Privacy preserving video surveillance using pedestrian tracking mechanism

Abstract

Video surveillance has become a ubiquitous feature of the modern day life. However, the widespread use of video surveillance has raised concerns about the privacy of people. In this paper, we propose a novel video surveillance with a privacy preserving mechanism. We achieve this by combining the techniques of pedestrian tracking based on a Markov chain with two hidden states, elliptical head contour detection and encryption. The detected pedestrian face/head is obscured by encrypting with a unique key derived from a master key for the privacy preservation purpose. The surveillance video can be viewed with complete privacy or by revoking the privacy of any subset of pedestrians while ensuring complete privacy of the remaining pedestrians. The performance evaluation on many challenging surveillance scenarios shows that the proposed mechanism can effectively and robustly track multiple pedestrians and obscure their faces/head in real time.