RGB-D image segmentation based on multiple random walkers

Se Ho Lee, Won Dong Jang, Byung Kwan Park, Chang-Su Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

A novel RGB-D image segmentation algorithm is proposed in this work. This is the first attempt to achieve image segmentation based on the theory of multiple random walkers (MRW). We construct a multi-layer graph, whose nodes are superpixels divided with various parameters. Also, we set an edge weight to be proportional to the similarity of color and depth features between two adjacent nodes. Then, we segment an input RGB-D image by employing MRW simulation. Specifically, we decide the initial probability distribution of agents so that they are far from each other. We then execute the MRW process with the repulsive restarting rule, which makes the agents repel one another and occupy their own exclusive regions. Experimental results show that the proposed MRW image segmentation algorithm provides competitive segmentation performances, as compared with the conventional state-of-the-art algorithms.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
PublisherIEEE Computer Society
Pages2549-2553
Number of pages5
Volume2016-August
ISBN (Electronic)9781467399616
DOIs
Publication statusPublished - 2016 Aug 3
Event23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States
Duration: 2016 Sep 252016 Sep 28

Other

Other23rd IEEE International Conference on Image Processing, ICIP 2016
CountryUnited States
CityPhoenix
Period16/9/2516/9/28

Fingerprint

Image segmentation
Probability distributions
Color

Keywords

  • Multiple random walkers
  • Random walk
  • RGB-D image segmentation
  • Segmentation

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Lee, S. H., Jang, W. D., Park, B. K., & Kim, C-S. (2016). RGB-D image segmentation based on multiple random walkers. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings (Vol. 2016-August, pp. 2549-2553). [7532819] IEEE Computer Society. https://doi.org/10.1109/ICIP.2016.7532819

RGB-D image segmentation based on multiple random walkers. / Lee, Se Ho; Jang, Won Dong; Park, Byung Kwan; Kim, Chang-Su.

2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. p. 2549-2553 7532819.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, SH, Jang, WD, Park, BK & Kim, C-S 2016, RGB-D image segmentation based on multiple random walkers. in 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. vol. 2016-August, 7532819, IEEE Computer Society, pp. 2549-2553, 23rd IEEE International Conference on Image Processing, ICIP 2016, Phoenix, United States, 16/9/25. https://doi.org/10.1109/ICIP.2016.7532819
Lee SH, Jang WD, Park BK, Kim C-S. RGB-D image segmentation based on multiple random walkers. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August. IEEE Computer Society. 2016. p. 2549-2553. 7532819 https://doi.org/10.1109/ICIP.2016.7532819
Lee, Se Ho ; Jang, Won Dong ; Park, Byung Kwan ; Kim, Chang-Su. / RGB-D image segmentation based on multiple random walkers. 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. pp. 2549-2553
@inproceedings{7d2165fcabbb4bdd898928198b02050f,
title = "RGB-D image segmentation based on multiple random walkers",
abstract = "A novel RGB-D image segmentation algorithm is proposed in this work. This is the first attempt to achieve image segmentation based on the theory of multiple random walkers (MRW). We construct a multi-layer graph, whose nodes are superpixels divided with various parameters. Also, we set an edge weight to be proportional to the similarity of color and depth features between two adjacent nodes. Then, we segment an input RGB-D image by employing MRW simulation. Specifically, we decide the initial probability distribution of agents so that they are far from each other. We then execute the MRW process with the repulsive restarting rule, which makes the agents repel one another and occupy their own exclusive regions. Experimental results show that the proposed MRW image segmentation algorithm provides competitive segmentation performances, as compared with the conventional state-of-the-art algorithms.",
keywords = "Multiple random walkers, Random walk, RGB-D image segmentation, Segmentation",
author = "Lee, {Se Ho} and Jang, {Won Dong} and Park, {Byung Kwan} and Chang-Su Kim",
year = "2016",
month = "8",
day = "3",
doi = "10.1109/ICIP.2016.7532819",
language = "English",
volume = "2016-August",
pages = "2549--2553",
booktitle = "2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - RGB-D image segmentation based on multiple random walkers

AU - Lee, Se Ho

AU - Jang, Won Dong

AU - Park, Byung Kwan

AU - Kim, Chang-Su

PY - 2016/8/3

Y1 - 2016/8/3

N2 - A novel RGB-D image segmentation algorithm is proposed in this work. This is the first attempt to achieve image segmentation based on the theory of multiple random walkers (MRW). We construct a multi-layer graph, whose nodes are superpixels divided with various parameters. Also, we set an edge weight to be proportional to the similarity of color and depth features between two adjacent nodes. Then, we segment an input RGB-D image by employing MRW simulation. Specifically, we decide the initial probability distribution of agents so that they are far from each other. We then execute the MRW process with the repulsive restarting rule, which makes the agents repel one another and occupy their own exclusive regions. Experimental results show that the proposed MRW image segmentation algorithm provides competitive segmentation performances, as compared with the conventional state-of-the-art algorithms.

AB - A novel RGB-D image segmentation algorithm is proposed in this work. This is the first attempt to achieve image segmentation based on the theory of multiple random walkers (MRW). We construct a multi-layer graph, whose nodes are superpixels divided with various parameters. Also, we set an edge weight to be proportional to the similarity of color and depth features between two adjacent nodes. Then, we segment an input RGB-D image by employing MRW simulation. Specifically, we decide the initial probability distribution of agents so that they are far from each other. We then execute the MRW process with the repulsive restarting rule, which makes the agents repel one another and occupy their own exclusive regions. Experimental results show that the proposed MRW image segmentation algorithm provides competitive segmentation performances, as compared with the conventional state-of-the-art algorithms.

KW - Multiple random walkers

KW - Random walk

KW - RGB-D image segmentation

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85006750235&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006750235&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2016.7532819

DO - 10.1109/ICIP.2016.7532819

M3 - Conference contribution

AN - SCOPUS:85006750235

VL - 2016-August

SP - 2549

EP - 2553

BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings

PB - IEEE Computer Society

ER -