Video results for an Augmented Reality tracking system. A computer tracks a camera and works out a map of the environment in realtime, and this can be used to overlay virtual graphics. Presented at the ISMAR 2007 conference.
This video shows extra video results made at ISMAR. All sequences were processed and recorded live on a dual-core laptop.
http://www.robots .ox.ac.uk/~gk/
Video results for an Augmented Reality tracking system. A computer tracks a camera and works out a map of the environment in realtime, and this can be used to overlay virtual graphics. Presented at the ISMAR 2007 conference.
http://www.robots .ox.ac.uk/~gk/
Position of the camera is tracked in real time while making a sparse 3D map of the scene. Relocalisation is possible after tracking failure. This work was submitted to ICCV 2007. Thanks to the Ashmolean Museum, Oxford for granting permission to film. See my website for more information.
http://www.robots .ox.ac.uk/~bpw/resea rch.htm
A simple Augmented Reality demo using our real-time SLAM system with automatic relocalisation. Oxford University.
See the website for more details
http://www.robots .ox.ac.uk/~bpw/resea rch.htm
Here real-time SLAM is applied to localisation of a wearable camera. The robot has a miniature IEEE1394 camera with a perspective lens. Output from real-time visual SLAM is used to localise the robot and control its fixation point automatically: the robot's camera can be directed to fixate on any of the feature points in its map as the wearer moves around freely.
This video shows a Wiimote controlled pan tilt camera tracking features using
a single camera SLAM system. Further info and software available at http://www.robots.ox .ac.uk/~bob/wiipanti lt.shtml
This video shows how multiple maps can be used to explore large environments, and is an extension to the original Parallel Tracking and Mapping system.
These are the results for the "Video-rate Localization in Multiple Maps for Wearable Augmented Reality" paper presented at ISWC 2008.
http://wwww.robot .ox.ac.uk/~bob
Here a user of a wearable, portable, vision system uses their hand to both guide an active wearable camera and to highlight objects of interest using a grasping vector.
