Paper Info
Title
Real-Time Automatic Detection of Violent-Acts by Low-Level Colour Visual Cues
Abstract
Automatic recognition of human activities is important for the development of next generation video-surveillance systems. In this paper we address the specific problem of automatically detecting violent interpersonal acts in monocular colour video streams. Unlikely previous approaches, only little knowledge is assumed about the acquisition setup and about the content of the acquired scenes. So the proposed approach is suitable in a wide range of practical cases. Reliability and general-purpose applicability is achieved by analysing low-level features (like the spatial-temporal behaviour of coloured stains), and by measuring some warping and motion parameters. In this way it is not necessary to extract accurate target silhouettes, that is a critical task because of occlusions and overcrowding that are typical during interpersonal contacts. A suitable index called Maximum Warping Energy (MWE) has been defined to describe the localized spatial-temporal complexity of colour conformations. Our experiments show that aggressive activities give significantly higher MWE values if compared with safe actions like: walking, running, embracing or handshaking. So it is possible to distinguish violent acts from normal behaviours even in presence of many people and crowded environments. Homography is used to improve robustness by verifying the real targets nearness. False interactions because of perspective- induced occlusions are discarded.
Year
DOI
Venue
2007
10.1109/ICIP.2007.4378962
ICIP
Keywords
Field
DocType
image colour analysis,video surveillance,automatic recognition,homography,low-level colour visual cues,maximum warping energy,monocular colour video stream,perspective-induced occlusion,real-time automatic detection,spatial-temporal complexity,video-surveillance system,Image Processing,Violent Acts Recognition
Sensory cue,Computer vision,Interpersonal communication,Image warping,Pattern recognition,Computer science,Image processing,Robustness (computer science),Homography,Handshaking,Artificial intelligence,Monocular
Conference
Volume
ISSN
Citations 
1
1522-4880
5
PageRank 
References 
Authors
0.49
2
2
Name
Order
Citations
PageRank
Alessandro Mecocci16014.38
Francesco Micheli250.83