2.1 Depth Estimation of Frames in Image Sequences Using Motion Occlusions
Abstract
This paper proposes a system to depth order regions of a frame belonging to a monocular image sequence. For a given frame, regions are ordered according to their relative depth using the previous and following frames. The algorithm estimates occluded and disoccluded pixels belonging to the central frame. Afterwards, a Binary Partition Tree (BPT) is constructed to obtain a hierarchical, region based representation of the image. The final depth partition is obtained by means of energy minimization on the BPT. To achieve a global depth ordering from local occlusion cues, a depth order graph is constructed and used to eliminate contradictory local cues. Results of the system are evaluated and compared with state of the art figure/ground labeling systems on several datasets, showing promising results.
Cite
Text
Palou and Salembier. "2.1 Depth Estimation of Frames in Image Sequences Using Motion Occlusions." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33885-4_52Markdown
[Palou and Salembier. "2.1 Depth Estimation of Frames in Image Sequences Using Motion Occlusions." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/palou2012eccv-depth/) doi:10.1007/978-3-642-33885-4_52BibTeX
@inproceedings{palou2012eccv-depth,
title = {{2.1 Depth Estimation of Frames in Image Sequences Using Motion Occlusions}},
author = {Palou, Guillem and Salembier, Philippe},
booktitle = {European Conference on Computer Vision},
year = {2012},
pages = {516-525},
doi = {10.1007/978-3-642-33885-4_52},
url = {https://mlanthology.org/eccv/2012/palou2012eccv-depth/}
}