Anomaly detection in a crowd using a cascade of deep learning networks

Peng Qiu; Sumi Kim; Jeong Hyu Lee; Jaeho Choi

doi:10.1007/978-981-10-7512-4_59

Anomaly detection in a crowd using a cascade of deep learning networks

Peng Qiu
, Sumi Kim
, Jeong Hyu Lee
, Jaeho Choi^*

^*Corresponding author for this work

Division of Electronic Engineering

Nanjing Institute of Technology
Seoyeong University
CBNU

Research output: Contribution to conference › Conference paper › peer-review

6 Scopus citations

Abstract

Anomaly detection allows to detect whereabouts of aberrant objects. In this paper, we propose anomaly detection using two connected neural networks. At the front, the convolutional neural network is used to extract visual features and the recurrent neural network implemented using a long short-term memory (LSTM) is followed to track and detect anomaly. In comparison to the conventional CNN and RNN method, the proposed method is capable of faster learning and is able to effectively detect anomaly objects.

Original language	English
Title of host publication	Information Systems Design and Intelligent Applications - Proceedings of 4th International Conference INDIA 2017
Editors	Vikrant Bhateja, Bao Le Nguyen, Nhu Gia Nguyen, Suresh Chandra Satapathy, Dac-Nhuong Le
Publisher	Springer Verlag
Pages	596-607
Number of pages	12
ISBN (Print)	9789811075117
DOIs	https://doi.org/10.1007/978-981-10-7512-4_59
State	Published - 2018
Event	4th International Conference on Information Systems Design and Intelligent Applications, INDIA 2017 - Da Nang, Viet Nam Duration: 2017.06.15 → 2017.06.17

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	672
ISSN (Print)	2194-5357

Conference

Conference	4th International Conference on Information Systems Design and Intelligent Applications, INDIA 2017
Country/Territory	Viet Nam
City	Da Nang
Period	17.06.15 → 17.06.17

Quacquarelli Symonds(QS) Subject Topics

Computer Science & Information Systems

Access to Document

10.1007/978-981-10-7512-4_59

Cite this

Qiu, P., Kim, S., Lee, J. H., & Choi, J. (2018). Anomaly detection in a crowd using a cascade of deep learning networks. In V. Bhateja, B. L. Nguyen, N. G. Nguyen, S. C. Satapathy, & D.-N. Le (Eds.), Information Systems Design and Intelligent Applications - Proceedings of 4th International Conference INDIA 2017 (pp. 596-607). (Advances in Intelligent Systems and Computing; Vol. 672). Springer Verlag. https://doi.org/10.1007/978-981-10-7512-4_59

Qiu, Peng ; Kim, Sumi ; Lee, Jeong Hyu et al. / Anomaly detection in a crowd using a cascade of deep learning networks. Information Systems Design and Intelligent Applications - Proceedings of 4th International Conference INDIA 2017. editor / Vikrant Bhateja ; Bao Le Nguyen ; Nhu Gia Nguyen ; Suresh Chandra Satapathy ; Dac-Nhuong Le. Springer Verlag, 2018. pp. 596-607 (Advances in Intelligent Systems and Computing).

@inproceedings{dd4c021c0a3d4609a3498d2d8ddcd2d5,

title = "Anomaly detection in a crowd using a cascade of deep learning networks",

abstract = "Anomaly detection allows to detect whereabouts of aberrant objects. In this paper, we propose anomaly detection using two connected neural networks. At the front, the convolutional neural network is used to extract visual features and the recurrent neural network implemented using a long short-term memory (LSTM) is followed to track and detect anomaly. In comparison to the conventional CNN and RNN method, the proposed method is capable of faster learning and is able to effectively detect anomaly objects.",

author = "Peng Qiu and Sumi Kim and Lee, \{Jeong Hyu\} and Jaeho Choi",

note = "Publisher Copyright: {\textcopyright} Springer Nature Singapore Pte Ltd. 2018.; 4th International Conference on Information Systems Design and Intelligent Applications, INDIA 2017 ; Conference date: 15-06-2017 Through 17-06-2017",

year = "2018",

doi = "10.1007/978-981-10-7512-4\_59",

language = "English",

isbn = "9789811075117",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Verlag",

pages = "596--607",

editor = "Vikrant Bhateja and Nguyen, \{Bao Le\} and Nguyen, \{Nhu Gia\} and Satapathy, \{Suresh Chandra\} and Dac-Nhuong Le",

booktitle = "Information Systems Design and Intelligent Applications - Proceedings of 4th International Conference INDIA 2017",

