Abstract | ||
---|---|---|
We present a new algorithm for unsupervised video segmentation based on boundary-aware optical flow. Existing video segmentation methods usually tweak their segmentation model to tolerate the inaccuracy in the estimation of optical flow around object boundaries. En contrast, we directly manipulate the optical flow for better quality. We smooth the optical flow via transductive inference to make the flow consistent within the object and lit to the object boundaries. We then use the boundary-aware optical flow to estimate the initial foreground object region from each frame for learning the appearance model. The learned appearance model is consequently used to refine the segmentation result. Experiments on the DAVIS dataset show that our method performs favorably against the existing ones. |
Year | Venue | Keywords |
---|---|---|
2017 | 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Video segmentation, optical flow, transductive inference |
Field | DocType | ISSN |
Transduction (machine learning),Computer vision,Pattern recognition,Computer science,Segmentation,Flow (psychology),Integrated optics,Active appearance model,Artificial intelligence,Optical propagation,Optical imaging,Optical flow | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ding-Jie Chen | 1 | 31 | 6.70 |
Hwann-Tzong Chen | 2 | 826 | 52.13 |
Long-Wen Chang | 3 | 92 | 12.27 |