Accurate dense stereo matching of slanted surfaces using 2D integral images

Authors:
Gwnag Yul Song;Seong Ik Cho;Dong Yong Kwak;Joon Woong Lee
Affiliations:
Dept. of Industrial Engineering, College of Engineering, Chonnam National University, Gwangju, Korea;Electronics and Telecommunications Research Institute, Daejeon, Korea;Electronics and Telecommunications Research Institute, Daejeon, Korea;Dept. of Industrial Engineering, College of Engineering, Chonnam National University, Gwangju, Korea
Venue:
ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
Year:
2013

Citing 6
Cited 0

A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

International Journal of Computer Vision
Calculating Dense Disparity Maps from Color Stereo Images, an Efficient Implementation

International Journal of Computer Vision
Adaptive Support-Weight Approach for Correspondence Search

IEEE Transactions on Pattern Analysis and Machine Intelligence
Stereo Matching with Color-Weighted Correlation, Hierachical Belief Propagation and Occlusion Handling

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Cross-based local stereo matching using orthogonal integral images

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an advanced algorithm providing accurate stereo correspondences of two frames through concise disparity gradient estimation at the per-pixel level and 2D integral images. The key contributions of this novel algorithm are twofold: First, combining an upright cross-based support region with disparity gradient estimation realizes the implicit construction of a 3D support region for each anchor pixel. This approach yields the disparity accuracy for slanted surfaces as well as fronto-parallel surfaces. Second, the 2D integral image technique leads to a speedup of matching cost aggregation in the implicit 3D support regions. The experimental results show that the proposed algorithm can successfully convey the correspondences of actual sequence of outdoor stereo images and Middlebury stereo images with high accuracy in near real time.