Top view of a 3D map generated by walking through the lab carrying the depth camera underlying Kinect. The system automatically estimates the motion of the camera and detects loop closures, which help it to globally align the camera frames. No external information or sensor is used.
Click http://www.cs.washington.edu/ai/Mobile_Robotics/projects/rgbd-3d-mapping/ to download a research paper describing the approach.
Collaboration between Intel Labs Seattle and University of Washington Department of Computer Science & Engineering.