Feature-Cut: Video Object Segmentation Through Local Feature Correspondences.
Citation:
D. Ring, A. Kokaram, Feature-Cut: Video Object Segmentation Through Local Feature Correspondences., Proc. of ICCV International Workshop on Video-oriented Object and Event Classification (VOEC), ICCV International Workshop on Video-oriented Object and Event Classification (VOEC), Kyoto, Japan, September, IEEE Computer Society, 2009Download Item:
Abstract:
Accurately segmenting objects in video is a difficult and
time consuming process in modern post-production houses.
Automatic systems may work for a small number of frames,
but will typically fail over longer video shots. This work
proposes a semi-automatic, feature-based system to perform
object segmentation over longer sequences. The user
manually extracts masks from representative instances of
the object, which are then propagated to the remaining unsegmented
frames and used to bootstrap the automatic segmentation
for these frames. The presented work dramatically
reduces the manual workload required to segment a
video sequence, allowing longer and more accurate object
mattes.
Sponsor
Grant Number
Irish Research Council for Science and Engineering Technology (IRCSET)
Author's Homepage:
http://people.tcd.ie/akokaramDescription:
PUBLISHEDKyoto, Japan
Author: KOKARAM, ANIL; RING, DANIEL
Other Titles:
Proc. of ICCV International Workshop on Video-oriented Object and Event Classification (VOEC)ICCV International Workshop on Video-oriented Object and Event Classification (VOEC)
Publisher:
IEEE Computer SocietyType of material:
Conference PaperAvailability:
Full text availableKeywords:
EngineeringMetadata
Show full item recordLicences: