In this project, we seek to early diagnose Autistic Spectrum Disorders (ASD), through automated video analysis. In this domain, few reliable solutions exist except off-line human expert analysis. For this purpose, we propose to develop a video interpretation platform allowing both the detection, by non-invasive solutions, of the position of the gaze and the extraction of the movements of a person moving in the scene, and therefore in a natural situation. It would also allow the recognition and the semantic interpretation of certain behaviors predefined by our partner experts, or even of emerging behaviors. This represents an innovation and a major technological breakthrough because it would make it possible to detect the behavioral characteristics of children with autism, to quantify their evolution over time and thus to facilitate the adjustment of the interventions practiced by professionals.
Madame Séverine Dubuisson (Laboratoire d'Informatique et Systèmes)
The author of this summary is the project coordinator, who is responsible for the content of this summary. The ANR declines any responsibility as for its contents.
INRIA Sophia Antipolis Mediterranée Institut National de Recherche en Informatique et en Automatique
WITA SARL WITA SARL
LIS - AMU Laboratoire d'Informatique et Systèmes
UNS - CoBTek UNIVERSITE NICE SOPHIA ANTIPOLIS - COGNITION BEHAVIOUR TECHNOLOGY
Help of the ANR 784,258 euros
Beginning and duration of the scientific project: December 2019 - 48 Months