Reliable Classifications with Machine Learning
ECML '02 Proceedings of the 13th European Conference on Machine Learning
Ridge Regression Confidence Machine
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
"GrabCut": interactive foreground extraction using iterated graph cuts
ACM SIGGRAPH 2004 Papers
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
SVM-Based Classifier Design with Controlled Confidence
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
Bi-Layer Segmentation of Binocular Stereo Video
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Bilayer Segmentation of Live Video
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
An Iterative Bayesian Approach for Digital Matting
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 02
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
On-line visualization of underground structures using context features
Proceedings of the 17th ACM Symposium on Virtual Reality Software and Technology
Hi-index | 0.00 |
High quality online video segmentation is a very challenging task. Among various cues to infer the segmentation, the foreground and background color distributions are the most important. However, previous color modeling methods are error-prone when some parts of the foreground and background have similar colors, to address this problem, we propose a novel approach of Confidence-based Color Modeling (CCM). Our approach can adaptively tune the effects of global and per-pixel color models according to the confidence of their predictions, methods of measuring the confidence of both type of models are developed. We also propose an adaptive threshold method for background subtraction that is robust against ambiguous colors. Experiments demonstrate the effectiveness and efficiency of our method in reducing the segmentation errors incurred by ambiguous colors.