to georeferenced the data and thus attach riding characteristics to a specific road segment. This work sketches the classification concept and presents data from a real-driving experiment using an external IMU.
Giannopoulos, Ioannis; Schmidtke, Hedda (Ed.)
COSIT 2019 Doctoral Colloquium Proceedings (Book)
Universität Regensburg, Regensburg, 2019.
Proceedings der Extended Abstracts für das Doktorandentreffen im Rahmen der COSIT 2019.
Gaze-Based Assistance for Collective Spatial Cognition (Inproceedings)
In: Curtin, Kevin M; Montello, Daniel R (Ed.): Innovative Research about Spatial Thinking by Human Groups, Laboratory for Location Science, University of Alabama, 2019, (Vortrag: Collective Spatial Cognition Specialist Meeting, Santa Barbara, California, USA; 2019-04-17 -- 2019-04-19).
When we walk and interact in an unfamiliar environment, wayfinding can be very challenging. We have to select a proper route than will lead us to the desired destination, we have to orient in our surroundings, we have to monitor our environment while walking to ensure that we are still on the right track and finally we have to recognize the destination. Furthermore, while we are wayfinding, we are acquiring spatial knowledge, developing and enhancing our mental representation of the environment we are interacting in. Assistance aids can be utilized for this purpose, helping us to offload some of the relevant tasks. Furthermore, assistance systems can help us to coordinate our activities with others, communicate, as well as increase our knowledge concerning the relevant environment. An assistance system that knows what we have seen, what we are interested in and what we want to achieve can be effectively utilized to support the process of wayfinding. Eye tracking data can be a great source, close to our cognitive processes, that can be utilized for the extraction of this relevant information that will help to coordinate and manage the spatial cognition of a person or even of a larger group of people. This position paper demonstrates how research in the area of gaze-based assistance can be utilized for acquiring, organizing and utilizing spatial knowledge of a group of people through the example of a group of tourists.
In: Bulletin TU Wien alumni club, vol. 47, no. Juni, 2019.
Während wir uns im Außenbereich bewegen und mit dem Raum interagieren, nehmen wir nur physische Objekte wie Gebäude, Straßen und andere Fußgänger in der Nähe wahr. Aber unsere Welt ist voll verborgener Informationen, z.B. unterirdischen Elemente, die von der Bodenoberfläche und den Gebäudewänden verdeckt werden oder von georeferenzierten Informationen, die im Internet, aber nicht im realen Raum zu finden sind. Diese Informationen können Geschichten erzählen oder sogar einen bestimmten Ort charakterisieren
Fogliaroni, Paolo; Mazurkiewicz, Bartosz; Kattenbeck, Markus; Giannopoulos, Ioannis
Geographic-Aware Augmented Reality for VGI (Inproceedings)
In: Gartner, Georg; Huang, Haosheng (Ed.): Advances in Cartography and GIScience of the ICA (ICA-Adv), pp. 3.1–3.9, International Cartographic Association (ICA), 2, 2019, (Vortrag: 15th International Conference on Location Based Services (LBS 2019), Wien; 2019-11-11 -- 2019-11-13).
Volunteered Geographic Information (VGI) has been a constantly growing field over the last decade, but the utilised technologies (i.e., mobile phones) are not able to exploit the full potential concerning effort and accuracy of registering geographic data. This paper introduces the GeoAR Glasses, a novel technology enabling the use of Geographic-Aware Augmented Reality for Mobile Geographic Information Systems (Mobile GIS) and Location-Based Services (LBS). The potentials of the GeoAR Glasses with respect to current mobile mapping applications is shown by means of an in-situ study (N=42) comparing two different modes of collecting VGI data. For the comparison we take into account the accuracy of the mapped data points and the time needed to complete the mapping. The results show that the GeoAR Glasses outperform the mobile application concerning both positional accuracy and completion time.
Giannopoulos, Ioannis; Navratil, Gerhard; Fogliaroni, Paolo; Özdal-Oktay, Simge; McCutchan, Marvin; Mazurkiewicz, Bartosz
Geoinformation Research Directions (Journal Article)
In: Österreichische Zeitschrift für Vermessung und Geoinformation (VGI), vol. 107. Jahrgang, no. 2, pp. 147–155, 2019.
