Video object segmentation by hypergraph cut

• Published in: 2009 IEEE Conference on Computer Vision and Pattern Recognition pp. 1738 - 1745
• Main Authors: Yuchi Huang, Qingshan Liu, Metaxas, Dimitris
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2009
• Subjects: Computer science; Computer vision; Image motion analysis; Layout; Motion detection; Motion estimation; Object detection; Object segmentation; Optical computing; Partitioning algorithms
• ISBN: 1424439922; 9781424439928
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2009.5206795

In this paper, we present a new framework of video object segmentation, in which we formulate the task of extracting prominent objects from a scene as the problem of hypergraph cut. We initially over-segment each frame in the sequence, and take the over-segmented image patches as the vertices in the graph. Different from the traditional pairwise graph structure, we build a novel graph structure, hypergraph, to represent the complex spatio-temporal neighborhood relationship among the patches. We assign each patch with several attributes that are computed from the optical flow and the appearance-based motion profile, and the vertices with the same attribute value is connected by a hyperedge. Through all the hyperedges, not only the complex non-pairwise relationships between the patches are described, but also their merits are integrated together organically. The task of video object segmentation is equivalent to the hypergraph partition, which can be solved by the hypergraph cut algorithm. The effectiveness of the proposed method is demonstrated by extensive experiments on nature scenes.