Robust Registration of Kinect Range Data for Sensor Motion Estimation

This work concerns the problem of determining the rototranslation between two 3D data sets. The sensor being used is Kinect, which yields large amount of data, thus processing all the point clouds in real-time on a standard PC is impossible. Therefore we analyse and compare two approaches: the standard ICP algorithm, and a method that uses salient point features to reduce the amount of data. To obtain a range data registration procedure, which is both precise and robust to large displacements of the sensor we combine these two methods.

[1]  W. Kabsch A solution for the best rotation to relate two sets of vectors , 1976 .

[2]  Wolfram Burgard,et al.  An evaluation of the RGB-D SLAM system , 2012, 2012 IEEE International Conference on Robotics and Automation.

[3]  Andrew W. Fitzgibbon,et al.  KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera , 2011, UIST.

[4]  Wolfram Burgard,et al.  Point feature extraction on 3D range scans taking into account object boundaries , 2011, 2011 IEEE International Conference on Robotics and Automation.

[5]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Achim J. Lilienthal,et al.  Comparative Evaluation of Range Sensor Accuracy in Indoor Environments , 2011, ECMR.

[7]  Seyedshams Feyzabadi,et al.  SLAM à la carte - GPGPU for Globally Consistent Scan Matching , 2011, ECMR.

[8]  F. Fraundorfer,et al.  Visual Odometry : Part II: Matching, Robustness, Optimization, and Applications , 2012, IEEE Robotics & Automation Magazine.

[9]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[10]  John J. Leonard,et al.  Sensor fusion for flexible human-portable building-scale mapping , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.