Abstract | ||
---|---|---|
Supervoxels have been widely used as a preprocessing step to exploit the object boundaries to improve the performance of video processing tasks. However, most of the traditional supervoxel algorithms do not perform well in the regions with complex textures or weak boundaries. These methods may generate the supervoxels with overlapping boundaries. In this paper, we present the novel video supervoxel generation algorithm using partially absorbing random walks to get more accurate supervoxels in these regions. Our spatial-temporal framework is introduced by making full use of the appearance and motion cues, which effectively exploits the temporal consistency in video sequence. Moreover, we build a novel Laplacian optimization structure using two adjacent frames to make our approach more efficient. Experimental results demonstrated that our method achieved better performance than the state-of-the-art supervoxel algorithms. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/TCSVT.2015.2406232 | IEEE Trans. Circuits Syst. Video Techn. |
Keywords | Field | DocType |
Laplacian graph,Video segmentation,supervoxel | Computer vision,Motion cues,Video processing,Algorithm design,Pattern recognition,Computer science,Random walk,Preprocessor,Artificial intelligence,Optical propagation,Temporal consistency,Laplace operator | Journal |
Volume | Issue | ISSN |
PP | 99 | 1051-8215 |
Citations | PageRank | References |
19 | 0.57 | 31 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Y. Zheng | 1 | 20 | 1.26 |
Jianbing Shen | 2 | 1362 | 60.11 |
Dong, X. | 3 | 22 | 1.60 |
Hanqiu Sun | 4 | 696 | 85.72 |