Thesis supervisor: Csaba Benedek
Web address (URL): https://itk.ppke.hu/en/education/doctoral-school Location of studies (in Hungarian): Pázmány Péter Catholic University Roska Tamás Doctoral School of Technology and Sciences Abbreviation of location of studies: PPKE
Description of the research topic:
Up to date 3D sensors revolutionized the acquisition of environmental information. The onboard Lidar laser scanners, calibrated camera systems and navigation sensors record high frame-rate measurement sequences. However due to their limited spatial resolution, environment analysis purely based on onboard sensor measurements exhibits significant limitations.
The new generation geo-information systems (GIS) store extremely detailed 3D maps about the cities, composed of dense 3D point clouds, registered camera images and semantic metadata.
The main goal of the research work is to facilitate the joint exploitation of the measurements from the cars' instant sensing platforms and the offline spatial database content. We propose new algorithms, which allow self driving cars to obtain in real time relevant GIS information for decision support, and provide opportunities for extending and updating the GIS databases based on the sensor measurements from everyday traffic.
Required language skills: English Recommended language skills (in Hungarian): English Further requirements: Advanced C/C++ programing skills are necessary. Experiences in computer vision, image processing, point cloud based 3D recognition, or 3D reconstruction mean advantage.