Thesis supervisor: László Zentai
Location of studies (in Hungarian): Faculty of Informatics, Institute of Cartography and Geoinformatics Abbreviation of location of studies: ELTE
Description of the research topic:
"Maps for navigation have become increasingly important in last time. User expectations of maps also increased. They are not only concerned with the appearance of a specific location/city/road junction, but also with supporting more useful, safer and more efficient navigation functions. There is also a demand for changes in the transport network to be reflected in navigation devices as quick as possible and with high quality. These new requirements led to the able to run quality analyses on the map database (which is supplied by a third partner) and/or the transformed database (used by the navigation system). These analyses are able to identify map anomalies (e.g. incoherent network, inefficient planned route, unclear/unrealistic search results) and propose possible solutions to them. These anomalies complicate/interfere with the driver's specific navigation activities and compromise safe driving. The analyses identify different regular or occurrence-based patterns and correlations. It is follow defining valid controls for the database of the country/relevant area. Naturally these rules follow the specific traffic and network operating rules within a given country.
The aim of the research is to develop algorithms and analytical tools that can analyses the database from third-party partners and list quality errors. As a first step, the aim is to define the important navigation functions (road graph, route planning, navigation messages, address search, POI access) and their most relevant attributes. A country-specific set of rules between these attributes must then be defined, this can be done using machine learning algorithms. Then the qualitative attributes that characteristic the internal consistency/usability/efficiency of the navigation database should be defined based on the relationships between the expected attributes. Based on the measurement of these attributes, error locations and discrepancies should be detected and recorded in a report.
The candidate will be supported in this work by experts from the NNG team. They will share map quality expectations and practical experience of the activities and processes involved in map publishing. They will present established control methods and quality assessment steps. The ultimate goal is to support the work of these professionals with tools that can drastically reduce the time needed for mass audits. This will allow professionals to focus on developing new requirements and expertise."
Required language skills: English Number of students who can be accepted: 1
Deadline for application: 2024-05-31
2024. IV. 17. ODT ülés Az ODT következő ülésére 2024. június 14-én, pénteken 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).
Login
