Vision-based location positioning using augmented reality for indoor navigation

In this paper, we propose a vision-based location positioning system using augmented reality technique for indoor navigation. The proposed system automatically recognizes a location from image sequences taken of indoor environments, and it realizes augmented reality by seamlessly overlaying the user´s view with location information. To recognize a location, we pre-constructed an image database and location model, which consists of locations and paths between locations, of an indoor environment. Location is recognized by using prior knowledge about the layout of the indoor environment. The image sequence is obtained by a wearable mobile PC with camera, which transmits the images to remote PCs for processing. The remote PCs perform marker detection, image sequence matching, and location recognition. The remote PCs transmit the recognized location information to the wearable mobile PC. The system provides the ability to identify similar locations in the image database and display location-related information. Accurate and efficient location positioning is achieved by using several vision-based techniques. The proposed system was tested in an indoor environment and achieved an average location recognition success rate of 89%. The proposed system could be applied to various consumer applications including the door plate system, notice board system, shopping assistance system, and bus service route guide system, among others¹.