Title :
Semantic video object segmentation and tracking using mathematical morphology and perspective motion model
Author :
Gu, Chuang ; Lee, Ming-Chieh
Author_Institution :
Microsoft Corp., Redmond, WA, USA
Abstract :
This paper introduces a novel semantic video object extraction system using mathematical morphology and a perspective motion model. Inspired by the results from a study of the human visual system, we solve the semantic video object extraction problem in two steps: semi-automatic I-frame segmentation and automatic P-frame tracking. First, the precise semantic video object boundary can be found with the combined power of human assistance and a morphological segmentation tool. Second, the semantic video object in the remaining frames can be obtained using a global perspective motion estimation and compensation of the previous semantic video object plus boundary refinement as used for frames
Keywords :
feature extraction; image segmentation; image sequences; mathematical morphology; motion compensation; motion estimation; set theory; tracking; video signal processing; visual perception; automatic P-frame tracking; boundary refinement; human visual system; mathematical morphology; morphological segmentation tool; motion compensation; motion estimation; perspective motion model; semantic video object extraction system; semantic video object segmentation; semi-automatic I-frame segmentation; set theory; video object boundary; video object tracking; Humans; Image segmentation; Mathematical model; Morphology; Motion estimation; Multimedia databases; Object segmentation; Power system modeling; Tracking; Visual system;
Conference_Titel :
Image Processing, 1997. Proceedings., International Conference on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
0-8186-8183-7
DOI :
10.1109/ICIP.1997.638821
