17 April 1995 Encoding motion and approximate segmentation in a slicing floorplan tree structure
Author Affiliations +
A new encoding scheme for motion and approximate scene segmentation in video sequences is described. The proposed segmentation partitions the scene into variable size rectangles that can be encoded efficiently in a data structure known as `a slicing floorplan tree' in VLSI design. The motion in each rectangle is represented by size parameters. We describe experiments comparing the compactness of this encoding to motion encoding in MPEG-1, and its quality to motion estimates obtained by standard computer vision techniques. These experiments establish two facts. (1) The proposed representation is flexible enough to describe motion as accurately as the output produced by the best motion algorithms developed by computer vision researchers. (2) The proposed representation is much more compact than the representation of motion in MPEG-1.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Haim Schweitzer, Haim Schweitzer, Yanjun Zhang, Yanjun Zhang, } "Encoding motion and approximate segmentation in a slicing floorplan tree structure", Proc. SPIE 2419, Digital Video Compression: Algorithms and Technologies 1995, (17 April 1995); doi: 10.1117/12.206364; https://doi.org/10.1117/12.206364


Optimal quad-tree-based motion estimator
Proceedings of SPIE (September 16 1996)
Motion vector synthesis algorithm for MPEG 2 to MPEG 4...
Proceedings of SPIE (December 29 2000)
A fast intra prediction algorithm for H.264
Proceedings of SPIE (October 30 2009)

Back to Top