Video saliency, aiming for estimation of a single dominant object in a sequence, offers strong object-level cues for unsupervised video object segmentation. In this paper, we present a geodesic distance based technique that provides reliable and temporally consistent saliency measurement of superpixels as a prior for pixel-wise labeling. Using undirected intra-frame and interframe graphs constructed from spatiotemporal edges or appearance and motion, and a skeleton abstraction step to further enhance saliency estimates, our method formulates the pixel-wise segmentation task as an energy minimization problem on a function that consists of unary terms of global foreground and background models, dynamic location models, and pairwise terms of label smoothness potentials. We perform extensive quantitative and qualitative experiments on benchmark datasets. Our method achieves superior performance in comparison to the current state-of-the-art in terms of accuracy and speed.
|Number of pages||14|
|Journal||IEEE Transactions on Pattern Analysis and Machine Intelligence|
|State||Published - Jan 2018|
Bibliographical noteFunding Information:
This work was supported in part by the National Basic Research Program of China (973 Program) (No. 2013CB328805), the National Natural Science Foundation of China (No. 61272359), the Australian Research Council’s Discovery Projects funding scheme (DP150104645), and the Fok Ying-Tong Education Foundation for Young Teachers. Specialized Fund for Joint Building Program of Beijing Municipal Education Commission. Jianbing Shen is the corresponding author.
© 2021 EDP Sciences. All rights reserved.
- Geodesic distance
- Spatiotemporal object prior
- Video object segmentation
- Video saliency
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Computational Theory and Mathematics
- Artificial Intelligence
- Applied Mathematics