Learning to Detect Motion Boundaries

Philippe Weinzaepfel 1 Jerome Revaud 1 Zaid Harchaoui 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
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.
Type de document :
Communication dans un congrès
CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2015, Boston, United States. IEEE, Proceedings IEEE Conference on Computer Vision & Pattern Recognition, pp.2578-2586, <10.1109/CVPR.2015.7298873>
Liste complète des métadonnées



https://hal.inria.fr/hal-01142653
Contributeur : Thoth Team <>
Soumis le : mercredi 15 avril 2015 - 16:37:54
Dernière modification le : vendredi 11 août 2017 - 11:53:15
Document(s) archivé(s) le : mardi 18 avril 2017 - 20:36:18

Fichiers

cvpr15_mobo.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

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. IEEE, Proceedings IEEE Conference on Computer Vision & Pattern Recognition, pp.2578-2586, <10.1109/CVPR.2015.7298873>. <hal-01142653>

Partager

Métriques

Consultations de
la notice

1109

Téléchargements du document

5808