Assessment of semantic taxonomies for blind indoor navigation based on a shopping center use case

Abstract

Despite the growing availability of location-based services (LBS) to support pedestrian activities, we know little about the effectiveness of existing geographical web information to assist the indoor navigation of people with special needs such as the visually impaired. To characterize these indoor environments, we surveyed three different specifications about taxonomies for environmental semantic information. Survey results show that even having different scopes, the three studied specifications share considerable environmental semantic information. In order to evaluate the validity of survey results, we created a set of environmental semantic information for a shopping center, and then performed a navigation experiment with 9 visually impaired participants in the same indoor location. A smartphone-based system providing audio navigation assistance based on accurate real-time localization in the shopping center was used to complete navigational tasks. Experiment results show an overall positive assessment from participants about the usefulness of the audio messages used. We present further findings about the assessment of the different audio messages by the study participants.