Implementing an intelligent video monitoring system to detect falls of older adults at home: a multiple case study

Acceptance and Privacy Perceptions Toward Video-based Active and Assisted Living Technologies: Scoping Review

BACKGROUND

The aging society posits new socioeconomic challenges to which a potential solution is active and assisted living (AAL) technologies. Visual-based sensing systems are technologically among the most advantageous forms of AAL technologies in providing health and social care; however, they come at the risk of violating rights to privacy. With the immersion of video-based technologies, privacy-preserving smart solutions are being developed; however, the user acceptance research about these developments is not yet being systematized.

OBJECTIVE

With this scoping review, we aimed to gain an overview of existing studies examining the viewpoints of older adults and/or their caregivers on technology acceptance and privacy perceptions, specifically toward video-based AAL technology.

METHODS

A total of 22 studies were identified with a primary focus on user acceptance and privacy attitudes during a literature search of major databases. Methodological quality assessment and thematic analysis of the selected studies were executed and principal findings are summarized. The PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines were followed at every step of this scoping review.

RESULTS

Acceptance attitudes toward video-based AAL technologies are rather conditional, and are summarized into five main themes seen from the two end-user perspectives: caregiver and care receiver. With privacy being a major barrier to video-based AAL technologies, security and medical safety were identified as the major benefits across the studies.

CONCLUSIONS

This review reveals a very low methodological quality of the empirical studies assessing user acceptance of video-based AAL technologies. We propose that more specific and more end user- and real life-targeting research is needed to assess the acceptance of proposed solutions.

LightAnomalyNet: A Lightweight Framework for Efficient Abnormal Behavior Detection

The continuous development of intelligent video surveillance systems has increased the demand for enhanced vision-based methods of automated detection of anomalies within various behaviors found in video scenes. Several methods have appeared in the literature that detect different anomalies by using the details of motion features associated with different actions. To enable the efficient detection of anomalies, alongside characterizing the specificities involved in features related to each behavior, the model complexity leading to computational expense must be reduced. This paper provides a lightweight framework (LightAnomalyNet) comprising a convolutional neural network (CNN) that is trained using input frames obtained by a computationally cost-effective method. The proposed framework effectively represents and differentiates between normal and abnormal events. In particular, this work defines human falls, some kinds of suspicious behavior, and violent acts as abnormal activities, and discriminates them from other (normal) activities in surveillance videos. Experiments on public datasets show that LightAnomalyNet yields better performance comparative to the existing methods in terms of classification accuracy and input frames generation.