The CIRDO Corpus: Comprehensive Audio/Video Database of Domestic Falls of Elderly People

Michel Vacher (1, 2) , Saida Bouakaz (3) , Marc-Eric Bobillier-Chaumon (4) , F Aman (1, 2) , Rizwan Ahmed Khan (3) , S Bekkadja (4) , François Portet (1, 2) , Erwan Guillou (3) , S Rossato (1, 2) , Benjamin Lecouteux (1, 2)

1 LIG - Laboratoire d'Informatique de Grenoble
2 GETALP - Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole
3 SAARA - Simulation, Analyse et Animation pour la Réalité Augmentée
4 GRePS - Groupe de Recherche en Psychologie Sociale

Ambient Assisted Living aims at enhancing the quality of life of older and disabled people at home thanks to Smart Homes. In particular, regarding elderly living alone at home, the detection of distress situation after a fall is very important to reassure this kind of population. However, many studies do not include tests in real settings, because data collection in this domain is very expensive and challenging and because of the few available data sets. The CIRDOcorpus is a dataset recorded in realistic conditions in DOMUS, a fully equipped Smart Home with microphones and home automation sensors, in which participants performed scenarios including real falls on a carpet and calls for help. These scenarios were elaborated thanks to a field study involving elderly persons. Experiments related in a first part to distress detection in real-time using audio and speech analysis and in a second part to fall detection using video analysis are presented. Results show the difficulty of the task. The database can be used as standardized database by researchers to evaluate and compare their systems for elderly person's assistance. Keywords: audio and video data set, multimodal corpus, natural language and multimodal interaction, Ambient Assisted Living (AAL), distress situation.

Mots clés: distress situation; Ambient Assisted Living (AAL); natural language and multimodal interaction; multimodal corpus; audio and video data set

Domaines: Base de données [cs.DB]

Michel Vacher, Saida Bouakaz, Marc-Eric Bobillier-Chaumon, F Aman, Rizwan Ahmed Khan, et al.. The CIRDO Corpus: Comprehensive Audio/Video Database of Domestic Falls of Elderly People. 10th International Conference on Language Resources and Evaluation (LREC 2016), ELRA, May 2016, Portoroz, Slovenia. pp.1389-1396. ⟨hal-01323603⟩