Share Email Print

Proceedings Paper

Semantic labeling of indoor scenes from RGB-D images with discriminative learning
Author(s): Bo Liu; Haoqi Fan
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Recently emerged RGB-D sensors provide great promise for indoor scene understanding, which is a fundamental and challenging problem in computer vision. We present a discriminative model in this paper to semantically label indoor scenes from RGB-D images. Unlike previous work which only labels pre-determined superpixels, we characterize the scenes with a set of planes and compose them into objects. The optimal way to composition and corresponding labels are inferred simultaneously using a greedy algorithm. Our model considers unary features and pairwise and co-occurrence context, as well as latent variables that account for multi-mode distributions of each object category. We train the model with latent structural SVM learning framework. Our approach achieves state-of-the-art performance on the Cornell RGB-D indoor scene dataset [1].

Paper Details

Date Published: 24 December 2013
PDF: 6 pages
Proc. SPIE 9067, Sixth International Conference on Machine Vision (ICMV 2013), 90670C (24 December 2013); doi: 10.1117/12.2049805
Show Author Affiliations
Bo Liu, Beijing Univ. of Technology (China)
Haoqi Fan, Beijing Univ. of Technology (China)

Published in SPIE Proceedings Vol. 9067:
Sixth International Conference on Machine Vision (ICMV 2013)
Branislav Vuksanovic; Antanas Verikas; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top