Superpixel-Based Video Object Segmentation Using Perceptual Organization and Location Prior
Abstract
In this paper we present an approach for segmenting objects in videos taken in complex scenes with multiple and different targets. The method does not make any specific assumptions about the videos and relies on how objects are perceived by humans according to Gestalt laws. Initially, we rapidly generate a coarse foreground segmentation, which provides predictions about motion regions by analyzing how superpixel segmentation changes in consecutive frames. We then exploit these location priors to refine the initial segmentation by optimizing an energy function based on appearance and perceptual organization, only on regions where motion is observed. We evaluated our method on complex and challenging video sequences and it showed significant performance improvements over recent state-of-the-art methods, being also fast enough to be used for "on-the-fly" processing.
Cite
Text
Giordano et al. "Superpixel-Based Video Object Segmentation Using Perceptual Organization and Location Prior." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7299114Markdown
[Giordano et al. "Superpixel-Based Video Object Segmentation Using Perceptual Organization and Location Prior." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/giordano2015cvpr-superpixelbased/) doi:10.1109/CVPR.2015.7299114BibTeX
@inproceedings{giordano2015cvpr-superpixelbased,
title = {{Superpixel-Based Video Object Segmentation Using Perceptual Organization and Location Prior}},
author = {Giordano, Daniela and Murabito, Francesca and Palazzo, Simone and Spampinato, Concetto},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2015},
doi = {10.1109/CVPR.2015.7299114},
url = {https://mlanthology.org/cvpr/2015/giordano2015cvpr-superpixelbased/}
}