A dynamic conditional random field model for object segmentation in image sequences

• Published in: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 1; pp. 264 - 270 vol. 1
• Main Authors: Yang Wang, Qiang Ji
• Format: Conference Proceeding
• Language: English
• Published: IEEE 2005
• Subjects: Filtering algorithms; Hidden Markov models; History; Image segmentation; Image sequences; Layout; Motion estimation; Object segmentation; Recursive estimation; Video sequences

This paper presents a dynamic conditional random field (DCRF) model to integrate contextual constraints for object segmentation in image sequences. Spatial and temporal dependencies within the segmentation process are unified by a dynamic probabilistic framework based on the conditional random field...