Arrow Research search

Author name cluster

Monique Thonnat

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers
2 author rows

Possible papers

4

ECAI Conference 2008 Invited Paper

Semantic Activity Recognition

  • Monique Thonnat

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.

Details

IJCAI Conference 2003 Conference Paper

Automatic Video Interpretation: A Novel Algorithm for Temporal Scenario Recognition

  • Van-Thinh Vu
  • Francois Bremond
  • Monique Thonnat

This paper presents a new scenario recognition algorithm for Video Interpretation. We represent a scenario model by specifying the characters involved in the scenario, the sub-scenarios composing the scenario and the constraints combining the sub-scenarios. Various types of constraints can be used including spatio-temporal and logical constraints. In this paper, we focus on the performance of the recognition algorithm. Our goal is to propose an efficient algorithm for processing temporal constraints and combining several actors defined within the scenario. By efficient we mean that the recognition process is linear in function of the number of sub-scenarios and in most of the cases in function of the number of characters. To validate this algorithm in term of correctness, robustness and processing time in function of scenario and scene properties (e. g. number of persons in the scene), we have tested the algorithm on several videos of a bank branch and of an office, in on-line and off-line mode and on simulated data. We conclude by comparing our algorithm with the state of the art and showing how the definition of scenario models can influence the results of the real-time scenario recognition.

PDF
v2026.09.13