A data structure for dynamic trees
Journal of Computer and System Sciences
Occlusions and binocular stereo
International Journal of Computer Vision
Intelligent scissors for image composition
SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
An Integrated Bayesian Approach to Layer Extraction from Image Sequences
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast Approximate Energy Minimization via Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multi-camera Scene Reconstruction via Graph Cuts
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
A Layered Approach to Stereo Reconstruction
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Gaze Manipulation for One-to-one Teleconferencing
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Dynamizing static algorithms, with applications to dynamic trees and history independence
SODA '04 Proceedings of the fifteenth annual ACM-SIAM symposium on Discrete algorithms
"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
SODA '05 Proceedings of the sixteenth annual ACM-SIAM symposium on Discrete algorithms
Maintaining information in fully dynamic trees with top trees
ACM Transactions on Algorithms (TALG)
Probabilistic Fusion of Stereo with Color and Contrast for Bilayer Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Maximum flows and parametric shortest paths in planar graphs
SODA '10 Proceedings of the twenty-first annual ACM-SIAM symposium on Discrete Algorithms
Hi-index | 0.00 |
Separating a foreground layer from stereo video in real-time is used in many applications such as live background substitution. Conventional separating models using stereo, contrast or color alone are usually not accurate enough to be satisfactory. Furthermore, the powerful tool of graph cut which is well suited for segmentation is known to be not efficient enough especially for high resolution images. In this paper, we conquer these difficulties by fusing stereo with color and contrast to model the segmentation problem as an minimum cut problem of a planar graph and solving it by a specialized algorithm, parametric shortest paths [8] with a dynamic tree structure, in O(nlogn) time. Experimental results demonstrate the high accuracy and efficiency of the algorithm.