Track to the Future: Spatio-temporal Video Segmentation with Long-range Motion Cues - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

Track to the Future: Spatio-temporal Video Segmentation with Long-range Motion Cues

Abstract

Video provides not only rich visual cues such as motion and appearance, but also much less explored long-range temporal interactions among objects. We aim to capture such interactions and to construct a powerful intermediate-level video representation for subsequent recognition. Motivated by this goal, we seek to obtain spatio-temporal oversegmentation of a video into regions that respect object boundaries and, at the same time, associate object pixels over many video frames. The contributions of this paper are two-fold. First, we develop an efficient spatiotemporal video segmentation algorithm, which naturally incorporates long-range motion cues from the past and future frames in the form of clusters of point tracks with coherent motion. Second, we devise a new track clustering cost function that includes occlusion reasoning, in the form of depth ordering constraints, as well as motion similarity along the tracks. We evaluate the proposed approach on a challenging set of video sequences of office scenes from feature length movies.
Fichier principal
Vignette du fichier
lezama11.pdf (1.07 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-00817961 , version 1 (17-10-2013)

Identifiers

Cite

Jose Lezama, Karteek Alahari, Josef Sivic, Ivan Laptev. Track to the Future: Spatio-temporal Video Segmentation with Long-range Motion Cues. CVPR - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2011, Colorado Springs, United States. pp.3369 - 3376, ⟨10.1109/CVPR.2011.6044588⟩. ⟨hal-00817961⟩
485 View
597 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More