In the last few years, the emergence of smartphones equipped with Internet access, high resolution cameras, and positioning sensors provides the possibility for augmented reality (AR) applications in urban settings. An important component of such systems will be the ability of non-expert users to add their own AR content to the system. A comprehensive 3D model of a scene is normally required as part of this authoring process. This can be computationally ex- pensive to compute and unnecessary since often the fac ̧ades within the urban scene are the main reference point for the user. This paper describes a method of authoring augmented reality content based on planar façade extraction from a single image. With this method the extracted plane can be used to create a front parallel view which in turn can be used as a frame of reference for authoring 3D AR content. This approach permits a simplified method for integrating augmented content into the view which can highlight and visualize geographically or contextually meaningful information about the scene. Results presented demonstrate an authoring solution which is easy to use for a non-expert user based on the fact that the façade based infrastructure allows for an intuitive frame of reference. Furthermore, although the underlying representation is not a complete 3D representation of the environment, it still allows the user to cre- ate full 3D AR content.
Content authoring is an important stage in the workflow of creating rich augmented reality applications. In this paper we describe a fac ̧ade-based database infrastructure for authoring and storing 3D content for use in urban environments. It provides frames of reference for the environment as well as a mechanism to match new images with the fac ̧ades and thus retrieving associated 3D content. The infrastructure is flexible in that we can add different 3D “layers” of content on top of the façades and hence opens many possibilities for augmented reality applications in urban environments. Furthermore the system provides a representation suitable for both manual and automatic content authoring.
Slides from our presentation at ISMAR 12 Workshop Authoring Solutions for Augmented Reality
No comments:
Post a Comment