Learning to Detect Motion Boundaries - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

Learning to Detect Motion Boundaries

Abstract

We propose a learning-based approach for motion boundary detection. Precise localization of motion boundaries is essential for the success of optical flow estimation, as motion boundaries correspond to discontinuities of the optical flow field. The proposed approach allows to predict motion boundaries, using a structured random forest trained on the ground-truth of the MPI-Sintel dataset. The random forest leverages several cues at the patch level, namely appearance (RGB color) and motion cues (optical flow estimated by state-of-the-art algorithms). Experimental results show that the proposed approach is both robust and computationally efficient. It significantly outperforms state-of-the-art motion-difference approaches on the MPI-Sintel and Middlebury datasets. We compare the results obtained with several state-of-the-art optical flow approaches and study the impact of the different cues used in the random forest. Furthermore, we introduce a new dataset, the YouTube Motion Boundaries dataset (YMB), that comprises 60 sequences taken from real-world videos with manually annotated motion boundaries. On this dataset, our approach , although trained on MPI-Sintel, also outperforms by a large margin state-of-the-art optical flow algorithms.
Fichier principal
Vignette du fichier
cvpr15_mobo.pdf (3.66 Mo) Télécharger le fichier
Vignette du fichier
cvpr15_mobo.jpg (29.44 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01142653 , version 1 (15-04-2015)

Identifiers

Cite

Philippe Weinzaepfel, Jerome Revaud, Zaid Harchaoui, Cordelia Schmid. Learning to Detect Motion Boundaries. CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2015, Boston, United States. pp.2578-2586, ⟨10.1109/CVPR.2015.7298873⟩. ⟨hal-01142653⟩
1238 View
4717 Download

Altmetric

Share

Gmail Facebook X LinkedIn More