Dieser Artikel stellt die Forschungsrichtungen der Forschungsgruppe Geoinformation an der Technischen Universität Wien vor. Wenn wir uns in einer realen oder virtuellen Umgebung bewegen und mit unserer direkten Umgebung, z. B. Gebäuden, interagieren, produzieren wir raumbezogene Spuren. Durch die effiziente und effektive Analyse dieser vom Menschen erzeugten Daten, aber auch von der städtischen Umwelt, sind wir in der Lage, mehrere Forschungsfragen des Bereichs zu beantworten. Zum Beispiel können wir die Struktur der Umwelt, in der wir leben, aufdecken, die Auswirkungen der Umwelt auf die menschliche Entscheidungsfindung untersuchen, verstehen wie Menschen mit der Umwelt interagieren, sowie neue raumbezogene Visualisierungen und Interaktionsdialoge ermöglichen. Neuartige Technologien wie Virtual and Augmented Reality sowie Eye Tracking befähigen uns, einen Schritt weiter zu gehen und komplexe Experimente durchzuführen, um relevante raumbezogene Daten zu generieren, die es uns ermöglichen, den Entscheidungsprozess des Menschen in kontrollierten Umgebungen zu untersuchen und zu verstehen. Darüber hinaus können wir aufgrund des aktuellen technologischen Fortschritts der Forschungsgruppe für Geoinformation die AR-Technologie nun auch im Außenbereich einsetzen, um georeferenzierte Objekte in Echtzeit zu visualisieren. Dies erlaubt uns, Experimente auch in natürlicher Umgebung durchzuführen und die räumliche Information, die der Mensch mit Hilfe unserer entwickelten Technologie wahrnehmen kann, zu verändern.
Navratil, Gerhard; Schmitzer, Manuel; Giannopoulos, Ioannis
Location Based Services for Human Self-Localization (Inproceedings)
In: Gartner, Georg; Huang, Haosheng (Ed.): Advances in Cartography and GIScience of the ICA (ICA-Adv), pp. 11.1–11.8, International Cartographic Association (ICA), 2, 2019, (Vortrag: 15th International Conference on Location Based Services (LBS 2019), Wien; 2019-11-11 -- 2019-11-13).
Human self-localisation is an important part of everyday life. In order to determine one's own position and orientation, the allocentric representation, usually in the form of a map, has to be aligned with one's own egocentric representation of the real world. This requires objects (anchor points) that are present in both representations. We present two novel approaches that aim to simplify the process of alignment and thus the self-localisation. The Viewshed approach is based on visibility analysis and the Image Recognition approach identifies objects and highlights them on the map. On the basis of an empirical experiment with 30 participants in the city of Vienna, Austria, the two approaches were compared with each other as well as with a standard approach using a 2D map representation. The goal is to assess and compare aspects like efficiency, user experience, and cognitive workload. Results show that the Image Recognition method provided the best support and was also most popular among users. The Viewshed method performed well below expectations.
Gokl, Lukas; McCutchan, Marvin; Mazurkiewicz, Bartosz; Fogliaroni, Paolo; Giannopoulos, Ioannis
Towards Urban Environment Familiarity Prediction (Inproceedings)
In: Gartner, Georg; Huang, Haosheng (Ed.): Advances in Cartography and GIScience of the ICA (ICA-Adv), pp. 5-1–5-8, International Cartographic Association (ICA), 2, 2019, (Vortrag: 15th International Conference on Location Based Services (LBS 2019), Wien; 2019-11-11 -- 2019-11-13).
Location Based Services (LBS) are definitely very helpful for people that interact within an unfamiliar environment, but also for those that already possess a certain level of familiarity with it. In order to avoid overwhelming familiar users with unnecessary information, the level of details offered by the LBS shall be adapted to the level of familiarity with the environment: providing more details to unfamiliar users and a lighter amount of information (that would be superfluous, if not even misleading) to the users that are more familiar with the current environment. Currently, the information exchange between the service and its users is not taking into account familiarity. Within this work, we investigate the potential of machine learning for a binary classification of environment familiarity (i.e., familiar vs unfamiliar) with the surrounding environment. For this purpose, a 3D virtual environment based on a part of Vienna, Austria was designed using datasets from the municipal government. During a navigation experiment with 22 participants we collected ground truth data in order to train four machine learning algorithms. The captured data included motion and orientation of the users as well as visual interaction with the surrounding buildings during navigation. This work demonstrates the potential of machine learning for predicting the state of familiarity as an enabling step for the implementation of LBS better tailored to the user.
