Improving streaming video segmentation with early and mid-level visual processing
Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt
Standard
Improving streaming video segmentation with early and mid-level visual processing. / Tripathi, Subarna; Hwang, Youngbae; Belongie, Serge; Nguyen, Truong.
I: 2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014, 2014, s. 477-484.Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Improving streaming video segmentation with early and mid-level visual processing
AU - Tripathi, Subarna
AU - Hwang, Youngbae
AU - Belongie, Serge
AU - Nguyen, Truong
PY - 2014
Y1 - 2014
N2 - Despite recent advances in video segmentation, many opportunities remain to improve it using a variety of low and mid-level visual cues. We propose improvements to the leading streaming graph-based hierarchical video segmentation (streamGBH) method based on early and mid level visual processing. The extensive experimental analysis of our approach validates the improvement of hierarchical supervoxel representation by incorporating motion and color with effective filtering. We also pose and illuminate some open questions towards intermediate level video analysis as further extension to streamGBH. We exploit the supervoxels as an initialization towards estimation of dominant affine motion regions, followed by merging of such motion regions in order to hierarchically segment a video in a novel motion-segmentation framework which aims at subsequent applications such as foreground recognition.
AB - Despite recent advances in video segmentation, many opportunities remain to improve it using a variety of low and mid-level visual cues. We propose improvements to the leading streaming graph-based hierarchical video segmentation (streamGBH) method based on early and mid level visual processing. The extensive experimental analysis of our approach validates the improvement of hierarchical supervoxel representation by incorporating motion and color with effective filtering. We also pose and illuminate some open questions towards intermediate level video analysis as further extension to streamGBH. We exploit the supervoxels as an initialization towards estimation of dominant affine motion regions, followed by merging of such motion regions in order to hierarchically segment a video in a novel motion-segmentation framework which aims at subsequent applications such as foreground recognition.
UR - http://www.scopus.com/inward/record.url?scp=84904657523&partnerID=8YFLogxK
U2 - 10.1109/WACV.2014.6836063
DO - 10.1109/WACV.2014.6836063
M3 - Conference article
AN - SCOPUS:84904657523
SP - 477
EP - 484
JO - 2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014
JF - 2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014
T2 - 2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014
Y2 - 24 March 2014 through 26 March 2014
ER -
ID: 302045052