Video Object Segmentation of Dynamic Scenes with Large Displacements

Yinhui ZHANG  Zifen HE  

IEICE TRANSACTIONS on Information and Systems   Vol.E98-D   No.9   pp.1719-1723
Publication Date: 2015/09/01
Publicized: 2015/06/17
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2015EDL8062
Type of Manuscript: LETTER
Category: Image Processing and Video Processing
video segmentation,  unsupervised,  saliency,  motion segmentation,  

Full Text: PDF>>
Buy this Article

Segmenting foreground objects in unconstrained dynamic scenes still remains a difficult problem. We present a novel unsupervised segmentation approach that allows robust object segmentation of dynamic scenes with large displacements. To make this possible, we project motion based foreground region hypotheses generated via standard optical flow onto visual saliency regions. The motion hypotheses correspond to inside seeds mapping of the motion boundary. For visual saliency, we generalize the image signature method from images to videos to delineate saliency mapping of object proposals. The mapping of image signatures estimated in Discrete Cosine Transform (DCT) domain favor stand-out regions in the human visual system. We leverage a Markov random field built on superpixels to impose both spatial and temporal consistence constraints on the motion-saliency combined segments. Projecting salient regions via an image signature with inside mapping seeds facilitates segmenting ambiguous objects from unconstrained dynamic scenes in presence of large displacements. We demonstrate the performance on fourteen challenging unconstrained dynamic scenes, compare our method with two state-of-the-art unsupervised video segmentation algorithms, and provide quantitative and qualitative performance comparisons.