Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Secrets of optical flow estimation and their principles

: Sun, Deqing; Roth, Stefan; Black, Michael

IEEE Computer Society:
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010. DVD-ROM : June 13-18, 2010, San Francisco, CA
New York, NY: IEEE, 2010
ISBN: 978-1-4244-6983-3
ISBN: 1-4244-6983-X
ISSN: 1063-6919
8 pp.
Conference on Computer Vision and Pattern Recognition (CVPR) <28, 2010, San Francisco/Calif.>
Conference Paper
Fraunhofer IGD ()
computer vision; optical flow; performance evaluation; Forschungsgruppe Visual Inference (VINF)

The accuracy of optical flow estimation algorithms has been improving steadily as evidenced by results on the Middlebury optical flow benchmark. The typical formulation, however, has changed little since the work of Horn and Schunck. We attempt to uncover what has made recent advances possible through a thorough analysis of how the objective function, the optimization method, and modern implementation practices influence accuracy. We discover that "classical" flow formulations perform surprisingly well when combined with modern optimization and implementation techniques. Moreover, we find that while median filtering of intermediate flow fields during optimization is a key to recent performance gains, it leads to higher energy solutions. To understand the principles behind this phenomenon, we derive a new objective that formalizes the median filtering heuristic. This objective includes a non-local term that robustly integrates flow estimates over large spatial neighborhoods. By modifying this new term to include information about flow and image boundaries we develop a method that ranks at the top of the Middlebury benchmark.