Harnessing location-context for content-based services in vehicular systems

By incorporating personalised content as context, vehicular telematic services can be made more user-centric, as opposed to vehicle-centric. We develop an ontology based model to integrate both context and content in one unifying framework to facilitate the creation of such services. Scenes captured spontaneously by the user can be a useful index to his or her intent and interests. Our empirical study shows that location-context leads to a higher precision in recognizing these captured scenes. A "tourist information" prototype based on scene recognition is built, to illustrate one such location-enhanced, user-centric service.