A decentralized privacy-sensitive video surveillance framework

With the increasing spread of accurate and robust video surveillance, applications such as crowd monitoring, people counting and abnormal behavior recognition become ubiquitous.This leads to needs of interactive systems taking into account a high degree of interoperability as well as privacy protection concerns. In this paper we propose a framework based on the ONVIF specification to support the work of video operators while implementing a privacy-by-design concept. We use an OpenGL-based 3D model of the CCTV site where we display the results of the video analytics in an avatar-based manner and give an example application on mugging detection. To place the automatically detected scene information, such as people detections and events, an automatic camera calibration is used which effectively reduces the deployment effort.