Automatically and Efficiently Matching Road Networks with Spatial Attributes in Unknown Geometry Systems

Vast amount of geospatial datasets are now available through numerous public and private organizations. These datasets usually cover different areas, have different accuracy and level of details, and are usually provided in the vector data format, where the latitude and longitude of each object is clearly specified. However, there are scenarios in which the spatial attributes of the objects are intentionally transformed to a different, and usually unknown, (alien) system. Moreover, it is possible that the datasets were generated from a legacy system or are represented in a native coordinate system. An example of this scenario is when a very accurate vector data representing the road network of a portion of a country is obtained with unknown coordinate. In this paper, we propose a solution that can efficiently and accurately find the area that is covered by this vector data simply by matching it with the (possibly inaccurate and abstract) data with known geocoordinates. In particular, we focus on vector datasets that represent road networks and our approach identifies the exact location of the vector dataset of alien system by comparing the distribution of the detected road intersection points between two datasets. Our experiment results show that our technique can match road vector datasets that are composed of thousands of arcs in a relatively short time with 91% precision and 92.5% recall for the matched road feature points.