The technology of Mobile Mapping System (MMS) is growing rapidly, which can acquire the image sequences and the position data more efficiently and effectively. Thus, the integration of MMS and remote sensing data is an important task in geospatial technologies for various applications, such as detailed road model construction, building up three dimensional attribute databases, and so on. This research integrated MMS data, airborne LIDAR and vector-based maps to reconstruct detailed road models. Because of the diversity and complexity of road types, the primary objective of this research is to reconstruct the detailed road model and build up attribute database. Focus was placed on extracting and recognizing traffic signs automatically from MMS images. The experimental result shows that using proposed algorithms, integrated MMS data and other geo-information can reconstruct highly detailed road models and the target traffic signs can be extracted correctly for attribute database.