Falling poses significant risks, especially for the geriatric population. In this study, we introduce an innovative approach to privacy-preserving fall detection using computer vision. Our technique leverages a deep neural network (DNN) to accurately identify falling events in input images, while simultaneously prioritizing privacy through the implementation of an optical element. The experimental results establish that our proposed method outperforms alternative hardware and software-based privacy-preserving approaches in terms of encryption level and accuracy. These results are derived from an extensive dataset encompassing diverse falling scenarios.
History
School affiliated with
School of Computer Science (Research Outputs)
College of Health and Science (Research Outputs)
School of Engineering and Physical Sciences (Research Outputs)
Publication Title
Enhancing Privacy with Optical Element Design for Fall Detection