DemCare action dataset for evaluating dementia patients in a home-based environment
Konstantinos Avgerinakis, Ioannis Yiannis Kompatsiaris · InImpact · 2016
Computer vision technologies and more specifically activity recognition can be considered one of the most helpful tools that computer science can provide to the society’s disposal. Activity recognition deals with the visual analysis of video sequences and provides semantic information about the activities that may occur within them. In state-of-the-art literature, activity recognition deals with problems that vary from (a) video retrieval topics, which concentrate to the extraction of visual information concerning activities that exist within movies or youtube video samples, to (b) activity of daily living (ADL) topics which focus to the recognition of activities that may occur within a home or kitchen based environment. Although the great range of activities that current action datasets include, we have not yet encountered the implementation of any realistic scenario which deal with the real life problems, such as dementia and related diseases. Considering the above reasons and trying to encourage future studies on dementia disease, we propose DemCare action datasets which record a spate of human patients to perform a large set of daily activities in a home based environment.