}

Qiu, P, Kim, S, Lee, JH & Choi, J 2018, Anomaly detection in a crowd using a cascade of deep learning networks. in V Bhateja, BL Nguyen, NG Nguyen, SC Satapathy & D-N Le (eds), Information Systems Design and Intelligent Applications - Proceedings of 4th International Conference INDIA 2017. Advances in Intelligent Systems and Computing, vol. 672, Springer Verlag, pp. 596-607, 4th International Conference on Information Systems Design and Intelligent Applications, INDIA 2017, Da Nang, Viet Nam, 17.06.15. https://doi.org/10.1007/978-981-10-7512-4_59

Anomaly detection in a crowd using a cascade of deep learning networks. / Qiu, Peng; Kim, Sumi; Lee, Jeong Hyu et al.
Information Systems Design and Intelligent Applications - Proceedings of 4th International Conference INDIA 2017. ed. / Vikrant Bhateja; Bao Le Nguyen; Nhu Gia Nguyen; Suresh Chandra Satapathy; Dac-Nhuong Le. Springer Verlag, 2018. p. 596-607 (Advances in Intelligent Systems and Computing; Vol. 672).

Research output: Contribution to conference › Conference paper › peer-review

TY - GEN

T1 - Anomaly detection in a crowd using a cascade of deep learning networks

AU - Qiu, Peng

AU - Kim, Sumi

AU - Lee, Jeong Hyu

AU - Choi, Jaeho

N1 - Publisher Copyright: © Springer Nature Singapore Pte Ltd. 2018.

PY - 2018

Y1 - 2018

N2 - Anomaly detection allows to detect whereabouts of aberrant objects. In this paper, we propose anomaly detection using two connected neural networks. At the front, the convolutional neural network is used to extract visual features and the recurrent neural network implemented using a long short-term memory (LSTM) is followed to track and detect anomaly. In comparison to the conventional CNN and RNN method, the proposed method is capable of faster learning and is able to effectively detect anomaly objects.

AB - Anomaly detection allows to detect whereabouts of aberrant objects. In this paper, we propose anomaly detection using two connected neural networks. At the front, the convolutional neural network is used to extract visual features and the recurrent neural network implemented using a long short-term memory (LSTM) is followed to track and detect anomaly. In comparison to the conventional CNN and RNN method, the proposed method is capable of faster learning and is able to effectively detect anomaly objects.

UR - https://www.scopus.com/pages/publications/85043757519

U2 - 10.1007/978-981-10-7512-4_59

DO - 10.1007/978-981-10-7512-4_59

M3 - Conference paper

AN - SCOPUS:85043757519

SN - 9789811075117

T3 - Advances in Intelligent Systems and Computing

SP - 596

EP - 607

BT - Information Systems Design and Intelligent Applications - Proceedings of 4th International Conference INDIA 2017

A2 - Bhateja, Vikrant

A2 - Nguyen, Bao Le

A2 - Nguyen, Nhu Gia

A2 - Satapathy, Suresh Chandra

A2 - Le, Dac-Nhuong

PB - Springer Verlag

T2 - 4th International Conference on Information Systems Design and Intelligent Applications, INDIA 2017

Y2 - 15 June 2017 through 17 June 2017

ER -

Qiu P, Kim S, Lee JH, Choi J. Anomaly detection in a crowd using a cascade of deep learning networks. In Bhateja V, Nguyen BL, Nguyen NG, Satapathy SC, Le DN, editors, Information Systems Design and Intelligent Applications - Proceedings of 4th International Conference INDIA 2017. Springer Verlag. 2018. p. 596-607. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-981-10-7512-4_59

Anomaly detection in a crowd using a cascade of deep learning networks

Abstract

Publication series

Conference

Quacquarelli Symonds(QS) Subject Topics

Access to Document

Other files and links

Fingerprint

Cite this