Model based segmentation of motion fields in compressed video sequences using partition projection and relaxation
Treetasanatavorn S, Rauschenbach U, Heuer A, Kaup A (2005)
Publication Status: Published
Publication Type: Conference contribution, Conference Contribution
Publication year: 2005
Book Volume: 5960
Pages Range: 111-120
Event location: Beijing
DOI: 10.1117/12.631458
Abstract
In the context of visual signal analysis for media adaptation, this paper presents a stochastic method for segmentation of motion vector fields or as known as displacement fields in compressed videos. The addressed field sequence is analysed and partitioned to temporally associated, motion-semantic regions by three analysis steps. The global motion based reliability analysis assesses the reliability extent of each encoded displacement vector. Upon this measure array, an initial partition is approximated by the region displacement prediction. The subsequent relaxation procedure optimises the partition shape, coverage, and location using the stochastic motion coherency model and the second-order random field based contour smoothness. The visually convincing results are demonstrated from the standard sequences.
Authors with CRIS profile
How to cite
APA:
Treetasanatavorn, S., Rauschenbach, U., Heuer, A., & Kaup, A. (2005). Model based segmentation of motion fields in compressed video sequences using partition projection and relaxation. In Li S.; Pereira F.; Shum H.Y.; Tescher A.G. (Eds.), Proceedings of the Visual Communications and Image Processing 2005 (pp. 111-120). Beijing, CN.
MLA:
Treetasanatavorn, Siripong, et al. "Model based segmentation of motion fields in compressed video sequences using partition projection and relaxation." Proceedings of the Visual Communications and Image Processing 2005, Beijing Ed. Li S.; Pereira F.; Shum H.Y.; Tescher A.G., 2005. 111-120.
BibTeX: Download