SEMIAUTOMATIC SEGMENTATION AND TRACKING OF SEMANTIC VIDEO OBJECTS

This paper introduces a novel semantic video object extraction system using mathematical morphology and a perspective motion model. Inspired by the results from the study of the human visual system, we intend t o solve the semantic video object extraction problem in two separate s teps: supervised I-frame segmentation, and unsupervised P-frame tracki ng. First, the precise semantic video object boundary can be found usi ng a combination of human assistance and a morphological segmentation tool. Second, the semantic video objects in the remaining frames are o btained using global perspective motion estimation and compensation of the previous semantic video object plus boundary refinement as used f or I frames.