2-D mesh-based video object segmentation and tracking with occlusion resolution
✍ Scribed by Işıl Celasun; A.Murat Tekalp; Mete H Gökçetekin; Derin M Harmancı
- Publisher
- Elsevier Science
- Year
- 2001
- Tongue
- English
- Weight
- 821 KB
- Volume
- 16
- Category
- Article
- ISSN
- 0923-5965
No coin nor oath required. For personal study only.
✦ Synopsis
This paper integrates fully automatic video object segmentation and tracking including detection and assignment of uncovered regions in a 2-D mesh-based framework. Particular contributions of this work are (i) a novel video object segmentation method that is posed as a constrained maximum contrast path search problem along the edges of a 2-D triangular mesh, and (ii) a 2-D mesh-based uncovered region detection method along the object boundary as well as within the object. At the "rst frame, an optimal number of feature points are selected as nodes of a 2-D content-based mesh. These points are classi"ed as moving (foreground) and stationary nodes based on multi-frame node motion analysis, yielding a coarse estimate of the foreground object boundary. Color di!erences across triangles near the coarse boundary are employed for a maximum contrast path search along the edges of the 2-D mesh to re"ne the boundary of the video object. Next, we propagate the re"ned boundary to the subsequent frame by using motion vectors of the node points to form the coarse boundary at the next frame. We detect occluded regions by using motion-compensated frame di!erences and range "ltered edge maps. The boundaries of detected uncovered regions are then re"ned by using the search procedure. These regions are either appended to the foreground object or tracked as new objects. The segmentation procedure is re-initialized when unreliable motion vectors exceed a certain number. The proposed scheme is demonstrated on several video sequences.