One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network

Abstract : There is an inherent need for autonomous cars, drones, and other robots to have a notion of how their environment behaves and to anticipate changes in the near future. In this work, we focus on anticipating future appearance given the current frame of a video. Existing work focuses on either predicting the future appearance as the next frame of a video, or predicting future motion as optical flow or motion trajectories starting from a single video frame. This work stretches the ability of CNNs (Convolutional Neural Networks) to predict an anticipation of appearance at an arbitrarily given future time, not necessarily the next video frame. We condition our predicted future appearance on a continuous time variable that allows us to anticipate future frames at a given temporal distance, directly from the input video frame. We show that CNNs can learn an intrinsic representation of typical appearance changes over time and successfully generate realistic predictions at a deliberate time difference in the near future.
Type de document :
Communication dans un congrès
International Conference of Image Analysis and Processing (ICIAP), Sep 2017, Catania, Italy. 2017, Proceedings of the 19th International Conference of Image Analysis and Processing. 〈iciap2017.com〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01567742
Contributeur : Vedran Vukotić <>
Soumis le : lundi 24 juillet 2017 - 13:57:06
Dernière modification le : mercredi 30 août 2017 - 09:40:36

Fichier

Vukotic_iciap2017.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01567742, version 1

Relations

  • est une version de hal-01467064 - Updated NCCV 2016 paper and submitted to an international conference - ICIAP 2017

Citation

Vedran Vukotic, Silvia-Laura Pintea, Christian Raymond, Guillaume Gravier, Jan Van Gemert. One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network. International Conference of Image Analysis and Processing (ICIAP), Sep 2017, Catania, Italy. 2017, Proceedings of the 19th International Conference of Image Analysis and Processing. 〈iciap2017.com〉. 〈hal-01567742〉

Partager

Métriques

Consultations de
la notice

155

Téléchargements du document

22