An algorithm for the selection of route dependent orientation information
This work addresses the need for enhanced spatial cognition tools by providing an incremental extension to existing algorithms for generating more informative route instructions.
The paper tackles the problem of automatically selecting orientation information for route descriptions, extending previous landmark selection algorithms to include salience evaluation of orientation information along routes, and demonstrates its functionality using OpenStreetMap data.
Landmarks are important features of spatial cognition. Landmarks are naturally included in human route descriptions and in the past algorithms were developed to select the most salient landmarks at decision points and automatically incorporate them in route instructions. Moreover, it was shown that human route descriptions contain a significant amount of orientation information and that these orientation information support the acquisition of survey knowledge. Thus, there is a need to extend the landmarks selection in order to automatically select orientation information. In this work we present an algorithm for the computational selection of route dependent orientation information, which extends previous algorithms and includes a salience evaluation of orientation information for any location along the route. We implemented the algorithm and demonstrate the functionality on the basis of OpenStreetMap data.