Will They Have A Fight? The Predictability of Natural Behaviour Viewed Thro ugh CCTV Cameras

T Troscianko, A Holmes, J Stillman, M Mirmehdi, D Wright

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

Abstract

Can closed-circuit TV (CCTV) surveillance allow potentially antisocial or criminal behaviour to be predicted? We report a study whose aims were (a) whethe r observers can successfully predict the onset of such behaviour; (b) whether there may be a difference between na\357ve and professional observers; (c) where, in the s equence of events, it is possible to make this prediction. We obtained 100 sample sc enes from urban locations in UK. 18 of these led to criminal behaviour (fights, vand alism). A further 18 scenes were matched as closely as possible to the crime example s, but did not lead to any crime. 64 were neutral scenes chosen from a wide variety of non-criminal situations. A signal-detection paradigm (yes/no, and 6-point confide nce rating scale) was used. Results on 50 na\357ve and 50 professional observers sho w (a) that observers can distinguish crime sequences from matches, with d'e=1.17; (b ) that there is no difference between the na\357ve observers and the experts; (c) th at there are key types of behaviour (particularly gestures and body position) that a llow prediction to be made. In principle, it may be possible to detect such aspects of behaviour and therefore produce alerting mechanisms.
Translated title of the contributionWill They Have A Fight? The Predictability of Natural Behaviour Viewed Thro ugh CCTV Cameras
Original languageEnglish
Title of host publicationUnknown
PublisherPion Ltd.
Pages72 - 72
Number of pages0
Publication statusPublished - Aug 2001

Bibliographical note

Conference Proceedings/Title of Journal: European Conference on Visual Perception 2001, Perception Vol 30 Supple ment

Fingerprint

Dive into the research topics of 'Will They Have A Fight? The Predictability of Natural Behaviour Viewed Thro ugh CCTV Cameras'. Together they form a unique fingerprint.

Cite this