File(s) under permanent embargo
Towards detecting patterns of human behaviour from image sequences
conference contribution
posted on 1995-01-01, 00:00 authored by R Hosie, Svetha VenkateshSvetha Venkatesh, G WestThis paper details research that will explore the analysis of human behaviour via video surveillance. Digital computer images will be obtained from video footage of a real world scene, and positions of people in the scene will be identified and tracked through each frame in the sequence.
The noted positions will build into a pattern of motion that can be examined and classified. It is proposed that specific events, such as panic or fight situations, will have unique, and therefore identifying, characteristics that will enable automatic detection of such events.
It is envisaged that active cameras will be used when a situation of interest occurs, to enable more information to be extracted from the scene (e.g., panning to follow action, or zooming to enhance detail.)
The noted positions will build into a pattern of motion that can be examined and classified. It is proposed that specific events, such as panic or fight situations, will have unique, and therefore identifying, characteristics that will enable automatic detection of such events.
It is envisaged that active cameras will be used when a situation of interest occurs, to enable more information to be extracted from the scene (e.g., panning to follow action, or zooming to enhance detail.)
History
Event
Artificial Intelligence in Defence Workshop (8th : 1995 : Canberra, A. C. T.)Pagination
109 - 121Publisher
DSTO Aeronautical and Maritime Research LaboratoryLocation
Canberra, A. C. T.Place of publication
Melbourne, Vic.Start date
1995-11-14Language
engPublication classification
E1.1 Full written paper - refereedCopyright notice
1997, Commonwealth of AustraliaEditor/Contributor(s)
S GossTitle of proceedings
AI'95 : Proceedings of the Artificial Intelligence in Defence Workshop : 8th Australian Joint Conference on Artificial IntelligenceUsage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC