Outdoor augmented reality using optical see-through HMD system for visualizing building information

With the development of Information Technologies (IT), a need for new methods to visualize digital information has appeared in architectural and urban field. Augmented Reality (AR) technology, that overlays computer graphics on real world scenes, can be used to satisfy the need. AR-systems can use a wide variety of displays with different characteristics and limitations. For example, most common AR mobile applications, that use devices such as smartphones, occupy both hands of the operator. On the other hand, Head Mounted Displays (HMD) allow more freedom of movement to the user. In this paper, an outdoor AR system for visualizing building information is proposed and implemented. The proposed system uses optical see-through HMD to facilitate visualization, conception and communication about building information by augmenting virtual models on real scenes while giving the users free movement capability. To realize the system, a marker-less AR, which was based on local feature image registration and Structure from Motion (SfM) technologies, was developed. In our proposed method, in the preprocessing step, using a number of photographs from several viewpoints, a point cloud representation of a building is reconstructed by SfM. Then, in the main process, the local features of the live video image of HMD are extracted in real time and are associated with photographs for SfM using image recognition algorithms (such as SURF). Finally, a label which has information for assessing and rating the environmental performance are rendered in the optical see-thorough HMD.

[1]  Shun Watanabe Simulating 3d architecture and urban landscapes in real space , 2011 .

[2]  Tobias Höllerer,et al.  Wide-area scene mapping for mobile visual tracking , 2012, 2012 IEEE International Symposium on Mixed and Augmented Reality (ISMAR).

[3]  Stephen DiVerdi,et al.  Annotation in outdoor augmented reality , 2009, Comput. Graph..

[4]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Frank Dellaert,et al.  Structure from motion without correspondence , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[6]  Gudrun Klinker,et al.  Tangible Mixed Reality On-Site: Interactive Augmented Visualisations from Architectural Working Models in Urban Design , 2015 .

[7]  Henry Fuchs,et al.  Optical Versus Video See-Through Head-Mounted Displays in Medical Visualization , 2000, Presence: Teleoperators & Virtual Environments.

[8]  Steven Zhiying Zhou,et al.  Positioning, tracking and mapping for outdoor augmentation , 2010, 2010 IEEE International Symposium on Mixed and Augmented Reality.

[9]  Tomohiro Fukuda,et al.  An invisible height evaluation system for building height regulation to preserve good landscapes using augmented reality , 2011 .

[10]  Jannick P. Rolland,et al.  Optical versus Video See-Through Head-Mounted Displays , 2001 .

[11]  Tom Drummond,et al.  Going out: robust model-based tracking for outdoor augmented reality , 2006, 2006 IEEE/ACM International Symposium on Mixed and Augmented Reality.