BEHAVE - Behavioral analysis of visual events for assisted living scenarios

Abstract : This paper proposes BEHAVE, a person-centered pipeline for probabilistic event recognition. The proposed pipeline firstly detects the set of people in a video frame, then it searches for correspondences between people in the current and previous frames (i.e., people tracking). Finally, event recognition is carried for each person using proba-bilistic logic models (PLMs, ProbLog2 language). PLMs represent interactions among people, home appliances and semantic regions. They also enable one to assess the probability of an event given noisy observations of the real world. BEHAVE was evaluated on the task of online (non-clipped videos) and open-set event recognition (e.g., target events plus none class) on video recordings of seniors carrying out daily tasks. Results have shown that BEHAVE improves event recognition accuracy by handling missed and partially satisfied logic models. Future work will investigate how to extend PLMs to represent temporal relations among events.
Type de document :
Communication dans un congrès
Assisted Computer Vision and Robotics workshop in conjunction with International Conference on Computer Vision, Oct 2017, Venice, Italy. 2017
Liste complète des métadonnées

Littérature citée [34 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01658665
Contributeur : Carlos Crispim <>
Soumis le : mardi 12 décembre 2017 - 11:51:54
Dernière modification le : jeudi 11 janvier 2018 - 17:01:43
Document(s) archivé(s) le : mardi 13 mars 2018 - 12:30:55

Identifiants

  • HAL Id : hal-01658665, version 1

Collections

Citation

Carlos Fernando Crispim-Junior, Jonas Vlasselaer, Anton Dries, François Bremond. BEHAVE - Behavioral analysis of visual events for assisted living scenarios. Assisted Computer Vision and Robotics workshop in conjunction with International Conference on Computer Vision, Oct 2017, Venice, Italy. 2017. 〈hal-01658665〉

Partager

Métriques

Consultations de la notice

127

Téléchargements de fichiers

40