Wearable privacy protection with visual bubble

Wearable cameras are increasingly used in many different applications from law enforcement to medicine. In this paper
¹
, we consider an application of using a wearable camera to record one-on-one therapy with a child in a classroom or clinic. To protect the privacy of other individuals in the same environment, we introduce a new visual privacy paradigm called privacy bubble. Privacy bubble is a virtual zone centered around the camera for observation whereas the rest of the environment and people are obfuscated. In contrast to most existing visual privacy systems that rely on visual classifier, privacy bubble is based on depth estimation to determine the extent of privacy protection. To demonstrate this concept, we construct a wearable stereo-camera for depth estimation on the Raspberry Pi platform. We also propose a novel framework to quantify the uncertainty in depth measurements so as to minimize a statistical privacy risk in constructing the depth-based privacy bubble. The effectiveness of the proposed scheme is demonstrated with preliminary experimental results.