Automated updating of road network databases: road segment grouping using snap-drift neural network

Presented in this paper is a major step towards an innovative solution of GIS road network
databases updating which moves away from existing traditional methods where vendors of road network
databases go through the time consuming and logistically challenging process of driving along roads to
register changes or GIS road network update methods that are exclusively tied to remote sensing images.
Our proposed road database update solution would allow users of GIS road network dependent
applications (e.g. in-car navigation system) to passively collect characteristics of any “unknown route”
(roads not in the database) on behalf of the provider. These data are transferred back to the provider and
inputted into an artificial neural net (ANN) which decides, along with similar track data provided by other
service users, whether to automatically update (add) the “unknown road” to the road database on
probation allowing subsequent users to see the road on their system and use it if need be. At a later stage
when there is enough certainty on road geometry and other characteristics the probationary flag could be
lifted and permanently added to the road network database. Towards this novel approach we mimicked
two journey scenarios covering two test sites and aimed to group the road segments from the journey into
their respective road types using the snap-drift neural network (SDNN). The performance of the SDNN is
presented and its potential in the proposed solution is investigated.

Citation:
Ekpenyong, F. et al. (2007) ‘Automated updating of road network databases: road segment grouping using snap-drift neural network’ Proceedings of Advances in Computing and Technology, (AC&T) The School of Computing and Technology 2nd Annual Conference, University of East London, pp.160-167.