Hierarchical Language-based Representation of Events in Video Streams

We aim to define an event ontology that allows natural representation of complex spatio-temporal events common in the physical world by a composition of simpler events. The events are abstracted into three hierarchies. Primitive events are defined directly from the mobile object properties. Single-t...

Full description

Saved in:
Bibliographic Details
Published in2003 Conference on Computer Vision and Pattern Recognition Workshop Vol. 4; p. 39
Main Authors Nevatia, Ram, Zhao, Tao, Hongeng, Somboon
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2003
Subjects
Computer vision
Conferences
Distance measurement
Hidden Markov models
Humans
Mobile communication
Pattern recognition
Online AccessGet full text
ISBN0769519008
9780769519005
ISSN1063-6919
1063-6919
DOI10.1109/CVPRW.2003.10038

Cover

More Information
Summary:We aim to define an event ontology that allows natural representation of complex spatio-temporal events common in the physical world by a composition of simpler events. The events are abstracted into three hierarchies. Primitive events are defined directly from the mobile object properties. Single-thread composite events are a number of primitive events with temporal sequencing. Multi-thread composite events are a number of single-thread events with temporal/ spatial/logical relationships. This hierarchical event representation naturally leads to a language description of the events. We define an Event Recognition Language (ERL) which allows the users to define the events of interest conveniently without interacting with the low level processing in the program. We will also briefly mention some approaches to compute the proposed representation.
ISBN:0769519008
9780769519005
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPRW.2003.10038