Accelerating Template-Based Matching on the GPU for AR Applications

Recently researchers have shown that it is possible to use GPU hardware for image processing and computer vision algorithms. We have been exploring how to use GPU hardware to improve marker- based tracking for AR Applications. In this paper we describe our findings and explored issues in the context of a standard fiducial tracking pipeline. We demonstrate the implementation of a template matching process on the GPU and the performance improvement gained in comparison to a traditional CPU implementation.

[1]  Steve Mann,et al.  Mediated reality using computer graphics hardware for computer vision , 2002, Proceedings. Sixth International Symposium on Wearable Computers,.

[2]  Hirokazu Kato,et al.  Marker tracking and HMD calibration for a video-based augmented reality conferencing system , 1999, Proceedings 2nd IEEE and ACM International Workshop on Augmented Reality (IWAR'99).

[3]  Mark Fiala,et al.  Comparing ARTag and ARToolkit Plus fiducial marker systems , 2005, IEEE International Workshop on Haptic Audio Visual Environments and their Applications.

[4]  Patrick Horain,et al.  GPUCV: A Framework for Image Processing Acceleration with Graphics Processors , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[5]  Vincent Lepetit,et al.  Monocular Model-Based 3D Tracking of Rigid Objects: A Survey , 2005, Found. Trends Comput. Graph. Vis..

[6]  Yakup Genc,et al.  GPU-based Video Feature Tracking And Matching , 2006 .