Multiple View Geometry in Computer Vision
Multiple View Geometry in Computer Vision
Pose tracking from natural features on mobile phones
ISMAR '08 Proceedings of the 7th IEEE/ACM International Symposium on Mixed and Augmented Reality
Shape recognition and pose estimation for mobile augmented reality
ISMAR '09 Proceedings of the 2009 8th IEEE International Symposium on Mixed and Augmented Reality
Parallel Tracking and Mapping on a camera phone
ISMAR '09 Proceedings of the 2009 8th IEEE International Symposium on Mixed and Augmented Reality
Estimating scale using depth from focus for mobile augmented reality
Proceedings of the 3rd ACM SIGCHI symposium on Engineering interactive computing systems
Proceedings of the 15th ACM on International conference on multimodal interaction
| Hi-index | 0.00 |
One of the key challenges of markerless Augmented Reality (AR) systems, where no a priori information of the environment is available, is map and scale initialization. In such systems, the scale is unknown as it is impossible to determine the scale from a sequence of images alone. Implementing scale is vital for ensuring that augmented objects are contextually sensitive to the environment they are projected upon. In this paper we demonstrate a sensor and vision fusion approach for robust and user-friendly initialization of map and scale. The map is initialized, using inbuilt accelerometers, whilst scale is initialized by the camera auto-focusing capability. The later is possible by applying the Depth From Focus (DFF) method, which was, till now, limited to high precision camera systems. The demonstrated illustrates benefits of such a system, which is running on a commercially available mobile phone Nokia N900.