Simultaneous object segmentation, múltiple object traking and alpha map generation
Material type:
Item type | Home library | Call number | Status | Date due | Barcode | |
---|---|---|---|---|---|---|
![]() |
Biblioteca de la Facultad de Informática | A0204 (Browse shelf(Opens below)) | Recurso en Línea |
Formato de archivo: PDF. -- Disponible también en línea (Cons. 23/04/2009)
This paper presents an object-based video modeling. Motion segmentation is performed at the initial frame to identify different coherently moving regions, called motion-objects. These regions are grouped to form objects. Each motion-object is fitted a content-based mesh, and trucked subsequently to the next frame via mesch motion estimation and compensation. The uncovered background (UB) region(s), which emerges when objects move, will be segmented so as to identify the new objects or occluded parts of already existing objects. the mesh model is modified to reflect the changes in object boundarics.
Proceedings of the 1997 International Conference on Image Processing (ICIP ྜྷ) 3-Volume Set-Volume 1 - Volume 1, pp. 69-72.