Παρουσίαση Διδακτορικής Διατριβής Κ. Γεωργίου Πετράκη, Σχολή Μηχοπ

This dissertation focuses on the development of a visual localization framework based on deep learning to enhance scene understanding and the potential of autonomous navigation in challenging unstructured environments. It is divided into five parts, including the design of training and evaluation datasets, implementation and improvement of a keypoint detection and description neural network, implementation and development of a lightweight neural network for visual localization, development of a lightweight encoder-decoder architecture for lunar ground segmentation, and development of a precise positioning and mapping alternative for GNSS-denied environments.