Hierarchical Hidden Markov Model in Detecting Activities of Daily Living in Wearable Videos for Studies of Dementia - Université Toulouse 1 Capitole Accéder directement au contenu
Article Dans Une Revue Multimedia Tools and Applications Année : 2014

Hierarchical Hidden Markov Model in Detecting Activities of Daily Living in Wearable Videos for Studies of Dementia

Résumé

This paper presents a method for indexing activities of daily living in videos obtained from wearable cameras. In the context of dementia diagnosis by doctors, the videos are recorded at patients' houses and later visualized by the medical practitioners. The videos may last up to two hours, therefore a tool for an efficient navigation in terms of activities of interest is crucial for the doctors. The specific recording mode provides video data which are really difficult, being a single sequence shot where strong motion and sharp lighting changes often appear. Our work introduces an automatic motion based segmentation of the video and a video structuring approach in terms of activities by a hierarchical two-level Hidden Markov Model. We define our description space over motion and visual characteristics of video and audio channels. Experiments on real data obtained from the recording at home of several patients show the difficulty of the task and the promising results of our approach.
Fichier principal
Vignette du fichier
MTAP-Karaman2012OA.pdf (1.08 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00639014 , version 1 (07-11-2011)
hal-00639014 , version 2 (08-04-2014)

Identifiants

Citer

Svebor Karaman, Jenny Benois-Pineau, Vladislavs Dovgalecs, Rémi Mégret, Julien Pinquier, et al.. Hierarchical Hidden Markov Model in Detecting Activities of Daily Living in Wearable Videos for Studies of Dementia. Multimedia Tools and Applications, 2014, 69 (3), pp.743-771. ⟨10.1007/s11042-012-1117-x⟩. ⟨hal-00639014v2⟩
395 Consultations
451 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More