Video shot boundary detection using compressed domain features of H.264

In this paper authors have proposed a multifactor based approach to automatically detect video shot boundaries. The compressed domain features of H.264 are used to assign the factor values. The features used in our approach are (i) Number of I Macroblocks (MBs) in a P frame, (ii) DC component of integer transformed luma coefficients and (iii) Number of MBs coded as P_Skip in P frame. A confidence score for all frames are assigned based on those above mentioned features. Experimental results show that the proposed approach can detect the shot boundaries successfully in real time. The system on different type of videos gives a recall rate of 0.98 and a precision rate of 0.94.