McCutchan, Marvin; Özdal-Oktay, Simge; Giannopoulos, Ioannis
Urban Growth Predictions with Deep Learning and Geosemantics (Inproceedings)
In: Ehrmann, Katharina; Khosravi, Hamid Reza Mansouri; others, (Ed.): VIENNA Young Scientists Symposium (VSS 2019), pp. 30–31, Book-of-Abstracts.com, Gumpoldskirchen, 2019, ISBN: 978-3-9504017-9-0, (Vortrag: VIENNA Young Scientists Symposium (VSS 2019), Wien; 2019-06-13 -- 2019-06-14).
This work outlines a novel approach for the prediction of urban growth. The method extracts semantic information of geospatial data and predicts if urban and non-urban areas are going to change in the future, using a deep neural network. The scored prediction accuracy is higher than any other urban growth prediction model. This superiority is based on two novelties: (1) The effective modeling of the geospatial configurations using semantics, (2) the use of deep learning. The proposed method is therefore an effective tool to predict one of the global challenges of urban sprawl and support the future development strategies.
Kiefer, Peter; Giannopoulos, Ioannis; Göbel, Fabian; Raubal, Martin; Duchowski, Andrew T (Ed.)
ETH-Zürich, Zürich, 2018.
(Tags: eye tracking)| | |
Proceedings of the 3rd International Workshop in conjunction with the 14th International Conference on Location Based Services (LBS 2018)
Navratil, Gerhard; Schwai, Marco; Vollnhofer, Stefan; Konturek, Philip; Giannopoulos, Ioannis
In: Oosterom, Peter; Dubbeling, Dirk (Ed.): Proceedings 6th International FIG Workshop on 3D Cadastres, pp. 515–528, FIG, 2018, ISBN: 978-87-92853-80-6, (Vortrag: 6th International FIG Workshop on 3D Cadastres, Delft; 2018-10-02 -- 2018-10-04).
The creation of a 3D cadaster faces a number of different challenges. Two of them are the collection of data on already existing 3D structures and the visualization for non-experts. The paper uses Augmented Reality (AR) technology for the visualization of models created from plans required in Austria to create condominiums. The advantages of such an approach would be:par
- Since the plans are required for the creation of condominiums, the data already exist and no additional surveying work is necessary.par
- AR technology might be more intuitive than 3D CAD-systems. Experts in 3D CAD have no problems to work with complex models but the typical person interested in a condominium will have a background in law (e.g., a notary) or economy (e.g., a real estate agent) and people interested in acquiring ownership may have any kind of background.par
The paper shows how to create a model of condominium from floor plans, import it in the AR environment, and interact with the model. The test setup is described and first results are sketched.
McCutchan, Marvin; Giannopoulos, Ioannis
Geospatial Semantics for Adaptive Interaction (Inproceedings)
In: Kuhn, Werner; Kemp, Karen; others, (Ed.): GIScience 2018 - Workshop on Core Computations on Spatial Information, pp. 1:1–1:4, 2018, (Vortrag: GIScience 2018 - Workshop on Core Computations on Spatial Information, Melbourne, Australien; 2018-08-28).
This work presents a concept for adaptive interaction dialogues which are based on geospatial semantics and machine learning. The proposed system should enable users to efficiently and effectively interact with their surrounding environment. Through this adaptive interaction dialogues the users should be able to ask relevant questions in a more natural way.
McCutchan, Marvin; Giannopoulos, Ioannis
Geospatial Semantics for Spatial Prediction (Inproceedings)
In: Winter, Stephan; Griffin, Amy; Sester, Monika (Ed.): Proceedings 10th International Conference on Geographic Information Science (GIScience 2018), pp. 45:1–45:6, LIPICS, 114, 2018, ISBN: 978-3-95977-083-5, (Vortrag: 10th International Conference on Geographic Information Science (GIScience 2018), Melbourne; 2018-08-28 -- 2018-08-31).
