EURASIP Journal on Applied Signal Processing 
Volume 2004 (2004), Issue 6, Pages 798-813
doi:10.1155/S111086570440122X

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

Hai-Yun Wang and Kai-Kuang Ma

School of Electrical and Electronic Engineering, Nanyang Technological University, Nanyang Avenue, Singapore 639798, Singapore

Received 29 January 2003; Revised 5 September 2003

Abstract

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.