Numerous navigation applications rely on data from global navigation satellite systems (GNSS), even though their accuracy is compromised in urban areas, posing a significant challenge, particularly for precise autonomous car localization. Extensive research has focused on enhancing outcomes by integrating various sensor types to address this. This thesis introduces a novel approach for car localization, leveraging image features that correspond with highly detailed semantic 3D building models. The core concept involves augmenting accuracy by incorporating prior environmental knowledge into calculations. The study assesses outcomes using Level-of-Detail 2 (LoD2) and Level-of-Detail 3 (LoD3) models, examining whether models enriched with facades yield superior accuracy. This examination encompasses diverse methods, including off-the-shelf feature matching and machine learning, facilitating comprehensive analysis and discussion. The results of the thesis have an impact for the field of navigation in areas where GNSS is not available.     «

Numerous navigation applications rely on data from global navigation satellite systems (GNSS), even though their accuracy is compromised in urban areas, posing a significant challenge, particularly for precise autonomous car localization. Extensive research has focused on enhancing outcomes by integrating various sensor types to address this. This thesis introduces a novel approach for car localization, leveraging image features that correspond with highly detailed semantic 3D building models. T...     »