RGB-D Dense Point Cloud Mapping

Peter Henry, Michael Krainin, Evan Herbst, Xiaofeng Ren (Intel), Dieter Fox

{peter, mkrainin, eherbst, fox} at cs dot washington dot edu

The current webpage for the project is here: link

Project Description

The goal of this research is to create dense 3D point cloud maps of building interiors using newly available inexpensive depth cameras. We use a reference design that is equivalent to the sensor in the Microsoft Kinect. These cameras provide depth information aligned with image pixels from a standard camera. We refer to this as RGB-D data (for Red, Green, Blue plus Depth).

Our paper at ISER 2010 describes our approach. [pdf]

We have recently collaborated with a team at MIT using a Kinect mounted on a quadrotor to localize and build 3D maps using our system as shown in the first video. More information on this collaboration is available here

This work was published at ISRR 2011. [pdf]

Also see the related interactive mapping project page.