Privacy-Preserving Action Recognition for Smart Hospitals using Low-Resolution Depth Images
This addresses privacy issues for patients in smart hospitals, but it is incremental as it builds on existing super-resolution and activity recognition methods.
The paper tackled the problem of patient privacy concerns in computer-vision hospital systems by downsampling video frames to extremely low resolutions to degrade private information, and showed that these privacy-preserving techniques retain enough information for realistic healthcare tasks like hand-hygiene compliance and ICU activity-logging.
Computer-vision hospital systems can greatly assist healthcare workers and improve medical facility treatment, but often face patient resistance due to the perceived intrusiveness and violation of privacy associated with visual surveillance. We downsample video frames to extremely low resolutions to degrade private information from surveillance videos. We measure the amount of activity-recognition information retained in low resolution depth images, and also apply a privately-trained DCSCN super-resolution model to enhance the utility of our images. We implement our techniques with two actual healthcare-surveillance scenarios, hand-hygiene compliance and ICU activity-logging, and show that our privacy-preserving techniques preserve enough information for realistic healthcare tasks.