Description:
The paper describes a method to integrate object detection, recognition
and 3D localization, with a monocular SLAM system. The objects make
the tracking over short timescales more robust and accurate. It
also provides the user with richer information about their
environment.

The video compares the monocular SLAM system running with and without
object detection in a spit-screen view. The system without the object
detection looses track due to insufficient features, and at this
point the video is slowed down to highlight this. The system with the
object detection continues and at the end of the video it has
successfully detected all five objects and accurately localized them
in the world.

Player Information: 
This video is in MPEG-4 format and should play on, MPlayer, Xine,
Kaffeine, VLC, Winamp, Windows Media Player, and probably others.

Contact Information:
Bob Castle's Homepage: http://www.robots.ox.ac.uk/~bob/
Active Vision Lab Homepage: http://www.robots.ox.ac.uk/ActiveVision/




Attachment filename: 1400_VI.mpeg (5213066 Bytes)