Image fusion and influence function for performance improvement of ATM vandalism action recognition

Jeongseop Yun; Junyeop Lee; Seongkyu Mun; Chul Jin Cho; David K. Han; Hanseok Ko

doi:10.1109/AVSS.2018.8639091

Image fusion and influence function for performance improvement of ATM vandalism action recognition

Jeongseop Yun, Junyeop Lee, Seongkyu Mun, Chul Jin Cho, David K. Han, Hanseok Ko

School of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Rising rate of vandalism against Automatic Teller Machines (ATMs) is a serious issue within banking industries, prompting needs of a technology to autonomously recognize such events. A vision based fusion method proposed here for classifying these incidents is rooted on visually recognizing heavy or sharp objects potentially used for detecting vandalism actions inferred from optical flow. The recognition performance has been improved chiefly by a novel employment of influence functions in selecting data points of each class useful in learning. We show that the tool recognition performance can be improved when the training data is selected from the ImageNet data set as guided by the influence function.

Original language	English
Title of host publication	Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538692943
DOIs	https://doi.org/10.1109/AVSS.2018.8639091
Publication status	Published - 2018 Jul 2
Event	15th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2018 - Auckland, New Zealand Duration: 2018 Nov 27 → 2018 Nov 30

Publication series

Name	Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance

Conference

Conference	15th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2018
Country/Territory	New Zealand
City	Auckland
Period	18/11/27 → 18/11/30

Bibliographical note

Funding Information:
This work was supported in part by the National Research Foundation (NRF) grant funded by the MSIP (No. 2017R1A2B4012720) and by the US Army Research Laboratory.

Publisher Copyright:
© 2018 IEEE.

ASJC Scopus subject areas

Signal Processing
Computer Vision and Pattern Recognition
Hardware and Architecture
Media Technology

Access to Document

10.1109/AVSS.2018.8639091

Cite this

Yun, J., Lee, J., Mun, S., Cho, C. J., Han, D. K., & Ko, H. (2018). Image fusion and influence function for performance improvement of ATM vandalism action recognition. In Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance Article 8639091 (Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AVSS.2018.8639091

Image fusion and influence function for performance improvement of ATM vandalism action recognition. / Yun, Jeongseop; Lee, Junyeop; Mun, Seongkyu et al.
Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance. Institute of Electrical and Electronics Engineers Inc., 2018. 8639091 (Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Yun, J, Lee, J, Mun, S, Cho, CJ, Han, DK & Ko, H 2018, Image fusion and influence function for performance improvement of ATM vandalism action recognition. in Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance., 8639091, Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance, Institute of Electrical and Electronics Engineers Inc., 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2018, Auckland, New Zealand, 18/11/27. https://doi.org/10.1109/AVSS.2018.8639091

Yun J, Lee J, Mun S, Cho CJ, Han DK, Ko H. Image fusion and influence function for performance improvement of ATM vandalism action recognition. In Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance. Institute of Electrical and Electronics Engineers Inc. 2018. 8639091. (Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance). doi: 10.1109/AVSS.2018.8639091

Yun, Jeongseop ; Lee, Junyeop ; Mun, Seongkyu et al. / Image fusion and influence function for performance improvement of ATM vandalism action recognition. Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance. Institute of Electrical and Electronics Engineers Inc., 2018. (Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance).

@inproceedings{44e84f1ee6b6453d8d32921c1a48b509,

title = "Image fusion and influence function for performance improvement of ATM vandalism action recognition",

abstract = "Rising rate of vandalism against Automatic Teller Machines (ATMs) is a serious issue within banking industries, prompting needs of a technology to autonomously recognize such events. A vision based fusion method proposed here for classifying these incidents is rooted on visually recognizing heavy or sharp objects potentially used for detecting vandalism actions inferred from optical flow. The recognition performance has been improved chiefly by a novel employment of influence functions in selecting data points of each class useful in learning. We show that the tool recognition performance can be improved when the training data is selected from the ImageNet data set as guided by the influence function.",

author = "Jeongseop Yun and Junyeop Lee and Seongkyu Mun and Cho, {Chul Jin} and Han, {David K.} and Hanseok Ko",

note = "Funding Information: This work was supported in part by the National Research Foundation (NRF) grant funded by the MSIP (No. 2017R1A2B4012720) and by the US Army Research Laboratory. Publisher Copyright: {\textcopyright} 2018 IEEE.; 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2018 ; Conference date: 27-11-2018 Through 30-11-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/AVSS.2018.8639091",

language = "English",

series = "Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance",

}

TY - GEN

T1 - Image fusion and influence function for performance improvement of ATM vandalism action recognition

AU - Yun, Jeongseop

AU - Lee, Junyeop

AU - Mun, Seongkyu

AU - Cho, Chul Jin

AU - Han, David K.

AU - Ko, Hanseok

N1 - Funding Information: This work was supported in part by the National Research Foundation (NRF) grant funded by the MSIP (No. 2017R1A2B4012720) and by the US Army Research Laboratory. Publisher Copyright: © 2018 IEEE.

PY - 2018/7/2

Y1 - 2018/7/2

N2 - Rising rate of vandalism against Automatic Teller Machines (ATMs) is a serious issue within banking industries, prompting needs of a technology to autonomously recognize such events. A vision based fusion method proposed here for classifying these incidents is rooted on visually recognizing heavy or sharp objects potentially used for detecting vandalism actions inferred from optical flow. The recognition performance has been improved chiefly by a novel employment of influence functions in selecting data points of each class useful in learning. We show that the tool recognition performance can be improved when the training data is selected from the ImageNet data set as guided by the influence function.

AB - Rising rate of vandalism against Automatic Teller Machines (ATMs) is a serious issue within banking industries, prompting needs of a technology to autonomously recognize such events. A vision based fusion method proposed here for classifying these incidents is rooted on visually recognizing heavy or sharp objects potentially used for detecting vandalism actions inferred from optical flow. The recognition performance has been improved chiefly by a novel employment of influence functions in selecting data points of each class useful in learning. We show that the tool recognition performance can be improved when the training data is selected from the ImageNet data set as guided by the influence function.

UR - http://www.scopus.com/inward/record.url?scp=85063269401&partnerID=8YFLogxK

U2 - 10.1109/AVSS.2018.8639091

DO - 10.1109/AVSS.2018.8639091

M3 - Conference contribution

AN - SCOPUS:85063269401

T3 - Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance

BT - Proceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2018

Y2 - 27 November 2018 through 30 November 2018

ER -

Image fusion and influence function for performance improvement of ATM vandalism action recognition

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this