Semantic Activity Recognition

Monique Thonnat 1
Abstract : Extracting automatically the semantics from visual data is a real challenge. We describe in this paper how recent work in cognitive vision leads to significative results in activity recognition for visualsurveillance and video monitoring. In particular we present work performed in the domain of video understanding in our PULSAR team at INRIA in Sophia Antipolis. Our main objective is to analyse in real-time video streams captured by static video cameras and to recognize their semantic content. We present a cognitive vision approach mixing 4D computer vision techniques and activity recognition based on a priori knowledge. Applications in visualsurveillance and healthcare monitoring are shown. We conclude by current issues in cognitive vision for activity recognition.
Complete list of metadatas

https://hal.inria.fr/inria-00502249
Contributor : Monique Thonnat <>
Submitted on : Tuesday, July 13, 2010 - 3:34:15 PM
Last modification on : Saturday, January 27, 2018 - 1:30:50 AM
Long-term archiving on : Thursday, October 14, 2010 - 3:43:31 PM

File

thonnatecai2008.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00502249, version 1

Collections

Citation

Monique Thonnat. Semantic Activity Recognition. 18th European Conference on Artificial Intelligence ECAI 2008, Jul 2008, Patras, Greece. pp 3-7. ⟨inria-00502249⟩

Share

Metrics

Record views

306

Files downloads

224