Violence Detection for Video Surveillance System Using Irregular Motion Information
- Authors
- Ha, Jinsol; Park, Jinho; Kim, Heegwang; Park, Hasil; Paik, Joonki
- Issue Date
- Jan-2018
- Publisher
- IEEE
- Keywords
- Violence detection; Human action analysis; Video surveillance system
- Citation
- 2018 INTERNATIONAL CONFERENCE ON ELECTRONICS, INFORMATION, AND COMMUNICATION (ICEIC), v.2018-January, pp 363 - 365
- Pages
- 3
- Journal Title
- 2018 INTERNATIONAL CONFERENCE ON ELECTRONICS, INFORMATION, AND COMMUNICATION (ICEIC)
- Volume
- 2018-January
- Start Page
- 363
- End Page
- 365
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/56205
- DOI
- 10.23919/ELINFOCOM.2018.8330609
- ISSN
- 2377-8431
- Abstract
- In this paper, we proposed violence detection method in surveillance video system. The proposed method consists of 4 steps: i) Detect the object region within a video image by background subtraction method and apply the morphology filter to reduce noise artifacts. ii) Estimate the motion vector using the Combined Local-Global approach with Total Variation (CLG-TV) in the object region. iii) Detect the violence event by analyzing the characteristic of motion vectors generated in the region of object by using the Motion Co-occurrence Feature (MCF).
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School of Advanced Imaging Sciences, Multimedia and Film > Department of Imaging Science and Arts > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.