A point cloud model of the author

As observed by the forward stereo camera of the GROK2 robot. This is a composite "mind's eye" view generated from observations in several different pan and tilt positions. There are some depth errors around the computer monitor, but the depth estimates for most of the scene look reasonable.

The points were exported in X3D format, then viewed using the MeshLab utility.





Also here is a point cloud view from the Rodney robot situated on the desktop. This uses the Minoru webcam which has a shorter baseline distance of 6cm, so the depth resolution is not as good as from GROK2. The original intention with the Rodney robot was just to be able to identify objects within a short range on the desktop, so longer ranges aren't very important anyway. The large black object on the right is the giraffe-like "neck" of the GROK2 robot.





Undoubtedly the quality of the imager on the Quickcam 9000 is much superior to that on the Minoru, especially under low artificial lighting conditions.