Local Background Enclosure for RGB-D Salient Object Detection

David Feng; Nick Barnes; Shaodi You; Chris McCarthy

doi:10.1109/CVPR.2016.257

Local Background Enclosure for RGB-D Salient Object Detection

David Feng, Nick Barnes, Shaodi You, Chris McCarthy

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

219 Citations (Scopus)

Abstract

Recent work in salient object detection has considered the incorporation of depth cues from RGB-D images. In most cases, depth contrast is used as the main feature. However, areas of high contrast in background regions cause false positives for such methods, as the background frequently contains regions that are highly variable in depth. Here, we propose a novel RGB-D saliency feature. Local Background Enclosure (LBE) captures the spread of angular directions which are background with respect to the candidate region and the object that it is part of. We show that our feature improves over state-of-the-art RGB-D saliency approaches as well as RGB methods on the RGBD1000 and NJUDS2000 datasets.

Original language	English
Title of host publication	Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Publisher	IEEE Computer Society
Pages	2343-2350
Number of pages	8
ISBN (Electronic)	9781467388504
DOIs	https://doi.org/10.1109/CVPR.2016.257
Publication status	Published - 9 Dec 2016
Event	29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States Duration: 26 Jun 2016 → 1 Jul 2016

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2016-December
ISSN (Print)	1063-6919

Conference

Conference	29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Country/Territory	United States
City	Las Vegas
Period	26/06/16 → 1/07/16

Access to Document

10.1109/CVPR.2016.257

Cite this

Feng, D., Barnes, N., You, S., & McCarthy, C. (2016). Local Background Enclosure for RGB-D Salient Object Detection. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 (pp. 2343-2350). Article 7780626 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December). IEEE Computer Society. https://doi.org/10.1109/CVPR.2016.257

@inproceedings{c8de3ca6264944c8951121795f06e31e,

title = "Local Background Enclosure for RGB-D Salient Object Detection",

abstract = "Recent work in salient object detection has considered the incorporation of depth cues from RGB-D images. In most cases, depth contrast is used as the main feature. However, areas of high contrast in background regions cause false positives for such methods, as the background frequently contains regions that are highly variable in depth. Here, we propose a novel RGB-D saliency feature. Local Background Enclosure (LBE) captures the spread of angular directions which are background with respect to the candidate region and the object that it is part of. We show that our feature improves over state-of-the-art RGB-D saliency approaches as well as RGB methods on the RGBD1000 and NJUDS2000 datasets.",

author = "David Feng and Nick Barnes and Shaodi You and Chris McCarthy",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 ; Conference date: 26-06-2016 Through 01-07-2016",

year = "2016",

month = dec,

day = "9",

doi = "10.1109/CVPR.2016.257",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "2343--2350",

booktitle = "Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016",

address = "United States",

}

Feng, D, Barnes, N, You, S & McCarthy, C 2016, Local Background Enclosure for RGB-D Salient Object Detection. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016., 7780626, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, IEEE Computer Society, pp. 2343-2350, 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, United States, 26/06/16. https://doi.org/10.1109/CVPR.2016.257

Local Background Enclosure for RGB-D Salient Object Detection. / Feng, David; Barnes, Nick; You, Shaodi et al.
Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. p. 2343-2350 7780626 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Local Background Enclosure for RGB-D Salient Object Detection

AU - Feng, David

AU - Barnes, Nick

AU - You, Shaodi

AU - McCarthy, Chris

PY - 2016/12/9

Y1 - 2016/12/9

N2 - Recent work in salient object detection has considered the incorporation of depth cues from RGB-D images. In most cases, depth contrast is used as the main feature. However, areas of high contrast in background regions cause false positives for such methods, as the background frequently contains regions that are highly variable in depth. Here, we propose a novel RGB-D saliency feature. Local Background Enclosure (LBE) captures the spread of angular directions which are background with respect to the candidate region and the object that it is part of. We show that our feature improves over state-of-the-art RGB-D saliency approaches as well as RGB methods on the RGBD1000 and NJUDS2000 datasets.

AB - Recent work in salient object detection has considered the incorporation of depth cues from RGB-D images. In most cases, depth contrast is used as the main feature. However, areas of high contrast in background regions cause false positives for such methods, as the background frequently contains regions that are highly variable in depth. Here, we propose a novel RGB-D saliency feature. Local Background Enclosure (LBE) captures the spread of angular directions which are background with respect to the candidate region and the object that it is part of. We show that our feature improves over state-of-the-art RGB-D saliency approaches as well as RGB methods on the RGBD1000 and NJUDS2000 datasets.

UR - http://www.scopus.com/inward/record.url?scp=84986329543&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2016.257

DO - 10.1109/CVPR.2016.257

M3 - Conference contribution

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 2343

EP - 2350

BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

PB - IEEE Computer Society

T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

Y2 - 26 June 2016 through 1 July 2016

ER -

Local Background Enclosure for RGB-D Salient Object Detection

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this