A benchmark for the evaluation of RGB-D SLAM systems
- Jürgen Sturm, Nikolas Engelhard, F. Endres, W. Burgard, D. Cremers
- Computer ScienceIEEE/RSJ International Conference on Intelligent…
- 24 December 2012
A large set of image sequences from a Microsoft Kinect with highly accurate and time-synchronized ground truth camera poses from a motion capture system is recorded for the evaluation of RGB-D SLAM systems.
An evaluation of the RGB-D SLAM system
- F. Endres, Jürgen Hess, Nikolas Engelhard, Jürgen Sturm, D. Cremers, W. Burgard
- Computer ScienceIEEE International Conference on Robotics and…
- 14 May 2012
We present an approach to simultaneous localization and mapping (SLAM) for RGB-D cameras like the Microsoft Kinect. Our system concurrently estimates the trajectory of a hand-held Kinect and…
3-D Mapping With an RGB-D Camera
- F. Endres, Jürgen Hess, Jürgen Sturm, D. Cremers, W. Burgard
- Computer ScienceIEEE Transactions on robotics
- 1 February 2014
A novel mapping system that robustly generates highly accurate 3-D maps using an RGB-D camera that applies to small domestic robots such as vacuum cleaners, as well as flying robotssuch as quadrocopters.
D Mapping with an RGB-D Camera
- F. Endres, Jürgen Hess, Jürgen Sturm, D. Cremers, W. Burgard
- Computer Science
- 2014
A novel mapping system that robustly generates highly accurate 3D maps using an RGB-D camera that applies to small domestic robots as well as flying robots such as quadrocopters and free-hand reconstruction of detailed 3D models.
Real-time 3D visual SLAM with a hand-held camera
- Nikolas Engelhard, F. Endres, Jürgen Hess, Jürgen Sturm, W. Burgard
- Computer Science
- 2011
Unsupervised discovery of object classes from range data using latent Dirichlet allocation
- F. Endres, Christian Plagemann, C. Stachniss, W. Burgard
- Computer ScienceRobotics: Science and Systems
- 28 June 2009
Practical experiments demonstrate, that the approach is able to learn object class models autonomously that are consistent with the true classifications provided by a human, and furthermore outperforms unsupervised method such as hierarchical clustering that operate on a distance metric.
Monocular range sensing: A non-parametric learning approach
- Christian Plagemann, F. Endres, Jürgen Hess, C. Stachniss, W. Burgard
- Computer ScienceIEEE International Conference on Robotics and…
- 19 May 2008
A novel approach to learning the relationship between range measurements and visual features extracted from a single monocular camera image is presented, using Gaussian processes, a non-parametric learning technique that not only yields the most likely range prediction corresponding to a certain visual input but also the predictive uncertainty.
Learning the dynamics of doors for robotic manipulation
- F. Endres, J. Trinkle, W. Burgard
- Computer ScienceIEEE/RSJ International Conference on Intelligent…
- 1 November 2013
This paper presents an approach to learn a dynamic model of a door from sensor observations and utilize it for effectively swinging the door open to a desired angle and applies Gaussian process regression to learn the deceleration of the door with respect to position and velocity.
A nonparametric learning approach to range sensing from omnidirectional vision
- Christian Plagemann, C. Stachniss, Jürgen Hess, F. Endres, Nathan Franklin
- Computer ScienceRobotics Auton. Syst.
- 1 June 2010
W-RGB-D: Floor-plan-based indoor global localization using a depth camera and WiFi
- Seigo Ito, F. Endres, M. Kuderer, G. D. Tipaldi, C. Stachniss, W. Burgard
- Computer ScienceIEEE International Conference on Robotics and…
- 29 September 2014
W-RGB-D is presented, a new method for indoor global localization based on WiFi and an RGB-D camera that is suitable to be used with abstract floor plans and the use of WiFi information as proposed improves the localization in terms of convergence speed and quality of the solution.
...
...