Parallel parsing of MPEG video in a multi-threaded multiprocessor environment

Video parsing refers to the detection of scene changes and special effects in the video stream and is used to extract key frames from a video stream. In this paper, we propose parallel algorithms for the detection of scene changes and special effects in MPEG video in a multi-threaded multiprocessor environment. The parallel video parsing algorithms are capable of detecting abrupt scene changes (cuts), gradual scene changes (dissolves) and dominant camera motion in the form of pans and zooms in an MPEG1-coded video stream while entailing minimal decompression of the MPEG1 video stream. Experimental results on real video clips in a multi-threaded multiprocessor environment are presented. These algorithms are useful when real-time parsing of streaming video or high-throughput parsing of archival video are desired.