Efficient Multi-cue Scene Segmentation

  • Timo Scharwächter
  • Markus Enzweiler
  • Uwe Franke
  • Stefan Roth
Conference paper

DOI: 10.1007/978-3-642-40602-7_46

Part of the Lecture Notes in Computer Science book series (LNCS, volume 8142)
Cite this paper as:
Scharwächter T., Enzweiler M., Franke U., Roth S. (2013) Efficient Multi-cue Scene Segmentation. In: Weickert J., Hein M., Schiele B. (eds) Pattern Recognition. GCPR 2013. Lecture Notes in Computer Science, vol 8142. Springer, Berlin, Heidelberg

Abstract

This paper presents a novel multi-cue framework for scene segmentation, involving a combination of appearance (grayscale images) and depth cues (dense stereo vision). An efficient 3D environment model is utilized to create a small set of meaningful free-form region hypotheses for object location and extent. Those regions are subsequently categorized into several object classes using an extended multi-cue bag-of-features pipeline. For that, we augment grayscale bag-of-features by bag-of-depth-features operating on dense disparity maps, as well as height pooling to incorporate a 3D geometric ordering into our region descriptor.

In experiments on a large real-world stereo vision data set, we obtain state-of-the-art segmentation results at significantly reduced computational costs. Our dataset is made public for benchmarking purposes.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Timo Scharwächter
    • 1
  • Markus Enzweiler
    • 1
  • Uwe Franke
    • 1
  • Stefan Roth
    • 2
  1. 1.Environment PerceptionDaimler R&DSindelfingenGermany
  2. 2.Department of Computer ScienceTU DarmstadtDarmstadtGermany

Personalised recommendations