Detecting and classifying video shot boundaries in MPEG compressed sequences

We present a new method for shot boundaries detection and classification that operates directly on the MPEG compressed video. It is based only on the information about the macroblock coding mode in P and B frames. In order to maintain good accuracy while limiting complexity, the system follows a two-pass scheme and has a hybrid rule-based/neural structure. A rough scan over the P frames locates the potential boundaries of the transitions and the solution is then refined by a precise scan over the B frames of the respective neighborhoods. The "simpler" boundaries are recognized by the rule-based module, while the decisions for the "complex" cases are refined by the neural part. The experimental results demonstrate high speed and accuracy in detecting cuts, fades and dissolves.