CP-Census: A Novel Model for Dense Variational Scene Flow from RGB-D Data

David Ferstl, Gernot Riegler, Matthias Rüther and Horst Bischof

In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.18

Abstract

We present a novel method for dense variational scene flow estimation based a multi-scale Ternary Census Transform in combination with a patchwise Closest Points depth data term. On the one hand, the Ternary Census Transform in the intensity data term is capable of handling illumination changes, low texture and noise. On the other hand, the patchwise Closest Points search in the depth data term increases the robustness in low structured regions. Further, we utilize higher order regularization which is weighted and directed according to the input data by an anisotropic diffusion tensor. This allows to calculate a dense and accurate flow field which supports smooth as well as non-rigid movements while preserving flow boundaries. The numerical algorithm is solved based on a primal-dual formulation and is efficiently parallelized to run at high frame rates. In an extensive qualitative and quantitative evaluation we show that this novel method for scene flow calculation outperforms existing approaches. The method is applicable to any sensor delivering dense depth and intensity data such as Microsoft Kinect or Intel Gesture Camera.

Session

3D and Stereo

Files

Extended Abstract (PDF, 1 page, 1.9M)

Paper (PDF, 11 pages, 2.5M)

Bibtex File

Presentation

Citation

David Ferstl, Gernot Riegler, Matthias Rüther and Horst Bischof. CP-Census: A Novel Model for Dense Variational Scene Flow from RGB-D Data. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.

BibTex

@inproceedings{BMVC.28.18
	title = {CP-Census: A Novel Model for Dense Variational Scene Flow from RGB-D Data},
	author = {Ferstl, David and Riegler, Gernot and Rüther, Matthias and Bischof, Horst},
	year = {2014},
	booktitle = {Proceedings of the British Machine Vision Conference},
	publisher = {BMVA Press},
	editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
	doi = { http://dx.doi.org/10.5244/C.28.18 }
}