Road extraction involves the intricate process of generating road maps automatically through deep learning algorithms. This task, particularly from satellite imagery, presents significant challenges due to various factors like occlusions, shadows, noise, and fluctuating illumination conditions. As a result, achieving complete and accurate road extraction is daunting without relying on manual annotations or imperfect road maps for guidance. One potential strategy to enhance road extraction accuracy is by incorporating partial road maps as supplementary data. These partial maps, sourced from platforms like OpenStreetMap or Google Maps, may not offer complete or pristine representations of roads but can still provide valuable additional information. By integrating these partial maps with satellite images, we can exploit their complementary nature to mitigate uncertainty in the extraction process. It's important to note that while road extraction may be relatively straightforward in some regions, such as rural areas, it becomes significantly more complex in urban or underdeveloped areas. These environments present unique challenges that require sophisticated algorithms and approaches to accurately extract roads from satellite imagery. Key Words: Road Extraction, Satellite Imagery, Google Maps, Open Street Map, Auxiliary information, Disaster management, Occlusions, Illumination, Annotation, Shadow.