User-assisted sparse stereo-video segmentation
File Type:
PDFItem Type:
Conference PaperDate:
2013Access:
openAccessCitation:
Raimbault, F., Pitié, F., Kokaram, A., User-assisted sparse stereo-video segmentation, ACM International Conference Proceeding Series, ACM International Conference, 6-7 Nov, 2013, a3-Download Item:
a3-raimbault.pdf (Published (author's copy) - Peer Reviewed) 6.758Mb
Abstract:
User-assisted Sparse Stereo-video Segmentation
Félix Raimbault, François Pitié and Anil Kokaram
Sigmedia Group
Dept. of Electronic and Electrical Engineering
Trinity College Dublin, Ireland
{raimbauf, fpitie, anil.kokaram}@tcd.ie
ABSTRACT
Motion-based video segmentation has been studied for many years
and remains challenging. Ill-posed problems must be solved when
seeking for a fully automated solution, so it is increasingly popular
to maintain users in the processing loop by letting them set pa-
rameters or draw mattes to guide the segmentation process. When
processing multiple-view videos, however, the amount of user in-
teraction should not be proportional to the number of views. In this
paper we present a novel sparse segmentation algorithm for two-
view stereoscopic videos that maintains
temporal coherence
and
view consistency
throughout. We track feature points on both views
with a generic tracker and analyse the pairwise affinity of both tem-
porally
overlapping
and
disjoint
tracks, whereas existing similar
techniques only exploit the information available when tracks over-
lap. The use of stereo-disparity also allows our technique to process
jointly feature tracks on both views, exhibiting a good view consis-
tency in the segmentation output. To make up for the lack of high
level understanding inherent to segmentation techniques, we allow
the user to refine the output with a
split-and-merge
approach so as
to obtain a desired view-consistent segmentation output over many
frames in a
few clicks
. We present several real video examples to
illustrate the versatility of our technique.
Author's Homepage:
http://people.tcd.ie/akokaramhttp://people.tcd.ie/pitief
Description:
PUBLISHED
Author: KOKARAM, ANIL; PITIE, FRANCOIS
Other Titles:
ACM International Conference Proceeding SeriesACM International Conference
Type of material:
Conference PaperAvailability:
Full text availableKeywords:
Motion-based video segmentationDOI:
http://dx.doi.org/10.1145/2534008.2534027Licences: