Saliency detection for RGBD image using optimization

Zhengchao Lei; Weiyan Chai; Sanyuan Zhao; Hongmei Song; Fengxia Li

doi:10.1109/ICCSE.2017.8085532

Saliency detection for RGBD image using optimization

Zhengchao Lei, Weiyan Chai, Sanyuan Zhao^*, Hongmei Song, Fengxia Li

^*Corresponding author for this work

School of Computer Science and Technology

Beijing Institute of Technology

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

2 Citations (Scopus)

Abstract

Saliency detection in images attracts much research attention for its usage in numerous multimedia applications. In this paper, we propose a saliency detection method based on optimization for RGBD images. With RGBD images, our method utilizes the depth channel to enhance the identification of background and foreground regions. We firstly generate new depth image by using non-linear transformation and outstand object region. Then, we introduce saliency optimization framework to integrate the depth cue and other low-level cues to obtain the final saliency map. The experimental results demonstrate that our method performs better in saliency detection for RGBD Images.

Original language	English
Title of host publication	ICCSE 2017 - 12th International Conference on Computer Science and Education
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	440-443
Number of pages	4
ISBN (Electronic)	9781509025084
DOIs	https://doi.org/10.1109/ICCSE.2017.8085532
Publication status	Published - 26 Oct 2017
Event	12th International Conference on Computer Science and Education, ICCSE 2017 - Houston, United States Duration: 22 Aug 2017 → 25 Aug 2017

Publication series

Name	ICCSE 2017 - 12th International Conference on Computer Science and Education

Conference

Conference	12th International Conference on Computer Science and Education, ICCSE 2017
Country/Territory	United States
City	Houston
Period	22/08/17 → 25/08/17

Keywords

Optimization
RGBD image
Saliency Detection

Access to Document

10.1109/ICCSE.2017.8085532

Cite this

Lei, Z., Chai, W., Zhao, S., Song, H., & Li, F. (2017). Saliency detection for RGBD image using optimization. In ICCSE 2017 - 12th International Conference on Computer Science and Education (pp. 440-443). Article 8085532 (ICCSE 2017 - 12th International Conference on Computer Science and Education). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCSE.2017.8085532

@inproceedings{fec2e4cb63f9421987c7a9682aa1d75c,

title = "Saliency detection for RGBD image using optimization",

abstract = "Saliency detection in images attracts much research attention for its usage in numerous multimedia applications. In this paper, we propose a saliency detection method based on optimization for RGBD images. With RGBD images, our method utilizes the depth channel to enhance the identification of background and foreground regions. We firstly generate new depth image by using non-linear transformation and outstand object region. Then, we introduce saliency optimization framework to integrate the depth cue and other low-level cues to obtain the final saliency map. The experimental results demonstrate that our method performs better in saliency detection for RGBD Images.",

keywords = "Optimization, RGBD image, Saliency Detection",

author = "Zhengchao Lei and Weiyan Chai and Sanyuan Zhao and Hongmei Song and Fengxia Li",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 12th International Conference on Computer Science and Education, ICCSE 2017 ; Conference date: 22-08-2017 Through 25-08-2017",

year = "2017",

month = oct,

day = "26",

doi = "10.1109/ICCSE.2017.8085532",

language = "English",

series = "ICCSE 2017 - 12th International Conference on Computer Science and Education",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "440--443",

booktitle = "ICCSE 2017 - 12th International Conference on Computer Science and Education",

address = "United States",

}

Lei, Z, Chai, W, Zhao, S, Song, H & Li, F 2017, Saliency detection for RGBD image using optimization. in ICCSE 2017 - 12th International Conference on Computer Science and Education., 8085532, ICCSE 2017 - 12th International Conference on Computer Science and Education, Institute of Electrical and Electronics Engineers Inc., pp. 440-443, 12th International Conference on Computer Science and Education, ICCSE 2017, Houston, United States, 22/08/17. https://doi.org/10.1109/ICCSE.2017.8085532

Saliency detection for RGBD image using optimization. / Lei, Zhengchao; Chai, Weiyan; Zhao, Sanyuan et al.
ICCSE 2017 - 12th International Conference on Computer Science and Education. Institute of Electrical and Electronics Engineers Inc., 2017. p. 440-443 8085532 (ICCSE 2017 - 12th International Conference on Computer Science and Education).

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

TY - GEN

T1 - Saliency detection for RGBD image using optimization

AU - Lei, Zhengchao

AU - Chai, Weiyan

AU - Zhao, Sanyuan

AU - Song, Hongmei

AU - Li, Fengxia

PY - 2017/10/26

Y1 - 2017/10/26

N2 - Saliency detection in images attracts much research attention for its usage in numerous multimedia applications. In this paper, we propose a saliency detection method based on optimization for RGBD images. With RGBD images, our method utilizes the depth channel to enhance the identification of background and foreground regions. We firstly generate new depth image by using non-linear transformation and outstand object region. Then, we introduce saliency optimization framework to integrate the depth cue and other low-level cues to obtain the final saliency map. The experimental results demonstrate that our method performs better in saliency detection for RGBD Images.

AB - Saliency detection in images attracts much research attention for its usage in numerous multimedia applications. In this paper, we propose a saliency detection method based on optimization for RGBD images. With RGBD images, our method utilizes the depth channel to enhance the identification of background and foreground regions. We firstly generate new depth image by using non-linear transformation and outstand object region. Then, we introduce saliency optimization framework to integrate the depth cue and other low-level cues to obtain the final saliency map. The experimental results demonstrate that our method performs better in saliency detection for RGBD Images.

KW - Optimization

KW - RGBD image

KW - Saliency Detection

UR - http://www.scopus.com/inward/record.url?scp=85040121818&partnerID=8YFLogxK

U2 - 10.1109/ICCSE.2017.8085532

DO - 10.1109/ICCSE.2017.8085532

M3 - Conference contribution

AN - SCOPUS:85040121818

T3 - ICCSE 2017 - 12th International Conference on Computer Science and Education

SP - 440

EP - 443

BT - ICCSE 2017 - 12th International Conference on Computer Science and Education

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th International Conference on Computer Science and Education, ICCSE 2017

Y2 - 22 August 2017 through 25 August 2017

ER -

Saliency detection for RGBD image using optimization

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this