Separating objects and clutter in indoor scenes

Research output: Chapter in Book/Conference paperConference paper

10 Citations (Scopus)

Abstract

© 2015 IEEE. Objects' spatial layout estimation and clutter identification are two important tasks to understand indoor scenes. We propose to solve both of these problems in a joint framework using RGBD images of indoor scenes. In contrast to recent approaches which focus on either one of these two problems, we perform 'fine grained structure categorization' by predicting all the major objects and simultaneously labeling the cluttered regions. A conditional random field model is proposed to incorporate a rich set of local appearance, geometric features and interactions between the scene elements. We take a structural learning approach with a loss of 3D localisation to estimate the model parameters from a large annotated RGBD dataset, and a mixed integer linear programming formulation for inference. We demonstrate that our approach is able to detect cuboids and estimate cluttered regions across many different object and scene categories in the presence of occlusion, illumination and appearance variations.
Original languageEnglish
Title of host publicationIEEE Conference on Computer Vision and Pattern Recognition
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages4603-4611
Volume07-12-June-2015
ISBN (Print)9781467369640
DOIs
Publication statusPublished - 2015
EventSeparating objects and clutter in indoor scenes - Boston, Massachusetts, USA
Duration: 1 Jan 2015 → …

Conference

ConferenceSeparating objects and clutter in indoor scenes
Period1/01/15 → …

Fingerprint

Linear programming
Labeling
Lighting

Cite this

Khan, S. H., He, X., Bannamoun, M., Sohel, F., & Togneri, R. (2015). Separating objects and clutter in indoor scenes. In IEEE Conference on Computer Vision and Pattern Recognition (Vol. 07-12-June-2015, pp. 4603-4611). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CVPR.2015.7299091
Khan, S.H. ; He, X. ; Bannamoun, Mohammed ; Sohel, Ferdous ; Togneri, Roberto. / Separating objects and clutter in indoor scenes. IEEE Conference on Computer Vision and Pattern Recognition. Vol. 07-12-June-2015 IEEE, Institute of Electrical and Electronics Engineers, 2015. pp. 4603-4611
@inproceedings{955a3b5012304f1a80e51eae6ceb5a70,
title = "Separating objects and clutter in indoor scenes",
abstract = "{\circledC} 2015 IEEE. Objects' spatial layout estimation and clutter identification are two important tasks to understand indoor scenes. We propose to solve both of these problems in a joint framework using RGBD images of indoor scenes. In contrast to recent approaches which focus on either one of these two problems, we perform 'fine grained structure categorization' by predicting all the major objects and simultaneously labeling the cluttered regions. A conditional random field model is proposed to incorporate a rich set of local appearance, geometric features and interactions between the scene elements. We take a structural learning approach with a loss of 3D localisation to estimate the model parameters from a large annotated RGBD dataset, and a mixed integer linear programming formulation for inference. We demonstrate that our approach is able to detect cuboids and estimate cluttered regions across many different object and scene categories in the presence of occlusion, illumination and appearance variations.",
author = "S.H. Khan and X. He and Mohammed Bannamoun and Ferdous Sohel and Roberto Togneri",
year = "2015",
doi = "10.1109/CVPR.2015.7299091",
language = "English",
isbn = "9781467369640",
volume = "07-12-June-2015",
pages = "4603--4611",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Khan, SH, He, X, Bannamoun, M, Sohel, F & Togneri, R 2015, Separating objects and clutter in indoor scenes. in IEEE Conference on Computer Vision and Pattern Recognition. vol. 07-12-June-2015, IEEE, Institute of Electrical and Electronics Engineers, pp. 4603-4611, Separating objects and clutter in indoor scenes, 1/01/15. https://doi.org/10.1109/CVPR.2015.7299091

Separating objects and clutter in indoor scenes. / Khan, S.H.; He, X.; Bannamoun, Mohammed; Sohel, Ferdous; Togneri, Roberto.

IEEE Conference on Computer Vision and Pattern Recognition. Vol. 07-12-June-2015 IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 4603-4611.

Research output: Chapter in Book/Conference paperConference paper

TY - GEN

T1 - Separating objects and clutter in indoor scenes

AU - Khan, S.H.

AU - He, X.

AU - Bannamoun, Mohammed

AU - Sohel, Ferdous

AU - Togneri, Roberto

PY - 2015

Y1 - 2015

N2 - © 2015 IEEE. Objects' spatial layout estimation and clutter identification are two important tasks to understand indoor scenes. We propose to solve both of these problems in a joint framework using RGBD images of indoor scenes. In contrast to recent approaches which focus on either one of these two problems, we perform 'fine grained structure categorization' by predicting all the major objects and simultaneously labeling the cluttered regions. A conditional random field model is proposed to incorporate a rich set of local appearance, geometric features and interactions between the scene elements. We take a structural learning approach with a loss of 3D localisation to estimate the model parameters from a large annotated RGBD dataset, and a mixed integer linear programming formulation for inference. We demonstrate that our approach is able to detect cuboids and estimate cluttered regions across many different object and scene categories in the presence of occlusion, illumination and appearance variations.

AB - © 2015 IEEE. Objects' spatial layout estimation and clutter identification are two important tasks to understand indoor scenes. We propose to solve both of these problems in a joint framework using RGBD images of indoor scenes. In contrast to recent approaches which focus on either one of these two problems, we perform 'fine grained structure categorization' by predicting all the major objects and simultaneously labeling the cluttered regions. A conditional random field model is proposed to incorporate a rich set of local appearance, geometric features and interactions between the scene elements. We take a structural learning approach with a loss of 3D localisation to estimate the model parameters from a large annotated RGBD dataset, and a mixed integer linear programming formulation for inference. We demonstrate that our approach is able to detect cuboids and estimate cluttered regions across many different object and scene categories in the presence of occlusion, illumination and appearance variations.

U2 - 10.1109/CVPR.2015.7299091

DO - 10.1109/CVPR.2015.7299091

M3 - Conference paper

SN - 9781467369640

VL - 07-12-June-2015

SP - 4603

EP - 4611

BT - IEEE Conference on Computer Vision and Pattern Recognition

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Khan SH, He X, Bannamoun M, Sohel F, Togneri R. Separating objects and clutter in indoor scenes. In IEEE Conference on Computer Vision and Pattern Recognition. Vol. 07-12-June-2015. IEEE, Institute of Electrical and Electronics Engineers. 2015. p. 4603-4611 https://doi.org/10.1109/CVPR.2015.7299091