Fast extraction of spatially reduced image sequences from MPEG-2 compressed video

MPEG-2 video standards are targeted for high-quality video broadcast and distribution and are optimized for efficient storage and transmission. However, it is difficult to process MPEG-2 for video browsing and database applications without first decompressing the video. Yeo and Liu (1995) have proposed fast algorithms for the direct extraction of spatially reduced images from MPEG-1 video. Reduced images have been demonstrated to be effective for shot detection, shot browsing and editing, and temporal processing of video for video presentation and content annotation. In this paper, we develop new tools to handle the extra complexity in MPEG-2 video for extracting spatially reduced images. In particular, we propose new classes of discrete cosine transform (DCT) domain and DCT inverse motion compensation operations for handling the interlaced modes in the different frame types of MPEG-2, and we design new and efficient algorithms for generating spatially reduced images of an MPEG-2 video. The algorithms proposed in this paper are fundamental for efficient and effective processing of MPEG-2 video.