Title :
Hierarchical contour-based segmentation of dynamic scenes
Author_Institution :
Ellemtel Telecom Lab., Alvsjo, Sweden
fDate :
9/1/1992 12:00:00 AM
Abstract :
A motion segmentation algorithm is introduced. The algorithm is based on the assumption of one coherent moving area (without holes) on a static background. It does coarse-to-fine pyramid-based boundary refinement that attempts to classify the blocks into three classes: inside, border, and outside
Keywords :
pattern recognition; picture processing; coarse-to-fine pyramid-based boundary refinement; dynamic scenes; hierarchical contour based segmentation; image sequence; motion segmentation; pattern recognition; picture processing; Computer vision; Data structures; Image segmentation; Image sequences; Layout; Motion estimation; Motion segmentation; Object recognition; Telecommunication computing; Testing;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
