Το work with title Informational system for managing photos and spatial information using sensors, ontologies and semantic maps by Foukarakis Michail is licensed under Creative Commons Attribution 4.0 International
Bibliographic Citation
Μιχαήλ Φουκαράκης, "Πληροφοριακό σύστημα διαχείρισης φωτογραφιών και χωρικής πληροφορίας με χρήση αισθητήρων, οντολογιών και σημασιολογικών χαρτών", Μεταπτυχιακή Διατριβή, Τμήμα Ηλεκτρονικών Μηχανικών και Μηχανικών Υπολογιστών, Πολυτεχνείο Κρήτης, Χανιά, Ελλάς, 2009.
https://doi.org/10.26233/heallink.tuc.13504
With the current developments in the digital photography domain, the task of capturing, storingand sharing photographic content has been simplified and the use of digital devices for this purpose is now widespread. This has led to the outstanding increase of the size of user personal photo collections, increasing the need to better organize, annotate, index and browse the photos.Moreover, the technological advancements related to the digital image capturing devices have allowed them to interoperate with an increasing number of internal or external sensors, giving them additional capabilities for capturing and understanding the image taking context. What ismissing is an attempt to take advantage of these new capabilities and build a system for efficient management of the ever-increasing media content.This thesis proposes a framework for semantic spatial information processing. The framework exploits the modern digital cameras' potential for capturing contextual parameters through the use of sophisticated sensor devices, information found in specially annotated semantic maps and industrial standards. The objective is to effectively manage and associate the information andsemantic objects contained in both the semantic maps and the pictures. In addition, the framework employs the use of image processing and other algorithms to enable the automatic annotation of the photos.The framework is generic enough to allow different system implementations and a system for demonstrating its ideas was created for the purposes of this thesis. The system implementation provides a picture database that allows users to store and view their photos. Along with the photos,the users can view personalized semantic maps, annotated with semantic objects described using ontologies. These maps are supplied from a remote server. Photos with position only information or both position and direction information can be visualized on top of the maps and be associated with semantic objects. Finally, several algorithms that allow interactive exploration of the picture contents have been implemented.Experimentation with a modern digital camera and external sensors has been conducted to test the usefulness of the system in the tourism domain and to show the effectiveness of the implemented algorithms.