The search functionality is under construction.
The search functionality is under construction.

Large Displacement Dynamic Scene Segmentation through Multiscale Saliency Flow

Yinhui ZHANG, Zifen HE

  • Full Text Views

    0

  • Cite this

Summary :

Most unsupervised video segmentation algorithms are difficult to handle object extraction in dynamic real-world scenes with large displacements, as foreground hypothesis is often initialized with no explicit mutual constraint on top-down spatio-temporal coherency despite that it may be imposed to the segmentation objective. To handle such situations, we propose a multiscale saliency flow (MSF) model that jointly learns both foreground and background features of multiscale salient evidences, hence allowing temporally coherent top-down information in one frame to be propagated throughout the remaining frames. In particular, the top-down evidences are detected by combining saliency signature within a certain range of higher scales of approximation coefficients in wavelet domain. Saliency flow is then estimated by Gaussian kernel correlation of non-maximal suppressed multiscale evidences, which are characterized by HOG descriptors in a high-dimensional feature space. We build the proposed MSF model in accordance with the primary object hypothesis that jointly integrates temporal consistent constraints of saliency map estimated at multiple scales into the objective. We demonstrate the effectiveness of the proposed multiscale saliency flow for segmenting dynamic real-world scenes with large displacements caused by uniform sampling of video sequences.

Publication
IEICE TRANSACTIONS on Information Vol.E99-D No.7 pp.1871-1876
Publication Date
2016/07/01
Publicized
2016/03/30
Online ISSN
1745-1361
DOI
10.1587/transinf.2015EDP7482
Type of Manuscript
PAPER
Category
Pattern Recognition

Authors

Yinhui ZHANG
  Kunming University of Science and Technology
Zifen HE
  Kunming University of Science and Technology

Keyword