Name
Abstract | ||
|---|---|---|
We present a novel, implementation friendly and occlusion aware semi-supervised video segmentation algorithm using tree structured graphical models, which delivers pixel labels along with their uncertainty estimates. Our motivation to employ supervision is to tackle a task-specific segmentation problem where the semantic objects are pre-defined by the user. The video model we propose for this problem is based on a tree structured approximation of a patch based undirected mixture model, which includes a novel time-series and a soft label Random Forest classifier participating in a feedback mechanism. We demonstrate the efficacy of our model in cutting out foreground objects and multi-class segmentation problems in lengthy and complex road scene sequences. Our results have wide applicability, including harvesting labelled video data for training discriminative models, shape/pose/articulation learning and large scale statistical analysis to develop priors for video segmentation. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/CVPR.2011.5995600 | CVPR |
Keywords | Field | DocType |
approximation theory,image classification,image segmentation,learning (artificial intelligence),statistical analysis,time series,trees (mathematics),video signal processing,articulation learning,feedback mechanism,multiclass segmentation problems,patch based undirected mixture model,pose learning,semi-supervised video segmentation algorithm,shape learning,soft label random forest classifier,statistical analysis,task-specific segmentation problem,time-series,tree structured approximation,tree structured graphical models,video model | Scale-space segmentation,Computer science,Image segmentation,Artificial intelligence,Contextual image classification,Random forest,Discriminative model,Computer vision,Pattern recognition,Segmentation,Graphical model,Machine learning,Mixture model | Conference |
Volume | Issue | ISSN |
2011 | 1 | 1063-6919 |
Citations | PageRank | References |
24 | 1.03 | 15 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| I. Budvytis | 1 | 24 | 1.03 |
| V. Badrinarayanan | 2 | 24 | 1.03 |
| Roberto Cipolla | 3 | 9413 | 827.88 |