Skip to Main content Skip to Navigation
Journal articles

Multi-reference combinatorial strategy towards longer long-term dense motion estimation

Abstract : This paper addresses the estimation of accurate long-term dense motion fields from videos of complex scenes. With computer vision applications such as video editing in mind, we exploit optical flows estimated with various inter-frame distances and combine them through multi-step integration and statistical selection (MISS). In this context, managing numerous combinations of multi-step optical flows requires a complexity reduction scheme to overcome computational and memory issues. Our contribution is two-fold. First, we provide an exhaustive analysis of available single-reference complexity reduction strategies. Second, we propose a simple and efficient alternative related to multi-reference frames multi-step integration and statistical selection (MR-MISS). Our method automatically inserts intermediate reference frames once matching failures are detected to re-generate the motion estimation process and re-correlates the resulting dense trajectories. By this way, it reaches longer accurate displacement fields while efficiently reducing the complexity. Experiments on challenging sequences reveal improved results compared to state-of-the-art methods including existing MISS schemes both in terms of complexity reduction and accuracy improvement (C) 2016 Elsevier Inc. All rights reserved.
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal-univ-rennes1.archives-ouvertes.fr/hal-01374475
Contributor : Laurent Jonchère <>
Submitted on : Monday, November 14, 2016 - 2:34:45 PM
Last modification on : Monday, October 5, 2020 - 9:50:24 AM
Long-term archiving on: : Monday, March 27, 2017 - 8:13:47 AM

File

Multi-reference combinatorial ...
Files produced by the author(s)

Identifiers

Citation

Pierre-Henri Conze, Philippe Robert, Tomas Crivelli, Luce Morin. Multi-reference combinatorial strategy towards longer long-term dense motion estimation. Computer Vision and Image Understanding, Elsevier, 2016, 150, pp.66-80. ⟨10.1016/j.cviu.2016.04.013⟩. ⟨hal-01374475⟩

Share

Metrics

Record views

512

Files downloads

239