Abstract
With rapidly widening access to high-capacity geospatial data via high-speed Internet, user demand for multiform and accurate information has increased. Correspondingly, there is a growing need for hybrid map services that can combine heterogeneous data. Conflation, defined as the combining of information from diverse sources so as to reconcile spatial inconsistencies, has emerged to meet that need. In this research, we developed an approach that conflates road maps with aerial images using road intersections as conjugate features. The method has a three-process workflow including preprocessing for road candidate identification, spatial inconsistency removal, and shape disagreement removal. On the basis of overall comparative evaluations of the experimental results with a reference, it was found that the correctness of the conflated road was 36.6% better than that of the original road.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call