Department of Electrical Engineering (ISY)

Teaching Stereo Perception to YOUR Robot

Marcus Wallenberg, Per-Erik Forssén
BMVC12, University of Surrey, UK
British Machine Vision Conference (BMVC12)
September 2012

Abstract

This paper describes a method for generation of dense stereo ground-truth using a consumer depth sensor such as the Microsoft Kinect. Such ground-truth allows adaptation of stereo algorithms to a specific setting. The method uses a novel residual weighting based on error propagation from image plane measurements to 3D. We use this ground-truth in wide-angle stereo learning by automatically tuning a novel extension of the best-first-propagation (BFP) dense correspondence algorithm. We extend BFP by adding a coarse-to-fine scheme, and a structure measure that limits propagation along linear structures and flat areas. The tuned correspondence algorithm is evaluated in terms of accuracy, robustness, and ability to generalise. Both the tuning cost function, and the evaluation are designed to balance the accuracy-robustness trade-off inherent in patch-based methods such as BFP.

Full Paper

Portable document format file PDF ()
Poster PDF.

---

Bibtex entry

@InProceedings{wallenberg12,
  author = 	 {Marcus Wallenberg and Per-Erik Forss\'en},
  title = 	 {Teaching Stereo Perception to {YOUR} Robot},
  booktitle = {British Machine Vision Conference ({BMVC}12)},
  year = 	 {2012},
  address = 	 {University of Surrey, UK},
  month = 	 {September},
  organization = {{BMVA}},
  publisher = {{BMVA}},
  isbn = {1-901725-46-4},
  note = 	 {http://dx.doi.org/10.5244/C.26.29}
}