Improving accuracy of feature-based RGB-D SLAM by modeling spatial uncertainty of point features

Many recent solutions to the RGB-D SLAM problem use the pose-graph optimization approach, which marginalizes out the actual depth measurements. In this paper we employ the same type of factor graph optimization, but we investigate the gains coming from maintaining a map of RGBD point features and modeling the spatial uncertainty of these features. We demonstrate that RGB-D SLAM accuracy can be increased by employing uncertainty models reflecting the actual errors introduced by measurements and image processing. The new approach is validated in simulations and in experiments involving publicly available data sets to ensure that our results are verifiable.

[1]  John J. Leonard,et al.  Robust real-time visual odometry for dense RGB-D mapping , 2013, 2013 IEEE International Conference on Robotics and Automation.

[2]  Shahram Izadi,et al.  Modeling Kinect Sensor Noise for Improved 3D Reconstruction and Tracking , 2012, 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission.

[3]  Sander Oude Elberink,et al.  Accuracy and Resolution of Kinect Depth Data for Indoor Mapping Applications , 2012, Sensors.

[4]  Moonhong Baeg,et al.  Spatial Uncertainty Model for Visual Features Using a Kinect™ Sensor , 2012, Sensors.

[5]  Michal R. Nowicki,et al.  Combining photometric and depth data for lightweight and robust visual odometry , 2013, 2013 European Conference on Mobile Robots.

[6]  S. Umeyama,et al.  Least-Squares Estimation of Transformation Parameters Between Two Point Patterns , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Wolfram Burgard,et al.  G2o: A general framework for graph optimization , 2011, 2011 IEEE International Conference on Robotics and Automation.

[8]  Luigi di Stefano,et al.  SlamDunk: Affordable Real-Time RGB-D SLAM , 2014, ECCV Workshops.

[9]  Piotr Skrzypczynski,et al.  The importance of measurement uncertainty modelling in the feature-based RGB-D SLAM , 2015, 2015 10th International Workshop on Robot Motion and Control (RoMoCo).

[10]  Kurt Konolige,et al.  Double window optimisation for constant time visual SLAM , 2011, 2011 International Conference on Computer Vision.

[11]  J. M. M. Montiel,et al.  ORB-SLAM: A Versatile and Accurate Monocular SLAM System , 2015, IEEE Transactions on Robotics.

[12]  Wolfram Burgard,et al.  A benchmark for the evaluation of RGB-D SLAM systems , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Andrew W. Fitzgibbon,et al.  Bundle Adjustment - A Modern Synthesis , 1999, Workshop on Vision Algorithms.

[14]  Dieter Fox,et al.  RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments , 2012, Int. J. Robotics Res..

[15]  Jizhong Xiao,et al.  Fast visual odometry and mapping from RGB-D data , 2013, 2013 IEEE International Conference on Robotics and Automation.

[16]  Andrew J. Davison,et al.  A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[17]  Michal R. Nowicki,et al.  On the Performance of Pose-Based RGB-D Visual Navigation Systems , 2014, ACCV.

[18]  Daniel Cremers,et al.  Robust odometry estimation for RGB-D cameras , 2013, 2013 IEEE International Conference on Robotics and Automation.

[19]  Wolfram Burgard,et al.  3-D Mapping With an RGB-D Camera , 2014, IEEE Transactions on Robotics.

[20]  Daniel Cremers,et al.  Submap-Based Bundle Adjustment for 3D Reconstruction from RGB-D Data , 2014, GCPR.

[21]  Andreas Zell,et al.  Using depth in visual simultaneous localisation and mapping , 2012, 2012 IEEE International Conference on Robotics and Automation.

[22]  G. Klein,et al.  Parallel Tracking and Mapping for Small AR Workspaces , 2007, 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.