In this paper the potential of geospatial semantics for spatial predictions is explored. Therefore data from the LinkedGeoData platform is used to predict landcover classes described by the CORINE dataset. Geo-objects obtained from LinkedGeoData are described by an OWL ontology, which is utilized for the purpose of spatial prediction within this paper. This prediction is based on an association analysis which computes the collocations between the landcover classes and the semantically described geo-objects. The paper provides an analysis of the learned association rules and finally concludes with a discussion on the promising potential of geospatial semantics for spatial predictions, as well as potentially fruitful future research within this domain.
Göbel, Fabian; Kiefer, Peter; Giannopoulos, Ioannis; Duchowski, Andrew T; Raubal, Martin
Improving Map Reading with Gaze-adaptive Legends (Inproceedings)
In: Proceedings of the 2018 ACM Symposium on Eye Tracking Research & Applications, pp. 29:1–29:9, ACM Association for Computing Machinery (ACM), New York, 2018, ISBN: 978-1-4503-5706-7.
Complex information visualizations, such as thematic maps, encode information using a particular symbology that often requires the use of a legend to explain its meaning. Traditional legends are placed at the edge of a visualization, which can be difficult to maintain visually while switching attention between content and legend.par
Moreover, an extensive search may be required to extract relevant information from the legend. In this paper we propose to consider the user's visual attention to improve interaction with a map legend by adapting both the legend's placement and content to the user's gaze.par
In a user study, we compared two novel adaptive legend behaviors to a traditional (non-adaptive) legend.We found that, with both of our approaches, participants spent significantly less task time looking at the legend than with the baseline approach. Furthermore, participants stated that they preferred the gaze-based approach of adapting the legend content (but not its placement).
Fogliaroni, Paolo; Bucher, Dominik; Jankovic, Nikola; Giannopoulos, Ioannis
Intersections of Our World (Inproceedings)
In: Winter, Stephan; Griffin, Amy; Sester, Monika (Ed.): Proceedings 10th International Conference on Geographic Information Science (GIScience 2018), pp. 3:1–3:15, LIPICS, 114, 2018, ISBN: 978-3-95977-083-5, (Vortrag: 10th International Conference on Geographic Information Science (GIScience 2018), Melbourne; 2018-08-28 -- 2018-08-31).
There are several situations where the type of a street intersections can become very important, especially in the case of navigation studies. The types of intersections affect the route complexity and this has to be accounted for, e.g., already during the experimental design phase of a navigation study. In this work we introduce a formal definition for intersection types and present a framework that allows for extracting information about the intersections of our planet. We present a case study that demonstrates the importance and necessity of being able to extract this information.
Pedestrian Navigation: What Can We Learn From Eye Tracking, Mixed Reality and Machine Learning (Journal Article)
In: Österreichische Zeitschrift für Vermessung und Geoinformation (VGI), vol. 106, no. 3, pp. 220–225, 2018.
Un verschiedene Prozesse wie zum Beispiel die Navigation zu verstehen, ist es entscheidend zu verstehen wie Menschen mit ihrer Umgebung während der Entscheidungsfindung interagieren. Während der räumlichen Entscheidungsfindung interagieren Menschen auch mit räumlichen Daten, die ihnen oft über Display Geräte präsentiert werden.Mit Hilfe von Eye Tracking, Mixed Reality und Machine Learning sind wir in der Lage, ein besseres Verständnis und eine Optimierung der relevanten Interaktionsdialoge zu erzielen, relevante Informationsräume zu klassifizieren sowie Menschen während des Entscheidungsfindungsprozesses zu assistieren.
Spatial Big Data for Human-Computer Interaction (Inproceedings)
In: Raubal, Martin; Wang, Shaowen; Guo, Mengyu; Jonietz, David; Kiefer, Peter (Ed.): Spatial Big Data and Machine Learning in GIScience, pp. 22–24, 2018, (Vortrag: Spatial Big Data and Machine Learning in GIScience, Melbourne, Australien; 2018-08-28).
