Translator Disclaimer
7 June 2002 Segmentation of MPEG-2 motion imagery within the compressed domain
Author Affiliations +
Temporal segmentation of video in the compressed domain is becoming increasingly popular due to its computational advantages over video decompression followed by pixel-domain segmentation. This paper discusses the advantages of compressed-domain processing, and proposes a computationally-efficient method of detecting scene changes without reconstructing the video. The target application provides requirements that allow the algorithm to avoid complicated processing that searches for unnatural scenes changes such as dissolves, fades, and wipes that are common studio effects. The paper provides experimental results to demonstrate operation of the algorithm on real data.
© (2002) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Thomas S. Heath, Mark A. Robertson, John G. Keller, and Todd B. Howlett "Segmentation of MPEG-2 motion imagery within the compressed domain", Proc. SPIE 4735, Hybrid Image and Signal Processing VIII, (7 June 2002);


Real-time video analysis for retail stores
Proceedings of SPIE (March 03 2015)
WCAM: smart encoding for wireless surveillance
Proceedings of SPIE (March 13 2005)
Geospatial processing of registered H.264 data
Proceedings of SPIE (May 21 2012)
Fade in out scene change detection in the MPEG 1...
Proceedings of SPIE (December 22 1999)

Back to Top