Region-Based Shape Incorporation for Probabilistic Spatio-Temporal Video Object Segmentation

Embedding generic shape information into probabilistic spatiotemporal video object segmentation is of pivotal importance to achieving better segmentation, since it provides valuable perceptual clues for humans in both distinguishing and recognising objects. Recently a probabilistic spatio-temporal video object segmentation algorithm incorporating shape information has been proposed, though since it is restricted to only pixel features, the probability of a pixel belonging to a certain cluster is directly correlated with its spatial location, which theoretically limits the segmentation performance of the technique. To address this problem, this paper proposes a new probabilistic spatio-temporal video object segmentation algorithm that incorporates generic shape information based on its region. Experimental results reveal a significant performance improvement in arbitrary-shaped video object segmentation compared with other contemporary methods for a variety of standard video test seque...

• Type: Conference
• Year: 2006
• Where: ICIP
• Authors: Rakib Ahmed, Gour C. Karmakar, Laurence S. Dooley
• Keywords: ICIP 2006, Image Processing, Object Segmentation Algorithm, Probabilistic Spatio-temporal Video, Segmentation Performance, Spatio-temporal Video Object, Video Object Segmentation