The importance of spatial data for the area of human-computer interaction is discussed in this vision paper as well as how machine learning and spatial big data can be utilized for optimizing and adapting the interaction modalities in outdoor spaces. This paper briefly introduces and tries to connect previous work in order to highlight the vision towards a space adaptive personalized system and list important research questions.
Duchowski, Andrew T; Krejtz, Krzysztof; Krejtz, Izabela; Biele, Cezary; Niedzielska, Anna; Kiefer, Peter; Raubal, Martin; Giannopoulos, Ioannis
In: CHI 2018, pp. 1–13, ACM, Paper No. 282, 2018, ISBN: 978-1-4503-5620-6, (Vortrag: CHI 2018 - Conference on Human Factors in Computing Systems, Montreal, Canada; 2018-04-21 -- 2018-04-26).
A novel eye-tracked measure of the frequency of pupil diameter oscillation is proposed for capturing what is thought to be an indicator of cognitive load. The proposed metric, termed the Index of Pupillary Activity, is shown to discriminate task difficulty vis-`a-vis cognitive load (if the implied causality can be assumed) in an experiment where participants performed easy and difficult mental arithmetic tasks while fixating a central target (a requirement for replication of prior work). The paper's contribution is twofold: full documentation is provided for the calculation of the proposed measurement which can be considered as an alternative to the existing proprietary Index of Cognitive Activity (ICA). Thus, it is possible for researchers to replicate the experiment and build their own software which implements this measurement. Second, several aspects of the ICA are approached in a more data-sensitive way with the goal of improving the measurement's performance.
Fogliaroni, Paolo; McCutchan, Marvin; Navratil, Gerhard; Giannopoulos, Ioannis
In: Winter, Stephan; Griffin, Amy; Sester, Monika (Ed.): Proceedings 10th International Conference on Geographic Information Science (GIScience 2018), pp. 26:1–26:6, LIPICS, 114, 2018, ISBN: 978-3-95977-083-5, (Vortrag: 10th International Conference on Geographic Information Science (GIScience 2018), Melbourne; 2018-08-28 -- 2018-08-31).
This paper extends previous work concerning intersection classification by including a new set of statistics that enable to describe the structure of a city at a higher level of detail. Namely, we suggest to analyze sequences of intersections of different types. We start with sequences of length two and present a probabilistic model to derive statistics for longer sequences. We validate the results by comparing them with real frequencies. Finally, we discuss how this work can contribute to the generation of virtual cities as well as to spatial configuration search.
Kiefer, Peter; Giannopoulos, Ioannis; Anagnostopoulos, Vasileios Athanasios; Schöning, Johannes; Raubal, Martin
Controllability Matters: The User Experience of Adaptive Maps (Journal Article)
In: Geoinformatica, vol. 21, no. 3, pp. 619–641, 2017.
(Tags: )| |
Kiefer, Peter; Giannopoulos, Ioannis; Raubal, Martin; Duchowski, Andrew T
Eye Ŧracking for Spatial Research: Cognition, Computation, Challenges (Journal Article)
In: Spatial Cognition & Computation, vol. 17, no. 1-2, pp. 1–19, 2017.
(Tags: )| |
Kiefer, Peter; Giannopoulos, Ioannis; Raubal, Martin; Duchowski, Andrew T (Ed.)
vol. 17(1-2), 2017.
(Tags: )| |
Duchowski, Andrew T; Krejtz, Krzysztof; Biele, Cezary; Niedzielska, Anna; Kiefer, Peter; Giannopoulos, Ioannis; Gehrer, Nina; Schönenberg, Michael
An Inverse-Linear Logistic Model of The Main Sequence (Journal Article)
In: Journal of Eye Movement Research, vol. 10, no. 3, pp. 1–19, 2017.
(Tags: )| |
Giannopoulos, Ioannis; Schöning, Johannes; Krüger, Antonio; Raubal, Martin
In: Multimedia Tools and Applications, vol. 75, no. 6, pp. 2913–2929, 2016, ISSN: 1573-7721.
