RMSD: A 3D Real-Time Mid-level Scene Description System

  • Kristiyan Georgiev
  • Rolf Lakaemper
Part of the Cognitive Systems Monographs book series (COSMOS, volume 23)


This paper introduces a system for real-time, visual 3D scene description. A scene is described by planar patches and conical objects (cylinders, cones and spheres). The system makes use of sensor’s natural point order, dimensionality reduction and fast incremental model update (in O(1)) to first build 2D geometric features. These features approximate the original data and form candidate sets of possible 3D object models. The candidate sets are used by a region growing algorithm to extract all targeted 3D objects. This two step (raw data to 2D features to 3D objects) approach is able to process 30 frames per second on Kinect depth data, which allows for real-time tracking and feature based robot mapping based on 3D range data.


Point Cloud Mobile Robot Planar Patch Scene Description Conical Object 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fitzgibbon, A., Pilu, M., Fisher, R.: Direct least square fitting of ellipses. IEEE Transactions on Pattern Analysis and Machine Intelligence 21(5), 476–480 (1999), doi:10.1109/34.765658CrossRefGoogle Scholar
  2. 2.
    Gath, I., Hoory, D.: Fuzzy clustering of elliptic ring-shaped clusters. Pattern Recognition Letters 16(7), 727–741 (1995),, doi:10.1016/0167-8655(95)00030-KCrossRefGoogle Scholar
  3. 3.
    Georgiev, K., Creed, R., Lakaemper, R.: Fast plane extraction in 3d range data based on line segments. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS (2011)Google Scholar
  4. 4.
    Georgiev, K., Lakaemper, R.: Real-time 3d scene description using spheres, cones and cylinderss - submitted. In: ICRA 2013 Workshop on Mobile Robot Navigation and Mapping (2013)Google Scholar
  5. 5.
    Halir, R., Flusser, J.: Numerically stable direct least squares fitting of ellipses (1998)Google Scholar
  6. 6.
    Bookstein, L.F.: Fitting conic sections to scattered data. Computer Graphics and Image Processing 9(1), 56–71 (1979),, doi:10.1016/0146-664X(79)90082-0CrossRefGoogle Scholar
  7. 7.
    Lakaemper, R., Jan Latecki, L.: Using extended em to segment planar structures in 3d. In: ICPR 2006: Proceedings of the 18th International Conference on Pattern Recognition, pp. 1077–1082. IEEE Computer Society, Washington, DC (2006)Google Scholar
  8. 8.
    Nguyen, V., Gächter, S., Martinelli, A., Tomatis, N., Siegwart, R.: A comparison of line extraction algorithms using 2d range data for indoor mobile robotics. Auton. Robots 23(2), 97–111 (2007), doi:
  9. 9.
    Nuechter, A.: 3D Robotic Mapping: The Simultaneous Localization and Mapping Problem with Six Degrees of Freedom. Springer Publishing Company, Incorporated (2009)Google Scholar
  10. 10.
    Poppinga, J., Vaskevicius, N., Birk, A., Pathak, K.: Fast plane detection and polygonalization in noisy 3d range images, pp. 3378–3383 (2008)Google Scholar
  11. 11.
    Rosin, P., West, G.: Nonparametric segmentation of curves into various representations. IEEE Transactions on Pattern Analysis and Machine Intelligence 17(12), 1140–1153 (1995), doi:10.1109/34.476507CrossRefGoogle Scholar
  12. 12.
    Rusu, R., Blodow, N., Marton, Z., Beetz, M.: Close-range scene segmentation and reconstruction of 3d point cloud maps for mobile manipulation in domestic environments. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009, pp. 1–6 (2009), doi:10.1109/IROS.2009.5354683Google Scholar
  13. 13.
    Vandorpe, J., Van Brussel, H., Xu, H.: Exact dynamic map building for a mobile robot using geometrical primitives produced by a 2d range finder, vol. 1, pp. 901–908 (1996), doi:10.1109/ROBOT.1996.503887Google Scholar
  14. 14.
    Weingarten, J., Gruener, G.: A fast and robust 3d feature extraction algorithm for structured environment reconstruction. In: Reconstruction, 11th International Conference on Advanced Robotics, ICAR (2003)Google Scholar
  15. 15.
    Werman, M., Geyzel, Z.: Fitting a second degree curve in the presence of error. IEEE Transactions on Pattern Analysis and Machine Intelligence 17(2), 207–211 (1995), doi:10.1109/34.368167CrossRefGoogle Scholar
  16. 16.
    Wu, W.Y., Wang, M.J.J.: Elliptical object detection by using its geometric properties. Pattern Recognition 26(10), 1499–1509 (1993),, doi:10.1016/0031-3203(93)90155-PCrossRefGoogle Scholar
  17. 17.
    Yip, R.K., Tam, P.K., Leung, D.N.: Modification of hough transform for circles and ellipses detection using a 2-dimensional array. Pattern Recognition 25(9), 1007–1022 (1992),, doi:10.1016/0031-3203(92)90064-PCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  1. 1.CIS DepartmentTemple UniversityPhiladelphiaUSA

Personalised recommendations