Abstract. Outdoor augmented reality applications project information of interest onto views of the world in real-time. Their core challenge is recognizing the meaningful objects present in the current view and retrieving and overlaying pertinent information onto such objects. In this paper we report on the development of a framework for mobile outdoor augmented reality application, applied to the overlay of peak information onto views of mountain landscapes. The resulting app operates by estimating the virtual panorama visible from the viewpoint of the user, using an online Digital Terrain Model (DEM), and by matching such panorama to the actual image framed by the camera. When a good match is found, meta-data from the DEM (e.g, peak name, altitude, distance) are projected in real time onto the view. The application, besides providing a nice experience to the user, can be employed to crowdsource the collection of annotated mountain images for environmental applications.

Mobile Augmented Reality (AR) apps promote a new way of marketing the touristic offer of a territory, by overlaying useful information directly on top of what the user sees. These apps analyze the sensor readings (GPS position and phone orientation) and possibly also the camera view, to understand what the user is watching and enrich the view with contextual information to enable knowledge acquisition and exploration. Developing mobile AR apps poses several challenges related to the acquisition, selection, transmission and display of information, which get more demanding in mountain applications where usage without Internet connectivity is a strong requirement. This paper discusses the experience of a real world mobile AR application for mountain tourists, from its design to the feedback from the community of users.

No abstract

Abstract. Outdoor augmented reality applications are an emerging class of software systems that demand the fast identification of natural objects, such as plant species or mountain peaks, in low power mobile devices. Convolutional Neural Networks (CNN) have exhibited superior performance in a variety of computer vision tasks, but their training is a labor intensive task and their execution requires non negligible memory and CPU resources. This paper presents the results of training a CNN for the fast extraction of mountain skylines, which exhibits a good balance between accuracy (94,45% in best conditions and 86,87% in worst conditions) and runtime execution overhead (273 ms on a Nexus 6 mobile phone), and thus has been exploited for implementing a real-world augmented reality applications for mountain peak recognition running on low to mid-end mobile phones.

No abstract