Title | ||
---|---|---|
Tube-embodied gradient vector flow fields for unsupervised video object plane (VOP) segmentation |
Abstract | ||
---|---|---|
In this paper constrained Gradient Vector Flow (GVF) field generation is performed, for fast and accurate unsupervised stereoscopic semantic segmentation. The scheme utilizes the in- formation provided by a depth segments map, produced by stereo analysis methods and incorporation of a segmentation algorithm. Then a Canny edge detector is applied to the depth region and produces an edge map. The edge map is used for tube estimation inside which the GVF field evolves. After generation of the GVF field an active contour is unsupervisedly initialized onto the outer bound of the tube. Finally a greedy approach is adopted and the active contour, guided by the GVF field, extracts the VOP. Ex- perimental results on real life stereoscopic video sequences indi- cate the efficiency of the proposed scheme. |
Year | DOI | Venue |
---|---|---|
2001 | 10.1109/ICIP.2001.958574 | ICIP (2) |
DocType | Citations | PageRank |
Conference | 1 | 0.37 |
References | Authors | |
8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Anastasios D. Doulamis | 1 | 883 | 93.64 |
Nikolaos Doulamis | 2 | 691 | 80.72 |
Stefanos Kollias | 3 | 2268 | 229.16 |
Klimis S. Ntalianis | 4 | 66 | 15.74 |