Incremental Video Event Learning

Abstract : We propose a new approach for video event learning. The only hypothesis is the availability of tracked object attributes. The approach incrementally aggregates the attributes and reliability information of tracked objects to learn a hierarchy of state and event concepts. Simultaneously, the approach recognises the states and events of the tracked objects. This approach proposes an automatic bridge between the low-level image data and higher level conceptual information. The approach has been evaluated for more than two hours of an elderly care application. The results show the capability of the approach to learn and recognise meaningful events occurring in the scene. Also, the results show the potential of the approach for giving a description of the activities of a person (e.g. approaching to a table, crouching), and to detect abnormal events based on the frequency of occurrence.
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/inria-00512502
Contributor : Monique Thonnat <>
Submitted on : Monday, August 30, 2010 - 3:51:15 PM
Last modification on : Tuesday, July 24, 2018 - 3:48:06 PM
Long-term archiving on : Thursday, December 1, 2016 - 5:54:37 PM

File

ICVS2009.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00512502, version 1

Collections

Citation

Marcos Zuniga, François Bremond, Monique Thonnat. Incremental Video Event Learning. 7th International Conference on Computer Vision Systems, ICVS, Oct 2009, Liege, Belgium. ⟨inria-00512502⟩

Share

Metrics

Record views

243

Files downloads

202