Unsupervised video object segmentation by supertrajectory labeling

研究成果: Conference contribution

1 引用 (Scopus)

抄録

We propose a novel approach to unsupervised video segmentation based on the trajectories of Temporal Super-pixels (TSPs). We cast the segmentation problem as a trajectory-labeling problem and define a Markov random field on a graph in which each node represents a trajectory of TSPs, which we minimize using a new two-stage optimization method we developed. The adaption of the trajectories as basic building blocks brings several advantages over conventional superpixel-based methods, such as more expressive potential functions, temporal coherence of the resulting segmentation, and drastically reduced number of the MRF nodes. The most important effect is, however, that it allows more robust segmentation of the foreground that is static in some frames. The method is evaluated on a subset of the standard SegTrack benchmark and yields competitive results against the state-of-the-art methods.

元の言語English
ホスト出版物のタイトルProceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017
出版者Institute of Electrical and Electronics Engineers Inc.
ページ448-451
ページ数4
ISBN(電子版)9784901122160
DOI
出版物ステータスPublished - 2017 7 19
イベント15th IAPR International Conference on Machine Vision Applications, MVA 2017 - Nagoya, Japan
継続期間: 2017 5 82017 5 12

Other

Other15th IAPR International Conference on Machine Vision Applications, MVA 2017
Japan
Nagoya
期間17/5/817/5/12

Fingerprint

Labeling
Trajectories
Pixels

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

これを引用

Masuda, M., Mochizuki, Y., & Ishikawa, H. (2017). Unsupervised video object segmentation by supertrajectory labeling. : Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017 (pp. 448-451). [7986897] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/MVA.2017.7986897

Unsupervised video object segmentation by supertrajectory labeling. / Masuda, Masahiro; Mochizuki, Yoshihiko; Ishikawa, Hiroshi.

Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 448-451 7986897.

研究成果: Conference contribution

Masuda, M, Mochizuki, Y & Ishikawa, H 2017, Unsupervised video object segmentation by supertrajectory labeling. : Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017., 7986897, Institute of Electrical and Electronics Engineers Inc., pp. 448-451, 15th IAPR International Conference on Machine Vision Applications, MVA 2017, Nagoya, Japan, 17/5/8. https://doi.org/10.23919/MVA.2017.7986897
Masuda M, Mochizuki Y, Ishikawa H. Unsupervised video object segmentation by supertrajectory labeling. : Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 448-451. 7986897 https://doi.org/10.23919/MVA.2017.7986897
Masuda, Masahiro ; Mochizuki, Yoshihiko ; Ishikawa, Hiroshi. / Unsupervised video object segmentation by supertrajectory labeling. Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 448-451
@inproceedings{81f3c2c648ac4de4a80a7264ad4c739e,
title = "Unsupervised video object segmentation by supertrajectory labeling",
abstract = "We propose a novel approach to unsupervised video segmentation based on the trajectories of Temporal Super-pixels (TSPs). We cast the segmentation problem as a trajectory-labeling problem and define a Markov random field on a graph in which each node represents a trajectory of TSPs, which we minimize using a new two-stage optimization method we developed. The adaption of the trajectories as basic building blocks brings several advantages over conventional superpixel-based methods, such as more expressive potential functions, temporal coherence of the resulting segmentation, and drastically reduced number of the MRF nodes. The most important effect is, however, that it allows more robust segmentation of the foreground that is static in some frames. The method is evaluated on a subset of the standard SegTrack benchmark and yields competitive results against the state-of-the-art methods.",
author = "Masahiro Masuda and Yoshihiko Mochizuki and Hiroshi Ishikawa",
year = "2017",
month = "7",
day = "19",
doi = "10.23919/MVA.2017.7986897",
language = "English",
pages = "448--451",
booktitle = "Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Unsupervised video object segmentation by supertrajectory labeling

AU - Masuda, Masahiro

AU - Mochizuki, Yoshihiko

AU - Ishikawa, Hiroshi

PY - 2017/7/19

Y1 - 2017/7/19

N2 - We propose a novel approach to unsupervised video segmentation based on the trajectories of Temporal Super-pixels (TSPs). We cast the segmentation problem as a trajectory-labeling problem and define a Markov random field on a graph in which each node represents a trajectory of TSPs, which we minimize using a new two-stage optimization method we developed. The adaption of the trajectories as basic building blocks brings several advantages over conventional superpixel-based methods, such as more expressive potential functions, temporal coherence of the resulting segmentation, and drastically reduced number of the MRF nodes. The most important effect is, however, that it allows more robust segmentation of the foreground that is static in some frames. The method is evaluated on a subset of the standard SegTrack benchmark and yields competitive results against the state-of-the-art methods.

AB - We propose a novel approach to unsupervised video segmentation based on the trajectories of Temporal Super-pixels (TSPs). We cast the segmentation problem as a trajectory-labeling problem and define a Markov random field on a graph in which each node represents a trajectory of TSPs, which we minimize using a new two-stage optimization method we developed. The adaption of the trajectories as basic building blocks brings several advantages over conventional superpixel-based methods, such as more expressive potential functions, temporal coherence of the resulting segmentation, and drastically reduced number of the MRF nodes. The most important effect is, however, that it allows more robust segmentation of the foreground that is static in some frames. The method is evaluated on a subset of the standard SegTrack benchmark and yields competitive results against the state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85027851736&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027851736&partnerID=8YFLogxK

U2 - 10.23919/MVA.2017.7986897

DO - 10.23919/MVA.2017.7986897

M3 - Conference contribution

AN - SCOPUS:85027851736

SP - 448

EP - 451

BT - Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -