Spatio-Temporal Video Object Segmentation via Scale-Adaptive 3D Structure Tensor

Autor: Hai-Yun Wang, Kai-Kuang Ma
Jazyk: angličtina
Rok vydání: 2004
Předmět:
Zdroj: EURASIP Journal on Advances in Signal Processing, Vol 2004, Iss 6, Pp 798-813 (2004)
Druh dokumentu: article
ISSN: 16876172
1687-6172
1687-6180
DOI: 10.1155/S111086570440122X
Popis: To address multiple motions and deformable objects' motions encountered in existing region-based approaches, an automatic video object (VO) segmentation methodology is proposed in this paper by exploiting the duality of image segmentation and motion estimation such that spatial and temporal information could assist each other to jointly yield much improved segmentation results. The key novelties of our method are (1) scale-adaptive tensor computation, (2) spatial-constrained motion mask generation without invoking dense motion-field computation, (3) rigidity analysis, (4) motion mask generation and selection, and (5) motion-constrained spatial region merging. Experimental results demonstrate that these novelties jointly contribute much more accurate VO segmentation both in spatial and temporal domains.
Databáze: Directory of Open Access Journals
Externí odkaz: