객체 탐지와 행동인식을 이용한 영상내의 비정상적인 상황 탐지 네트워크Abnormal Situation Detection on Surveillance Video Using Object Detection and Action Recognition
- Other Titles
- Abnormal Situation Detection on Surveillance Video Using Object Detection and Action Recognition
- Authors
- 김정훈; 최종혁; 박영호; 나스리디노프 아지즈
- Issue Date
- Feb-2021
- Publisher
- 한국멀티미디어학회
- Keywords
- Video Surveillance; Abnormal Situation Detection; Deep Neural Networ
- Citation
- 멀티미디어학회논문지, v.24, no.2, pp 186 - 198
- Pages
- 13
- Journal Title
- 멀티미디어학회논문지
- Volume
- 24
- Number
- 2
- Start Page
- 186
- End Page
- 198
- URI
- https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/146809
- DOI
- 10.9717/kmms.2020.24.2.186
- ISSN
- 1229-7771
- Abstract
- Security control using surveillance cameras is established when people observe all surveillance videos directly. However, this task is labor-intensive and it is difficult to detect all abnormal situations. In this paper, we propose a deep neural network model, called AT-Net, that automatically detects abnormal situations in the surveillance video, and introduces an automatic video surveillance system developed based on this network model. In particular, AT-Net alleviates the ambiguity of existing abnormal situation detection methods by mapping features representing relationships between people and objects in surveillance video to the new tensor structure based on sparse coding. Through experiments on actual surveillance videos, AT-Net achieved an F1-score of about 89%, and improved abnormal situation detection performance by more than 25% compared to existing methods.
- Files in This Item
-
Go to Link
- Appears in
Collections - ETC > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.