Learning discriminative occlusion feature for depth ordering inference on monocular image
Lists
Only you see this
Abstract
In this paper, a novel depth ordering inference approach is presented. Our main insight is to integrate the discriminative feature selection, occlusion feature learning and same-layer (S-L) relationship judgement into a uniform sparsity based classification objective, which cannot only supply the precise segmentation for the occlusion edge, but also reduce the solution space for the depth ordering inference efficiently. In addition, a novel triple descriptor is adopted to judge the foreground relationship, which is more discriminative than conversional local cues and can further reduce the solution space. The inference is executed by finding a valid path on a directed graph model. We validate our approach on the Cornell depth-order dataset and the NYU 2 dataset, and the convincing experimental results demonstrate the effectiveness of our approach.
BibTeX
@inproceedings{ming2015learning,
author = {Anlong Ming and Baofeng Xun and Jia Ni and Mingfei Gao and Yu Zhou},
title = {{Learning discriminative occlusion feature for depth ordering inference on monocular image}},
booktitle = {ICIP},
year = {2015},
doi = {10.1109/icip.2015.7351257},
}Loading related content...