Local group relationship analysis for group activity recognition

Dong Gyu Lee, Pil Soo Kim, Seong Whan Lee

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

1 Citation (Scopus)

Abstract

In this paper, we present an approach that exploits local group relationship to tackle the human group activity recognition problem. Specifically, rather than analyze every human motion, we first grouping individual human object into local groups to represent the relationship in the overall scene. The important movement information is maximized by modeling both each human motion and local group relationships. The gated recurrent unit model has been adopted to handle an arbitrary length of trajectory information with non-linear hidden units. In our experiment on public human group activity dataset, we compared the performance of proposed method with that of other competing methods and showed that the proposed method outperforms others.

Original languageEnglish
Title of host publicationICCAS 2017 - 2017 17th International Conference on Control, Automation and Systems - Proceedings
PublisherIEEE Computer Society
Pages236-238
Number of pages3
Volume2017-October
ISBN (Electronic)9788993215137
DOIs
Publication statusPublished - 2017 Dec 13
Event17th International Conference on Control, Automation and Systems, ICCAS 2017 - Jeju, Korea, Republic of
Duration: 2017 Oct 182017 Oct 21

Other

Other17th International Conference on Control, Automation and Systems, ICCAS 2017
CountryKorea, Republic of
CityJeju
Period17/10/1817/10/21

Fingerprint

Trajectories
Experiments

Keywords

  • Gated recurrent unit
  • Group activity recognition
  • Local group relationship
  • Video surveillance

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Lee, D. G., Kim, P. S., & Lee, S. W. (2017). Local group relationship analysis for group activity recognition. In ICCAS 2017 - 2017 17th International Conference on Control, Automation and Systems - Proceedings (Vol. 2017-October, pp. 236-238). IEEE Computer Society. https://doi.org/10.23919/ICCAS.2017.8204447

Local group relationship analysis for group activity recognition. / Lee, Dong Gyu; Kim, Pil Soo; Lee, Seong Whan.

ICCAS 2017 - 2017 17th International Conference on Control, Automation and Systems - Proceedings. Vol. 2017-October IEEE Computer Society, 2017. p. 236-238.

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

Lee, DG, Kim, PS & Lee, SW 2017, Local group relationship analysis for group activity recognition. in ICCAS 2017 - 2017 17th International Conference on Control, Automation and Systems - Proceedings. vol. 2017-October, IEEE Computer Society, pp. 236-238, 17th International Conference on Control, Automation and Systems, ICCAS 2017, Jeju, Korea, Republic of, 17/10/18. https://doi.org/10.23919/ICCAS.2017.8204447
Lee DG, Kim PS, Lee SW. Local group relationship analysis for group activity recognition. In ICCAS 2017 - 2017 17th International Conference on Control, Automation and Systems - Proceedings. Vol. 2017-October. IEEE Computer Society. 2017. p. 236-238 https://doi.org/10.23919/ICCAS.2017.8204447
Lee, Dong Gyu ; Kim, Pil Soo ; Lee, Seong Whan. / Local group relationship analysis for group activity recognition. ICCAS 2017 - 2017 17th International Conference on Control, Automation and Systems - Proceedings. Vol. 2017-October IEEE Computer Society, 2017. pp. 236-238
@inproceedings{fcd353d8b2544f95a035067ce87da535,
title = "Local group relationship analysis for group activity recognition",
abstract = "In this paper, we present an approach that exploits local group relationship to tackle the human group activity recognition problem. Specifically, rather than analyze every human motion, we first grouping individual human object into local groups to represent the relationship in the overall scene. The important movement information is maximized by modeling both each human motion and local group relationships. The gated recurrent unit model has been adopted to handle an arbitrary length of trajectory information with non-linear hidden units. In our experiment on public human group activity dataset, we compared the performance of proposed method with that of other competing methods and showed that the proposed method outperforms others.",
keywords = "Gated recurrent unit, Group activity recognition, Local group relationship, Video surveillance",
author = "Lee, {Dong Gyu} and Kim, {Pil Soo} and Lee, {Seong Whan}",
year = "2017",
month = "12",
day = "13",
doi = "10.23919/ICCAS.2017.8204447",
language = "English",
volume = "2017-October",
pages = "236--238",
booktitle = "ICCAS 2017 - 2017 17th International Conference on Control, Automation and Systems - Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Local group relationship analysis for group activity recognition

AU - Lee, Dong Gyu

AU - Kim, Pil Soo

AU - Lee, Seong Whan

PY - 2017/12/13

Y1 - 2017/12/13

N2 - In this paper, we present an approach that exploits local group relationship to tackle the human group activity recognition problem. Specifically, rather than analyze every human motion, we first grouping individual human object into local groups to represent the relationship in the overall scene. The important movement information is maximized by modeling both each human motion and local group relationships. The gated recurrent unit model has been adopted to handle an arbitrary length of trajectory information with non-linear hidden units. In our experiment on public human group activity dataset, we compared the performance of proposed method with that of other competing methods and showed that the proposed method outperforms others.

AB - In this paper, we present an approach that exploits local group relationship to tackle the human group activity recognition problem. Specifically, rather than analyze every human motion, we first grouping individual human object into local groups to represent the relationship in the overall scene. The important movement information is maximized by modeling both each human motion and local group relationships. The gated recurrent unit model has been adopted to handle an arbitrary length of trajectory information with non-linear hidden units. In our experiment on public human group activity dataset, we compared the performance of proposed method with that of other competing methods and showed that the proposed method outperforms others.

KW - Gated recurrent unit

KW - Group activity recognition

KW - Local group relationship

KW - Video surveillance

UR - http://www.scopus.com/inward/record.url?scp=85044464831&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044464831&partnerID=8YFLogxK

U2 - 10.23919/ICCAS.2017.8204447

DO - 10.23919/ICCAS.2017.8204447

M3 - Conference contribution

AN - SCOPUS:85044464831

VL - 2017-October

SP - 236

EP - 238

BT - ICCAS 2017 - 2017 17th International Conference on Control, Automation and Systems - Proceedings

PB - IEEE Computer Society

ER -