RGBDSLAM - 6DOF SLAM for Kinect-style cameras

RGBDSLAM allows to quickly acquire colored 3D models of objects and indoor scenes with a hand-held Kinect-style camera. It provides a SLAM front-end based on visual features s.a. SURF or SIFT to match pairs of acquired images, and uses RANSAC to robustly estimate the 3D transformation between them. The resulting camera pose graph is then optimized with the SLAM back-end HOG-Man.

Authors
Felix Endres; Juergen Hess; Nikolas Engelhard; Juergen Sturm; Wolfram Burgard;

Get the Source Code!

Long Description
RGBDSLAM allows to quickly acquire colored 3D models of objects and indoor scenes with a hand-held Kinect-style camera. It uses visual features s.a. SURF or SIFT to match pairs of acquired images, and uses RANSAC to robustly estimate the 3D transformation between them. To achieve online processing, the current image is matched only versus a subset of the previous images. Subsequently, it constructs a graph whose nodes correspond to camera views and whose edges correspond to the estimated 3D transformations. The graph is then optimized with HOG-Man to reduce the accumulated pose errors. Further information and installation instructions can be found in the README file and at


Input Data
Monochrome and depth image, colored point cloud

Type of Map
Pose graph with colored point clouds

Hardware/Software Requirements
Developed and tested under Ubuntu (GCC). Requires ROS Diamondback and HOG-Man.

Documentation
RGBDSLAM on ros.org

Papers Describing the Approach
F. Endres, J. Hess, N. Engelhard, J. Sturm, D. Cremers, W. Burgard: An Evaluation of the RGB-D SLAM System, Proc. of the IEEE Int. Conf. on Robotics and Automation (ICRA), 2012 (link)

License Information
This software is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
The authors allow the users of OpenSLAM.org to use and modify the source code for their own research. Any commercial application, redistribution, etc has to be arranged between users and authors individually and is not covered by OpenSLAM.org.

RGBDSLAM is licenced under GPL v.3


*** OpenSLAM.org is not responsible for the content of this webpage ***
*** Copyright and V.i.S.d.P.: Felix Endres; Juergen Hess; Nikolas Engelhard; Juergen Sturm; Wolfram Burgard; ***