eduzhai > Applied Sciences > Engineering >

Fall Detector Adapted to Nursing Home Needs through an Optical-Flow based CNN

  • Save

... pages left unread,continue reading

Document pages: 4 pages

Abstract: Fall detection in specialized homes for the elderly is challenging.Vision-based fall detection solutions have a significant advantage oversensor-based ones as they do not instrument the resident who can suffer frommental diseases. This work is part of a project intended to deploy falldetection solutions in nursing homes. The proposed solution, based on DeepLearning, is built on a Convolutional Neural Network (CNN) trained to maximizea sensitivity-based metric. This work presents the requirements from themedical side and how it impacts the tuning of a CNN. Results highlight theimportance of the temporal aspect of a fall. Therefore, a custom metric adaptedto this use case and an implementation of a decision-making process areproposed in order to best meet the medical teams requirements. Clinicalrelevance This work presents a fall detection solution enabled to detect 86.2 of falls while producing only 11.6 of false alarms in average on theconsidered databases.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×