A primal-dual framework for real-time dense RGB-D scene flow

Jaimez M, Souiai M, Gonzalez-Jimenez J, Cremers D (2015)

Publication Type: Conference contribution

Publication year: 2015

Journal

Proceedings - IEEE International Conference on Robotics and Automation Institute of Electrical and Electronics Engineers

Publisher: Institute of Electrical and Electronics Engineers Inc.

Book Volume: 2015-June

Pages Range: 98-104

Conference Proceedings Title: Proceedings - IEEE International Conference on Robotics and Automation

Event location: Seattle, WA, USA

ISBN: 9781479969234

DOI: 10.1109/ICRA.2015.7138986

Abstract

This paper presents the first method to compute dense scene flow in real-time for RGB-D cameras. It is based on a variational formulation where brightness constancy and geometric consistency are imposed. Accounting for the depth data provided by RGB-D cameras, regularization of the flow field is imposed on the 3D surface (or set of surfaces) of the observed scene instead of on the image plane, leading to more geometrically consistent results. The minimization problem is efficiently solved by a primal-dual algorithm which is implemented on a GPU, achieving a previously unseen temporal performance. Several tests have been conducted to compare our approach with a state-of-the-art work (RGB-D flow) where quantitative and qualitative results are evaluated. Moreover, an additional set of experiments have been carried out to show the applicability of our work to estimate motion in real-time. Results demonstrate the accuracy of our approach, which outperforms the RGB-D flow, and which is able to estimate heterogeneous and non-rigid motions at a high frame rate.

Involved external institutions

Universidad de Málaga / University of Malaga ES Spain (ES) Technische Universität München (TUM) DE Germany (DE)

How to cite

APA:

Jaimez, M., Souiai, M., Gonzalez-Jimenez, J., & Cremers, D. (2015). A primal-dual framework for real-time dense RGB-D scene flow. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 98-104). Seattle, WA, USA: Institute of Electrical and Electronics Engineers Inc..

MLA:

Jaimez, Mariano, et al. "A primal-dual framework for real-time dense RGB-D scene flow." Proceedings of the 2015 IEEE International Conference on Robotics and Automation, ICRA 2015, Seattle, WA, USA Institute of Electrical and Electronics Engineers Inc., 2015. 98-104.

BibTeX: Download