Multi-instance object segmentation with occlusion handling

Yi Ting Chen, Xiaokai Liu, Ming Hsuan Yang

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

45 Citations (Scopus)

Abstract

We present a multi-instance object segmentation algorithm to tackle occlusions. As an object is split into two parts by an occluder, it is nearly impossible to group the two separate regions into an instance by purely bottomup schemes. To address this problem, we propose to incorporate top-down category specific reasoning and shape prediction through exemplars into an intuitive energy minimization framework. We perform extensive evaluations of our method on the challenging PASCAL VOC 2012 segmentation set. The proposed algorithm achieves favorable results on the joint detection and segmentation task against the state-of-the-art method both quantitatively and qualitatively.

Original languageEnglish
Title of host publicationIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
PublisherIEEE Computer Society
Pages3470-3478
Number of pages9
ISBN (Electronic)9781467369640
DOIs
Publication statusPublished - 2015 Oct 14
EventIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States
Duration: 2015 Jun 72015 Jun 12

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume07-12-June-2015
ISSN (Print)1063-6919

Other

OtherIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
CountryUnited States
CityBoston
Period15/6/715/6/12

Fingerprint

Volatile organic compounds

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Chen, Y. T., Liu, X., & Yang, M. H. (2015). Multi-instance object segmentation with occlusion handling. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 (pp. 3470-3478). [7298969] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015). IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7298969
Chen, Yi Ting ; Liu, Xiaokai ; Yang, Ming Hsuan. / Multi-instance object segmentation with occlusion handling. IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. pp. 3470-3478 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{5d3b65a1b37a4a229df3fd4eafbc2998,
title = "Multi-instance object segmentation with occlusion handling",
abstract = "We present a multi-instance object segmentation algorithm to tackle occlusions. As an object is split into two parts by an occluder, it is nearly impossible to group the two separate regions into an instance by purely bottomup schemes. To address this problem, we propose to incorporate top-down category specific reasoning and shape prediction through exemplars into an intuitive energy minimization framework. We perform extensive evaluations of our method on the challenging PASCAL VOC 2012 segmentation set. The proposed algorithm achieves favorable results on the joint detection and segmentation task against the state-of-the-art method both quantitatively and qualitatively.",
author = "Chen, {Yi Ting} and Xiaokai Liu and Yang, {Ming Hsuan}",
year = "2015",
month = "10",
day = "14",
doi = "10.1109/CVPR.2015.7298969",
language = "English",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "3470--3478",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015",
address = "United States",

}

Chen, YT, Liu, X & Yang, MH 2015, Multi-instance object segmentation with occlusion handling. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015., 7298969, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, IEEE Computer Society, pp. 3470-3478, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 15/6/7. https://doi.org/10.1109/CVPR.2015.7298969

Multi-instance object segmentation with occlusion handling. / Chen, Yi Ting; Liu, Xiaokai; Yang, Ming Hsuan.

IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. p. 3470-3478 7298969 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015).

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

TY - GEN

T1 - Multi-instance object segmentation with occlusion handling

AU - Chen, Yi Ting

AU - Liu, Xiaokai

AU - Yang, Ming Hsuan

PY - 2015/10/14

Y1 - 2015/10/14

N2 - We present a multi-instance object segmentation algorithm to tackle occlusions. As an object is split into two parts by an occluder, it is nearly impossible to group the two separate regions into an instance by purely bottomup schemes. To address this problem, we propose to incorporate top-down category specific reasoning and shape prediction through exemplars into an intuitive energy minimization framework. We perform extensive evaluations of our method on the challenging PASCAL VOC 2012 segmentation set. The proposed algorithm achieves favorable results on the joint detection and segmentation task against the state-of-the-art method both quantitatively and qualitatively.

AB - We present a multi-instance object segmentation algorithm to tackle occlusions. As an object is split into two parts by an occluder, it is nearly impossible to group the two separate regions into an instance by purely bottomup schemes. To address this problem, we propose to incorporate top-down category specific reasoning and shape prediction through exemplars into an intuitive energy minimization framework. We perform extensive evaluations of our method on the challenging PASCAL VOC 2012 segmentation set. The proposed algorithm achieves favorable results on the joint detection and segmentation task against the state-of-the-art method both quantitatively and qualitatively.

UR - http://www.scopus.com/inward/record.url?scp=84959224495&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959224495&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7298969

DO - 10.1109/CVPR.2015.7298969

M3 - Conference contribution

AN - SCOPUS:84959224495

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

SP - 3470

EP - 3478

BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

PB - IEEE Computer Society

ER -

Chen YT, Liu X, Yang MH. Multi-instance object segmentation with occlusion handling. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society. 2015. p. 3470-3478. 7298969. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2015.7298969