Learning Motion Patterns in Videos

Pavel Tokmakov 1 Karteek Alahari 1 Cordelia Schmid 1
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
Abstract : The problem of determining whether an object is in motion, irrespective of camera motion, is far from being solved. We address this challenging task by learning motion patterns in videos. The core of our approach is a fully convolutional network, which is learned entirely from synthetic video sequences, and their ground-truth optical flow and motion segmentation. This encoder-decoder style architecture first learns a coarse representation of the optical flow field features, and then refines it iteratively to produce motion labels at the original high-resolution. We further improve this labeling with an objectness map and a conditional random field, to account for errors in optical flow, and also to focus on moving "things" rather than "stuff". The output label of each pixel denotes whether it has undergone independent motion, i.e., irrespective of camera motion. We demonstrate the benefits of this learning framework on the moving object segmentation task, where the goal is to segment all objects in motion. Our approach outperforms the top method on the recently released DAVIS benchmark dataset, comprising real-world sequences, by 5.6%. We also evaluate on the Berkeley motion segmentation database, achieving state-of-the-art results.
Type de document :
Communication dans un congrès
CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jul 2017, Honolulu, United States
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01427480
Contributeur : Thoth Team <>
Soumis le : mardi 11 avril 2017 - 17:36:10
Dernière modification le : vendredi 11 août 2017 - 11:35:53
Document(s) archivé(s) le : mercredi 12 juillet 2017 - 13:34:46

Fichier

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

Identifiants

  • HAL Id : hal-01427480, version 2
  • ARXIV : 1612.07217

Collections

Citation

Pavel Tokmakov, Karteek Alahari, Cordelia Schmid. Learning Motion Patterns in Videos. CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jul 2017, Honolulu, United States. 〈hal-01427480v2〉

Partager

Métriques

Consultations de
la notice

765

Téléchargements du document

675