Refine stereo correspondence using bayesian network and dynamic programming on a color based minimal span tree

Authors:
Naveed I Rao;Huijun Di;GuangYou Xu
Affiliations:
Pervasive Computing Lab, Institute of Human Computer Interaction Department, of Computer Engineering, Tsinghua University, Beijing, China;Pervasive Computing Lab, Institute of Human Computer Interaction Department, of Computer Engineering, Tsinghua University, Beijing, China;Pervasive Computing Lab, Institute of Human Computer Interaction Department, of Computer Engineering, Tsinghua University, Beijing, China
Venue:
ACIVS'06 Proceedings of the 8th international conference on Advanced Concepts For Intelligent Vision Systems
Year:
2006

Citing 13
Cited 0

Introduction to algorithms

Introduction to algorithms
Occlusions and binocular stereo

International Journal of Computer Vision
A maximum likelihood stereo algorithm

Computer Vision and Image Understanding
A Bayesian approach to binocular stereopsis

International Journal of Computer Vision
Large Occlusion Stereo

International Journal of Computer Vision
Fast Approximate Energy Minimization via Graph Cuts

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

International Journal of Computer Vision
Occlusions, Discontinuities, and Epipolar Lines in Stereo

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Multi-camera Scene Reconstruction via Graph Cuts

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Stereo Matching Using Belief Propagation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Advances in Computational Stereo

IEEE Transactions on Pattern Analysis and Machine Intelligence
Stereo Correspondence by Dynamic Programming on a Tree

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
A Comparison of Algorithms for Inference and Learning in Probabilistic Graphical Models

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Stereo correspondence is one of the basic and most important problems in computer vision. For better correspondence, we need to determine the occlusion. Recently dynamic programming on a minimal span tree (mst) structure is used to search for correspondence. We have extended this idea. First, mst is generated directly based on the color information in the image instead of converting the color image into a gray scale. Second, have treated this mst as a Bayesian Network. Novelty is attained by considering local variances of the disparity and intensity differences in the conditional Gaussians as unobserved random parameters. These parameters are iteratively inferenced by alternate estimation along the tree given a current disparity map. It is followed by dynamic programming estimation of the map given the current variance estimates thus reducing the overall occlusion. We evaluate our algorithm on the benchmark Middlebury database. The results are promising for modeling occlusion in early vision problems.