Thesis supervisor: Márton Szemenyei
Location of studies (in Hungarian): Department of Control Engineering and Information Technology Abbreviation of location of studies: IIT
Description of the research topic:
The advancement of modern machine learning-based methods and the enabling hardware infrastructure (general purpose parallel computing devices, memory and embedded solutions) opened numerous possibilities for researching computer vision systems. The methods relying on deep neural networks to process visual information have greatly contributed to the advancement of the navigation and control methods of autonomous vehicles.
Nowadays, a novel research direction is to exploit the possibilities of using cooperating vehicles as separate data sources. The use of separate data points as auxiliary information and integrated processing of these data is a major research goal in the field a computer vision.
The goal of this research is to create novel computer vision or image synthesis methods for autonomous driving tasks that effectively support the integration necessary for multi-agent vision, or are useful for generating data to train the above methods.
Required language skills: english Number of students who can be accepted: 3