Fast Appearance Modeling for Automatic Primary Video Object Segmentation

• Published in: IEEE transactions on image processing 2016-02, Vol.25 (2), p.503-515
• Main Authors: Jiong Yang, Price, Brian, Xiaohui Shen, Zhe Lin, Junsong Yuan
• Format: Article
• Language: English
• Subjects: Adaptation models; appearance modeling; automatic; Automation; Consumption; Fields (mathematics); graph cut; Graph theory; Image segmentation; Iterative methods; Markov random fields; Modelling; Motion segmentation; object; Object segmentation; Optimization; primary; Proposals; Segmentation; Transaction processing; video
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2015.2500820

Automatic segmentation of the primary object in a video clip is a challenging problem as there is no prior knowledge of the primary object. Most existing techniques thus adapt an iterative approach for foreground and background appearance modeling, i.e., fix the appearance model while optimizing the segmentation and fix the segmentation while optimizing the appearance model. However, these approaches may rely on good initialization and can be easily trapped in local optimal. In addition, they are usually time consuming for analyzing videos. To address these limitations, we propose a novel and efficient appearance modeling technique for automatic primary video object segmentation in the Markov random field (MRF) framework. It embeds the appearance constraint as auxiliary nodes and edges in the MRF structure, and can optimize both the segmentation and appearance model parameters simultaneously in one graph cut. The extensive experimental evaluations validate the superiority of the proposed approach over the state-of-the-art methods, in both efficiency and effectiveness.