Key Frame Extraction from MPEG Video Stream

摘要

In order to extract valid information from video, process video data efficiently, and reduce the transfer stress of network, more and more attention is being paid to the video processing technology. The amount of data in video processing is significantly reduced by using video segmentation and key-frame extraction. So, these two technologies have gradually become the focus of research. With the features of MPEG compressed video stream, a new method is presented for extracting key frames. Firstly, an improved histogram matching method is used for video segmentation. Secondly, the key frames are extracted utilizing the features of I-frame, P-frame and B-frame for each sub-lens. Fidelity and compression ratio are used to measure the validity of the method. Experimental results show that the extracted key frames can summarize the salient content of the video and the method is of good feasibility, high efficiency, and high robustness.