Crowd context-dependent privacy protection filters

While various privacy protection filters have been proposed in the literature, little importance has been given to the context relevance of these filters. In this paper, we specifically focus on the dependency between privacy preservation and crowd density. We show that information about the crowd density in a scene can be used in order to adjust the level of privacy protection according to the local needs. For the estimation of density maps, we use an approach based on FAST feature extraction and local optical flow computation which allow excluding feature points on the background. This process is favorable for the later density function estimation since the influence of features irrelevant to the crowd density is removed. Afterwards, we adapt the protection level of personal privacy in videos according to the crowd density. The effectiveness of the proposed framework is evaluated with videos from different crowd datasets.