Probabilistic interactive segmentation for anthropomorphic robots in cluttered environments

  title={Probabilistic interactive segmentation for anthropomorphic robots in cluttered environments},
  author={Herke van Hoof and Oliver Kroemer and Jan Peters},
  journal={2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids)},
Recognition and manipulation of novel objects in human environments are a prerequisite for many tasks of robots. Since objects often occur in clutter, such robots should be capable of segmenting their environment into individual objects before attempting to learn the objects' properties. In this paper, we propose a probabilistic part-based approach to interactive segmentation of cluttered scenes containing multiple novel objects. Our experiments show that our probabilistic approach outperforms… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 32 references

Object segmentation from motion with dense feature matching

  • E. Herbst, X. Ren, D. Fox
  • ICRA Workshop on Semantic Perception, Mapping and…
  • 2012
2 Excerpts

Feature segmentation for object recognition using robot manipulation

  • O. O. Sushkov, C. Sammut
  • Australian Conf. on Robotics and Automation, 2011…
  • 2011

Similar Papers

Loading similar papers…