Monocular Depth-Ordering Reasoning with Occlusion Edge Detection and Couple Layers Inference

A depth-ordering reasoning approach first provides novel occlusion edge detection, generating precise same-layer relationship judgment and producing reliable region proposals for the depth-ordering inference. Specifically, a novel sparsity-induced regression model learns a discriminative feature sub...

Full description

Saved in:
Bibliographic Details
Published in:IEEE intelligent systems 2016-03, Vol.31 (2), p.54-65
Main Authors: Ming, Anlong, Wu, Tianfu, Ma, Jianxiang, Sun, Fang, Zhou, Yu
Format: Article
Language:English
Subjects:
depth-order inference
Edge detection
Feature extraction
feature selection
Graph theory
Image color analysis
Image edge detection
Inference
Intelligent systems
Joining
Judgment
Kernels
Mathematical models
Occlusion
occlusion edge detection
Pattern recognition
Reasoning
Regression
Regression analysis
Regression models
triple descriptor
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A depth-ordering reasoning approach first provides novel occlusion edge detection, generating precise same-layer relationship judgment and producing reliable region proposals for the depth-ordering inference. Specifically, a novel sparsity-induced regression model learns a discriminative feature subspace. In addition, kernel ridge regression assigns the occlusion label for each edge. The kernel trick guarantees linearly separable edges in a rich, high-dimensional feature space. Secondly, a couple layers inference approach infers the final depth order. In the semilocal layer, a novel triple descriptor judges the foreground relationship. In the global layer, the inference is executed by finding a valid path on a directed graph model. The proposed approach is validated on the Cornell depth-order and NYU 2 datasets.
ISSN:1541-1672
1941-1294
DOI:10.1109/MIS.2015.94