On fast microscopic browsing of MPEG-compressed video

MPEG has been established as a compression standard for efficient storage a nd transmission of digital video. However, users are limited to VCR-like (a nd tedious) functionalities when viewing MPEG video. The usefulness of MPEG video is presently limited by the lack of tools available for fast browsin g, manipulation and processing of MPEG video. In this paper, we first address the problem of rapid access to individual s hots and frames in MPEG video. We build upon the compressed-video-processin g framework proposed in [1, 8], and propose new and fast algorithms based o n an adaptive mixture of approximation techniques for extracting spatially reduced image sequence of uniform quality from MPEG video across different frame types and also under different motion activities in the scenes. The a lgorithms execute faster than real time on a Pentium personal computer. We demonstrate how the reduced images facilitate fast and convenient shot- and frame-level video browsing and access, shot-level editing and annotation, without the need for frequent decompression of MPEG video. We further propo se methods for reducing the auxiliary data size associated with the reduced images through exploitation of spatial and temporal redundancy. We also ad dress how the reduced images lead to computationally efficient algorithms f or video analysis based on intra- and inter-shot processing for video datab ase and browsing applications. The algorithms, tools for browsing and techn iques for video processing presented in this paper have been used by many i n IBM Research on more than 30 h of MPEG-1 video for video browsing and ana lysis.