Unnecessary image extraction from video sequences of cc tv surveillance in the Smart Cities for Traffic Monitoring

Security and surveillance are important issues in today‟s world. The recent acts of security have highlighted the urgent need for efficient surveillance in the Smart Cities. Contemporary surveillance systems use digital video recording (DVR) cameras which play host to multiple channels. Video summarization targets to facilitate large video file by producing short, concise summaries that are diverse and representative of original videos. In this paper, I formulate video summarization as a sequential decision making process and develop a deep summarization network (DSN) in the 5th level to summarize videos of a Smart City. Since labels are not required, this method can be fully unsupervised. Video is time-consuming to watch so I adopt a technique which efficiently represents most significant information in a video stream using a combination of still images, video segments, graphical representations and textual descriptors.