Automatic fight detection in surveillance videos. Issue 2 (5th June 2017)
- Record Type:
- Journal Article
- Title:
- Automatic fight detection in surveillance videos. Issue 2 (5th June 2017)
- Main Title:
- Automatic fight detection in surveillance videos
- Authors:
- Fu, Eugene Yujun
Leong, Hong Va
Ngai, Grace
Chan, Stephen C.F. - Abstract:
- Abstract : Purpose: Social signal processing under affective computing aims at recognizing and extracting useful human social interaction patterns. Fight is a common social interaction in real life. A fight detection system finds wide applications. This paper aims to detect fights in a natural and low-cost manner. Design/methodology/approach: Research works on fight detection are often based on visual features, demanding substantive computation and good video quality. In this paper, the authors propose an approach to detect fight events through motion analysis. Most existing works evaluated their algorithms on public data sets manifesting simulated fights, where the fights are acted out by actors. To evaluate real fights, the authors collected videos involving real fights to form a data set. Based on the two types of data sets, the authors evaluated the performance of their motion signal analysis algorithm, which was then compared with the state-of-the-art approach based on MoSIFT descriptors with Bag-of-Words mechanism, and basic motion signal analysis with Bag-of-Words. Findings: The experimental results indicate that the proposed approach accurately detects fights in real scenarios and performs better than the MoSIFT approach. Originality/value: By collecting and annotating real surveillance videos containing real fight events and augmenting with well-known data sets, the authors proposed, implemented and evaluated a low computation approach, comparing it with theAbstract : Purpose: Social signal processing under affective computing aims at recognizing and extracting useful human social interaction patterns. Fight is a common social interaction in real life. A fight detection system finds wide applications. This paper aims to detect fights in a natural and low-cost manner. Design/methodology/approach: Research works on fight detection are often based on visual features, demanding substantive computation and good video quality. In this paper, the authors propose an approach to detect fight events through motion analysis. Most existing works evaluated their algorithms on public data sets manifesting simulated fights, where the fights are acted out by actors. To evaluate real fights, the authors collected videos involving real fights to form a data set. Based on the two types of data sets, the authors evaluated the performance of their motion signal analysis algorithm, which was then compared with the state-of-the-art approach based on MoSIFT descriptors with Bag-of-Words mechanism, and basic motion signal analysis with Bag-of-Words. Findings: The experimental results indicate that the proposed approach accurately detects fights in real scenarios and performs better than the MoSIFT approach. Originality/value: By collecting and annotating real surveillance videos containing real fight events and augmenting with well-known data sets, the authors proposed, implemented and evaluated a low computation approach, comparing it with the state-of-the-art approach. The authors uncovered some fundamental differences between real and simulated fights and initiated a new study in discriminating real against simulated fight events, with very good performance. … (more)
- Is Part Of:
- International journal of pervasive computing and communications. Volume 13:Issue 2(2017)
- Journal:
- International journal of pervasive computing and communications
- Issue:
- Volume 13:Issue 2(2017)
- Issue Display:
- Volume 13, Issue 2 (2017)
- Year:
- 2017
- Volume:
- 13
- Issue:
- 2
- Issue Sort Value:
- 2017-0013-0002-0000
- Page Start:
- 130
- Page End:
- 156
- Publication Date:
- 2017-06-05
- Subjects:
- Optical flow -- Bag-of-words -- MoSIFT -- Motion analysis -- Real and simulated fights
Ubiquitous computing -- Periodicals
Mobile computing -- Periodicals
Computer network protocols -- Periodicals
Computer network architectures -- Periodicals
Application software -- Development -- Periodicals
004.6 - Journal URLs:
- http://info.emeraldinsight.com/products/journals/journals.htm?PHPSESSID=hprfp8ctb78gnbgodr3rkog6s0&id=ijpcc ↗
http://www.emeraldinsight.com/ ↗
http://www.troubador.co.uk/jpcc/ ↗ - DOI:
- 10.1108/IJPCC-02-2017-0018 ↗
- Languages:
- English
- ISSNs:
- 1742-7371
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 4542.452750
British Library DSC - BLDSS-3PM
British Library STI - ELD Digital store - Ingest File:
- 2925.xml