“Not the Usual Suspects”: A study of factors reducing the effectiveness of CCTV

Keval, Hina; Sasse, M. Angela

doi:10.1057/palgrave.sj.8350092

Cited by 43 publications

(27 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, current systems are actually quite burdensome for human operators because they are required to watch a large quantity of screens (usually up to 50 [1]) which show the content captured by several different cameras. Detecting unusual individuals and events [2], a.k.a., anomalies, is one of the most important and main tasks of human operators. Thus the performance of anomaly detection is highly dependent on the human operators.…”

Section: Introductionmentioning

confidence: 99%

Anomaly Detection via Midlevel Visual Attributes

Tan

Zhang

Zha

2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Automatically discovering anomalous events and objects from surveillance videos plays an important role in real-world application and has attracted considerable attention in computer vision community. However it is still a challenging issue. In this paper, a novel approach for automatic anomaly detection is proposed. Our approach is highly efficient; thus it can perform real-time detection. Furthermore, it can also handle multiscale detection and can cope with spatial and temporal anomalies. Specifically, local features capturing both appearance and motion characteristics of videos are extracted from spatiotemporal video volume (STV). To bridge the large semantic gap between low-level visual feature and high-level event, we use the middle-level visual attributes as the intermediary. And these three-level framework is modeled as an extreme learning machine (ELM). We propose to use the spatiotemporal pyramid (STP) to capture the spatial and temporal continuity of an anomalous even, enabling our approach to cope with multiscale and complicated events. Furthermore, we propose a method to efficiently update the ELM; thus our approach is self-adaptive to background change which often occurs in real-world application. Experiments on several datasets are carried out and the superior performance of our approach compared to the state-of-the-art approaches verifies its effectiveness.

show abstract

Section: Introductionmentioning

confidence: 99%

Anomaly Detection via Midlevel Visual Attributes

Tan

Zhang

Zha

2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…This has been attributed to many factors, including the detection rates of operators van Voorthuijsen et al , 2005 ;Wells et al , 2006 ;Keval and Sasse, 2010 ). Detection rates in real-time CCTV surveillance vary considerably for different conditions, types of scenes and signifi cant events.…”

Section: Introductionmentioning

confidence: 99%

CCTV: A challenging case for threat image projection implementation

Donald

2012

Secur J

View full text Add to dashboard Cite

This study examines an intervention aimed at improving the detection rates of closed circuit television (CCTV) operators during real-time surveillance. The intervention consists of electronically inserting graphic objects (IGOs) into video stream with the intention of assisting operators in detecting actual signifi cant events. It is based on threat image projection (TIP) that has been used to heighten the performance of X-ray baggage screeners. Seventy-three participants observed a 90-min CCTV video from an industrial plant, showing both normal work activity and signifi cant events. The control group received no IGOs, one treatment group received generic IGOs, and the second treatment group received IGOs with small semantic distances to target behaviours. There were indications that the IGOs had positive effects on alertness and attention sets, but this was not statistically signifi cant. Reasons for this are discussed in terms of differences between the CCTV and baggage screening or TIP contexts.

show abstract

“…Most CCTV systems in Australia and the UK have the reduction of alcohol-related violence and disorder as a goal,6–8 but evaluations of the effectiveness of these systems in reducing injuries are hard to find 4–6 8–10. Operational practices in open-space CCTV camera rooms have been identified as critical for promptly detecting antisocial behaviour and violence8 9 11 and are a growing area of research 11–13. Evidence suggests that violence in LNEPs is a staged process14 and that observers of CCTV footage can differentiate between behavioural sequences ending in violence and matched sequences which do not 15.…”

Section: Introductionmentioning

confidence: 99%

The role of an open-space CCTV system in limiting alcohol-related assault injuries in a late-night entertainment precinct in a tropical Queensland city, Australia

et al. 2011

View full text Add to dashboard Cite

Closed circuit television (CCTV) systems which incorporate real-time communication links between camera room operators and on-the-ground security may limit injuries resulting from alcohol-related assault. This pilot study examined CCTV footage and operator records of security responses for two periods totalling 22 days in 2010-2011 when 30 alcohol-related assaults were recorded. Semistructured discussions were conducted with camera room operators during 18 h of observation. Camera operators were proactive, efficiently directing street security to assault incidents. The system intervened in 40% (n=12) of alcohol-related assaults, limiting possible injury. This included three incidents judged as potentially preventable. A further five (17%) assault incidents were also judged as potentially preventable, while 43% (n=13) happened too quickly for intervention. Case studies describe security intervention in each category. Further research is recommended, particularly to evaluate the effects on preventing injuries through targeted awareness training to improve responsiveness and enhance the preventative capacity of similar CCTV systems.

show abstract

“Not the Usual Suspects”: A study of factors reducing the effectiveness of CCTV

Cited by 43 publications

References 6 publications

Anomaly Detection via Midlevel Visual Attributes

Anomaly Detection via Midlevel Visual Attributes

CCTV: A challenging case for threat image projection implementation

The role of an open-space CCTV system in limiting alcohol-related assault injuries in a late-night entertainment precinct in a tropical Queensland city, Australia

Contact Info

Product

Resources

About