Activity detection of untrimmed CCTV ATM footage using 3D convolutional neural network

Aldi Hilman Ramadhani; Dina Chahyati

doi:10.1109/ICACSIS51025.2020.9263171

Activity detection of untrimmed CCTV ATM footage using 3D convolutional neural network

Aldi Hilman Ramadhani, Dina Chahyati

Department of Computer Science

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

Abstract

This paper presents an approach to temporal human activity detection using the proposal then classification framework, which is one of the frameworks for temporal activity detection. The goal of this research is to detect and recognize certain activities at the ATM. We propose an activity detection method using a 3D convolutional neural network (3D CNN). Our proposed method achieved performance with the accuracy score of 93.94%, a precision of 96.36%, a recall of 93.94%, and an f-score of 93.69%.

Original language	English
Title of host publication	2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	357-362
Number of pages	6
ISBN (Electronic)	9781728192796
DOIs	https://doi.org/10.1109/ICACSIS51025.2020.9263171
Publication status	Published - 17 Oct 2020
Event	12th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020 - Virtual, Depok, Indonesia Duration: 17 Oct 2020 → 18 Oct 2020

Publication series

Name	2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020

Conference

Conference	12th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020
Country/Territory	Indonesia
City	Virtual, Depok
Period	17/10/20 → 18/10/20

Keywords

Activity at the ATM
Activity detection
Activity recognition
Computer vision
Convolutional neural network

Access to Document

10.1109/ICACSIS51025.2020.9263171

Cite this

Ramadhani, A. H., & Chahyati, D. (2020). Activity detection of untrimmed CCTV ATM footage using 3D convolutional neural network. In 2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020 (pp. 357-362). Article 9263171 (2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICACSIS51025.2020.9263171

Ramadhani, Aldi Hilman ; Chahyati, Dina. / Activity detection of untrimmed CCTV ATM footage using 3D convolutional neural network. 2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 357-362 (2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020).

@inproceedings{35f1556f3e2949f6a940ebd0b62069e5,

title = "Activity detection of untrimmed CCTV ATM footage using 3D convolutional neural network",

abstract = "This paper presents an approach to temporal human activity detection using the proposal then classification framework, which is one of the frameworks for temporal activity detection. The goal of this research is to detect and recognize certain activities at the ATM. We propose an activity detection method using a 3D convolutional neural network (3D CNN). Our proposed method achieved performance with the accuracy score of 93.94%, a precision of 96.36%, a recall of 93.94%, and an f-score of 93.69%.",

keywords = "Activity at the ATM, Activity detection, Activity recognition, Computer vision, Convolutional neural network",

author = "Ramadhani, {Aldi Hilman} and Dina Chahyati",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; 12th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020 ; Conference date: 17-10-2020 Through 18-10-2020",

year = "2020",

month = oct,

day = "17",

doi = "10.1109/ICACSIS51025.2020.9263171",

language = "English",

series = "2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020",

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

pages = "357--362",

booktitle = "2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020",

address = "United States",

}

Ramadhani, AH & Chahyati, D 2020, Activity detection of untrimmed CCTV ATM footage using 3D convolutional neural network. in 2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020., 9263171, 2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020, Institute of Electrical and Electronics Engineers Inc., pp. 357-362, 12th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020, Virtual, Depok, Indonesia, 17/10/20. https://doi.org/10.1109/ICACSIS51025.2020.9263171

Activity detection of untrimmed CCTV ATM footage using 3D convolutional neural network. / Ramadhani, Aldi Hilman; Chahyati, Dina.
2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 357-362 9263171 (2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020).

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

TY - GEN

T1 - Activity detection of untrimmed CCTV ATM footage using 3D convolutional neural network

AU - Ramadhani, Aldi Hilman

AU - Chahyati, Dina

PY - 2020/10/17

Y1 - 2020/10/17

N2 - This paper presents an approach to temporal human activity detection using the proposal then classification framework, which is one of the frameworks for temporal activity detection. The goal of this research is to detect and recognize certain activities at the ATM. We propose an activity detection method using a 3D convolutional neural network (3D CNN). Our proposed method achieved performance with the accuracy score of 93.94%, a precision of 96.36%, a recall of 93.94%, and an f-score of 93.69%.

AB - This paper presents an approach to temporal human activity detection using the proposal then classification framework, which is one of the frameworks for temporal activity detection. The goal of this research is to detect and recognize certain activities at the ATM. We propose an activity detection method using a 3D convolutional neural network (3D CNN). Our proposed method achieved performance with the accuracy score of 93.94%, a precision of 96.36%, a recall of 93.94%, and an f-score of 93.69%.

KW - Activity at the ATM

KW - Activity detection

KW - Activity recognition

KW - Computer vision

KW - Convolutional neural network

UR - http://www.scopus.com/inward/record.url?scp=85099743011&partnerID=8YFLogxK

U2 - 10.1109/ICACSIS51025.2020.9263171

DO - 10.1109/ICACSIS51025.2020.9263171

M3 - Conference contribution

AN - SCOPUS:85099743011

T3 - 2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020

SP - 357

EP - 362

BT - 2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020

Y2 - 17 October 2020 through 18 October 2020

ER -

Ramadhani AH, Chahyati D. Activity detection of untrimmed CCTV ATM footage using 3D convolutional neural network. In 2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 357-362. 9263171. (2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020). doi: 10.1109/ICACSIS51025.2020.9263171

Activity detection of untrimmed CCTV ATM footage using 3D convolutional neural network

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this