Geospatial data conflation is the compilation or reconciliation of two different geospatial datasets covering overlapping regions (Saalfeld, 1988). In general, the goal of conflation is to combine the best quality elements of both datasets to create a composite dataset that is better than either of them. The consolidated dataset can then provide additional information that cannot be gathered from any single dataset.
Based on the types of geospatial datasets dealt with, the conflation technologies can be categorized into the following three groups:
Vector to vector data conflation: A typical example is the conflation of two road networks of different accuracy levels. Figure 1shows a concrete example to produce a superior dataset by integrating two road vector datasets: road network from US Census TIGER/Line files, and road network from the department of...