Title :
Hierarchical Language-based Representation of Events in Video Streams
Author :
Nevatia, Ram ; Zhao, Tao ; Hongeng, Somboon
Author_Institution :
University of Southern California, Los Angeles
Abstract :
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.
Keywords :
Hidden Markov models; Humans; Intelligent robots; Intelligent systems; Logic; Ontologies; Pattern recognition; Streaming media; Videoconference; Yarn;
Conference_Titel :
Computer Vision and Pattern Recognition Workshop, 2003. CVPRW '03. Conference on
Conference_Location :
Madison, Wisconsin, USA
Print_ISBN :
0-7695-1900-8
DOI :
10.1109/CVPRW.2003.10038