A Particle Filter Framework for Contour Detection
Abstract
We investigate the contour detection task in complex natural images. We propose a novel contour detection algorithm which locally tracks small pieces of edges called edgelets. The combination of the Bayesian modeling and the edgelets enables the use of semi-local prior information and image-dependent likelihoods. We use a mixed offline and online learning strategy to detect the most relevant edgelets. The detection problem is then modeled as a sequential Bayesian tracking task, estimated using a particle filtering technique. Experiments on the Berkeley Segmentation Datasets show that the proposed Particle Filter Contour Detector method performs well compared to competing state-of-the-art methods.
Cite
Text
Widynski and Mignotte. "A Particle Filter Framework for Contour Detection." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33718-5_56Markdown
[Widynski and Mignotte. "A Particle Filter Framework for Contour Detection." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/widynski2012eccv-particle/) doi:10.1007/978-3-642-33718-5_56BibTeX
@inproceedings{widynski2012eccv-particle,
title = {{A Particle Filter Framework for Contour Detection}},
author = {Widynski, Nicolas and Mignotte, Max},
booktitle = {European Conference on Computer Vision},
year = {2012},
pages = {780-793},
doi = {10.1007/978-3-642-33718-5_56},
url = {https://mlanthology.org/eccv/2012/widynski2012eccv-particle/}
}