Tampering Detection and Classification of Intelligent Video Surveillance System
Pla Information · Shuju caiji yu chuli · 2013
A novel method is proposed to detect tampering of intelli gent video surveillance and recognize the types of tampering.In order to det ect tampering and recognize its type,the method gives every type of t ampe ring a detection feature,such as covered camera,defocused,intensity error, color error,noise of video and so on.At the same time,adaptive threshold is a pplied to decrease complexity.The experimental results show that the proposed m ethod satisfies the demand for real-time of video surveillance system and also has excellent performance of detection and recognition.Finally,the ac c uracy rate can reach 92.2%.