• DOI:10.1007/978-3-642-40602-7_46
Corpus ID: 8784827

Efficient Multi-cue Scene Segmentation

@inproceedings{Scharwchter2013EfficientMS,
  title={Efficient Multi-cue Scene Segmentation},
  author={Timo Scharw{\"a}chter and M. Enzweiler and Uwe Franke and S. Roth},
  booktitle={GCPR},
  year={2013}
}

• Timo Scharwächter, M. Enzweiler, +1 author S. Roth
• Published in GCPR 2013
• Computer Science

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… Expand

View via Publisher

gris.informatik.tu-darmstadt.de

Save to Library

Create Alert

Cite

Launch Research Feed