Identifying Landmark Candidates Beyond Toy Examples

Abstract

Incorporating references to landmarks in navigation systems requires having data on potential landmarks in the first place. While there have been many approaches in the scientific literature for identifying landmark candidates, these have hardly been picked up in actual, running systems. One major obstacle for this to happen may be that most—if not all—approaches presented so far are not scalable due to their underlying data requirements. In this paper, I will critically discuss existing approaches in light of their scalability. I will then suggest a way forward to more scalable solutions by combining in a smart way aspects of different approaches.