Predicting Deeper into the Future of Semantic Segmentation - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2017

Predicting Deeper into the Future of Semantic Segmentation

Abstract

The ability to predict and therefore to anticipate the future is an important attribute of intelligence. It is also of utmost importance in real-time systems, e.g. in robotics or autonomous driving, which depend on visual scene understanding for decision making. While prediction of the raw RGB pixel values in future video frames has been studied in previous work, here we introduce the novel task of predicting semantic segmentations of future frames. Given a sequence of video frames, our goal is to predict segmentation maps of not yet observed video frames that lie up to a second or further in the future. We develop an autoregressive convolutional neural network that learns to iteratively generate multiple frames. Our results on the Cityscapes dataset show that directly predicting future segmentations is substantially better than predicting and then segmenting future RGB frames. Prediction results up to half a second in the future are visually convincing and are much more accurate than those of a baseline based on warping semantic segmentations using optical flow.
Fichier principal
Vignette du fichier
0270.pdf (3.97 Mo) Télécharger le fichier
Vignette du fichier
HAL-logo.png (768.86 Ko) Télécharger le fichier
0270-supp.pdf (2.59 Mo) Télécharger le fichier
17results.gif (135.86 Ko) Télécharger le fichier
Vignette du fichier
17results.jpg (6.54 Ko) Télécharger le fichier
Vignette du fichier
HAL-logo.jpg (111.21 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Format Figure, Image
Origin Files produced by the author(s)
Origin Files produced by the author(s)
Origin Files produced by the author(s)
Format Figure, Image
Origin Files produced by the author(s)
Format Figure, Image
Origin Files produced by the author(s)

Dates and versions

hal-01494296 , version 1 (23-03-2017)
hal-01494296 , version 2 (21-08-2017)

Identifiers

Cite

Pauline Luc, Natalia Neverova, Camille Couprie, Jakob Verbeek, Yann Lecun. Predicting Deeper into the Future of Semantic Segmentation. ICCV 2017 - International Conference on Computer Vision, Oct 2017, Venise, Italy. pp.648-657, ⟨10.1109/ICCV.2017.77⟩. ⟨hal-01494296v2⟩
1781 View
1729 Download

Altmetric

Share

More