16 September 1996 Segmentation-based video codec with a block-based fallback mode
Author Affiliations +
This paper describes a possible strategy to migrate from block-based coding towards object-based coding. We use the results of an intelligent motion estimation algorithm to define low resolution (block based) segmentation. The information from previous segmentation results together with the motion vector field, the image data and spatial relations are used to define the cost to belong to a given object. A separate selection procedure is used to generate the high resolution (pixel based) objects. Afterwards some shape simplification is performed to generate the final objects.
© (1996) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Stefaan Desmet, Albert A. Deknuydt, Luc Van Eycken, Andre J. Oosterlinck, "Segmentation-based video codec with a block-based fallback mode", Proc. SPIE 2952, Digital Compression Technologies and Systems for Video Communications, (16 September 1996); doi: 10.1117/12.251286; https://doi.org/10.1117/12.251286


Real-time architecture for large displacements estimation
Proceedings of SPIE (September 16 1994)
MPEG-4 video compression optimization research
Proceedings of SPIE (October 01 2011)
Watershed data aggregation for mean-shift video segmentation
Proceedings of SPIE (September 24 2007)
Region-based H.263+ coding for real-time video communication
Proceedings of SPIE (January 04 2002)
Automatic segmentation for very low bit-rate video coding
Proceedings of SPIE (April 19 2000)
Hybrid VQ of video sequences using quadtree motion segmentation
Proceedings of SPIE (September 16 1994)

Back to Top