(Tags: )| | |
Eye tracking is one of the most prominent modalities to track user attention while interacting with computational devices. Today, most of the current eye tracking frameworks focus on tracking the user gaze during website browsing or while performing other tasks and interactions with a digital device. Most frameworks have in common that they do not exploit gaze as an input modality. In this paper we describe the realization of a framework named viGaze. Its main goal is to provide an easy to use framework to exploit the use of eye gaze as an input modality in various contexts. Therefore it provides features to explore explicit and implicit interactions in complex virtual environments by using the eye gaze of a user for various interactions. The viGaze framework is flexible and can be easily extended to incorporate other input modalities typically used in Post-WIMP interfaces such as gesture or foot input. In this paper we describe the key components of our viGaze framework and additionally describe a user study that was conducted to test the framework. The user study took place in a virtual retail environment, which provides a challenging pervasive environment and contains complex interactions that can be supported by gaze. The participants performed two gaze-based interactions with products on virtual shelves and started an interaction cycle between the products and an advertisement monitor placed on the shelf. We demonstrate how gaze can be used in Post-WIMP interfaces to steer the attention of users to certain components of the system. We conclude by discussing the advantages provided through the viGaze framework and highlighting the potentials of gaze-based interaction.
Çöltekin, Arzu; Hempel, J; Brychtova, A; Giannopoulos, Ioannis; Stellmach, Sophie; Dachselt, Raimund
Gaze and feet as additional input modalities for interacting with geospatial interfaces (Journal Article)
In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 3, 2016.
Schnitzler, Verena; Giannopoulos, Ioannis; Hölscher, Christoph; Barisic, Iva
In: Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications, pp. 85–93, ACM, Charleston, South Carolina, 2016, ISBN: 978-1-4503-4125-7.
Kiefer, Peter; Giannopoulos, Ioannis; Duchowski, Andrew T; Raubal, Martin
In: Miller, J A; O'Sullivan, D; Wiegand, N (Ed.): Proceedings of the Ninth International Conference on Geographic Information Science (GIScience 2016), pp. 323–337, Springer International Publishing, 2016.
(Tags: )| |
Göbel, Fabian; Giannopoulos, Ioannis; Raubal, Martin
The Importance of Visual Attention for Adaptive Interfaces (Inproceedings)
In: Proceedings of the 18th International Conference on Human-Computer Interaction with Mobile Devices and Services Adjunct, pp. 930–935, ACM, Florence, Italy, 2016, ISBN: 978-1-4503-4413-5.
Rudi, David; Giannopoulos, Ioannis; Kiefer, Peter; Peier, Christian; Raubal, Martin
Interacting with Maps on Optical Head-Mounted Displays (Inproceedings)
In: Proceedings of the 2016 Symposium on Spatial User Interaction, pp. 3–12, ACM, Tokyo, Japan, 2016, ISBN: 978-1-4503-4068-7.
Dingler, Tilman; Kunze, Kai; Niforatos, Evangelos; Gurrin, Cathal; Giannopolos, Ioannis; Dengel, Andreas; Kise, Koichi
ACM, Heidelberg, Germany, 2016, ISBN: 978-1-4503-4462-3.
Duchowski, Andrew T; Jörg, Sophie; Allen, Tyler N; Giannopoulos, Ioannis; Krejtz, Krzysztof
Eye Movement Synthesis (Inproceedings)
In: Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications, pp. 147–154, ACM, Charleston, South Carolina, 2016, ISBN: 978-1-4503-4125-7.
ETH Zurich, 2016.
(Tags: COMPUTER APPLICATIONS IN NAVIGATION; AUGENBEWEGUNGEN (SINNESPHYSIOLOGIE); EYE MOVEMENTS (SENSORY PHYSIOLOGY); COMPUTER VISION + SCENE UNDERSTANDING (ARTIFICIAL INTELLIGENCE); PERVASIVE COMPUTING + UBIQUITOUS COMPUTING (COMPUTER SYSTEMS); HUMAN-COMPUTER INTERACTION, HCI; COMPUTERVISION (KÃœNSTLICHE INTELLIGENZ); COMPUTERANWENDUNGEN IN DER NAVIGATION; PERVASIVE COMPUTING + UBIQUITOUS COMPUTING (COMPUTERSYSTEME))| |