Advertisement

Robust Registration of Kinect Range Data for Sensor Motion Estimation

  • Michał Nowicki
  • Piotr Skrzypczyński
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 226)

Abstract

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.

Keywords

Point Cloud Mobile Robot Iterative Close Point Iterative Close Point Kinect Sensor 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Besl, P.J., McKay, N.D.: A Method for Registration of 3-D Shapes. IEEE Trans. on Pattern Analysis and Machine Intell. 14(2), 239–256 (1992)CrossRefGoogle Scholar
  2. 2.
    Endres, F., Hess, J., Engelhard, N., Sturm, J., Cremers, D., Burgard, W.: An Evaluation of the RGB-D SLAM System. In: Proc. IEEE Int. Conf. on Robot. and Automat., pp. 1691–1696. St. Paul (2012)Google Scholar
  3. 3.
    Fallon, M., Johannsson, H., Brookshire, J., Teller, S., Leonard, J.: Sensor Fusion for Flexible Human-Portable Building-Scale Mapping. In: Proc. IEEE/RSJ Int. Conf. on Intell. Robots and Systems, Vilamoura, pp. 4405–4412 (2012)Google Scholar
  4. 4.
    Fraundorfer, F., Scaramuzza, D.: Visual Odometry: Part II - Matching, Robustness and Applications. IEEE Robotics and Automation Magazine 19(2), 78–90 (2012)CrossRefGoogle Scholar
  5. 5.
    Izadi, S.: KinectFusion: Real-Time 3D Reconstruction and Interaction Using a Moving Depth Camera. In: ACM Symp. on User Interface Software and Technology, New York, pp. 559–568 (2011)Google Scholar
  6. 6.
    Kabsch, W.: A Solution of the Best Rotation to Relate Two Sets of Vectors. Acta Crystallographica 32, 922 (1976)CrossRefGoogle Scholar
  7. 7.
    The Kinect Effect – How the World is Using Kinect (2012), http://www.xbox.com/en-GB/kinect/kinect-effect
  8. 8.
    Lowe, D.G.: Distinctive Image Features from Scale-Invariant Keypoints. Int. Journal of Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  9. 9.
    Nowicki, M., Skrzypczyński, P.: Experimental Verification of a Walking Robot Self-Localization System with the Kinect Sensor, Prace Naukowe Politechniki Warszawskiej – Elektronika. Postȩpy robotyki, Warsaw, pp. 561–572 (2012) (in Polish)Google Scholar
  10. 10.
    Nüchter, N., Feyzabadi, S., Qiu, D., May, S.: SLAM à la Carte – GPGPU for Globally Consistent Scan Matching. In: Proc. 5th European Conf. on Mobile Robots (ECMR), Örebro, pp. 271–276 (2011)Google Scholar
  11. 11.
    Rusinkiewicz, S., Levoy, M.: Eficient Variants of the ICP Algorithm. In: Proc. 3rd Int. Conf. on 3D Digital Imaging and Modeling, Quebec, pp. 145–152 (2001)Google Scholar
  12. 12.
    Rusu, R.B., Cousins, S.: 3D is Here: Point Cloud Library (PCL). In: Proc. IEEE Int. Conf. on Robot. and Automat., Shanghai., pp. 1–4 (2011)Google Scholar
  13. 13.
    Segal, A., Haehnel, D., Thrun, S.: Generalized-ICP. In: Proc. of Robotics: Science and Systems, Seattle (2009)Google Scholar
  14. 14.
    Steder, B., Rusu, R.B., Konolige, K., Burgard, W.: Point Feature Extraction on 3D Range Scans Taking Into Account Object Boundaries. In: Proc. IEEE Int. Conf. on Robot. and Automat., Shanghai, pp. 2601–2608 (2011)Google Scholar
  15. 15.
    Stoyanov, T., Louloudi, A., Andreasson, H., Lilienthal, A.: Comparative Evaluation of Range Sensor Accuracy in Indoor Environments. In: Proc. 5th European Conf. on Mobile Robots (ECMR), Örebro, pp. 19–24 (2011)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  1. 1.Institute of Control and Information EngineeringPoznań University of TechnologyPoznańPoland

Personalised recommendations