An object-based video authentication mechanism for smart-living surveillance

Now-a-days, surveillance cameras have been widely deployed in connection with various applications. In these type of applications, object based coding offers very low bit rate video compression for transmission/storage of the data and protecting the privacy of the people, especially in the smart living system for elderly and children care. In addition to the compression advantages, object-based coding techniques can support content-based functionalities such as to selectively code, decode, and manipulate specific objects in a video stream. However, protecting the authenticity of the video becomes more challenging in this case as a malicious entity can modify/replace/remove the individual foreground objects and background in the video. In this paper, we propose a Chinese remainder theorem based authentication mechanism for protecting the authenticity of videos transmitted or stored using object based coding techniques. Our mechanism ensures the authenticity between the foreground objects and their associated background in a video frame.