Object-level Segmentation of Rgbd Data

  title={Object-level Segmentation of Rgbd Data},
  author={Hai Huang and Hao Jiang and Claus Brenner and Helmut Mayer},
We propose a novel method to segment MicrosoftKinect data of indoor scenes with the emphasis on freeform objects. We use the full 3D information for the scene parsing and the segmentation of potential objects instead of treating the depth values as an additional channel of the 2D image. The raw RGBD image is first converted to a 3D point cloud with color. We then group the points into patches, which are derived from a 2D superpixel segmentation. With the assumption that every patch in the point… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 12 references

A generative statistical approach to automatic 3d building roof reconstruction from laser scanning data

  • H. Huang, C. Brenner, M. Sester
  • ISPRS Journal of Photogrammetry and Remote…
  • 2013
2 Excerpts

An integrated approach for modelling and global registration of point clouds

  • T. Rabbani, S. Dijkman, F. Van den Heuvel, G. Vosselman
  • ISPRS Journal of Photogrammetry and Remote…
  • 2007
2 Excerpts

Similar Papers

Loading similar papers…