Two Deep Learning Solutions for Automatic Blurring of Faces in Videos
This work addresses privacy concerns in public surveillance videos by providing automated blurring techniques, but it is incremental as it applies existing deep learning methods to a specific domain.
The paper tackles the problem of protecting individual privacy in videos by presenting two deep learning solutions for automatic face blurring: a direct approach using a YOLO-based detector and an indirect approach using a Unet-like segmentation network, both aimed at blurring faces in surveillance footage.
The widespread use of cameras in everyday life situations generates a vast amount of data that may contain sensitive information about the people and vehicles moving in front of them (location, license plates, physical characteristics, etc). In particular, people's faces are recorded by surveillance cameras in public spaces. In order to ensure the privacy of individuals, face blurring techniques can be applied to the collected videos. In this paper we present two deep-learning based options to tackle the problem. First, a direct approach, consisting of a classical object detector (based on the YOLO architecture) trained to detect faces, which are subsequently blurred. Second, an indirect approach, in which a Unet-like segmentation network is trained to output a version of the input image in which all the faces have been blurred.