TOCSAC: TOpology Constraint SAmple Consensus for Fast and Reliable Feature Correspondence

Authors:
Zhoucan He;Qing Wang;Heng Yang
Affiliations:
School of Computer Science, Engineering Northwestern Polytechnical University, Xi'an, P.R. China 710072;School of Computer Science, Engineering Northwestern Polytechnical University, Xi'an, P.R. China 710072;School of Computer Science, Engineering Northwestern Polytechnical University, Xi'an, P.R. China 710072
Venue:
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part II
Year:
2009

Citing 13
Cited 0

Robust regression and outlier detection

Robust regression and outlier detection
MLESAC: a new robust estimator with application to estimating image geometry

Computer Vision and Image Understanding - Special issue on robusst statistical techniques in image understanding
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
Outlier Modeling in Image Matching

IEEE Transactions on Pattern Analysis and Machine Intelligence
Guided Sampling and Consensus for Motion Estimation

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Multiple View Geometry in Computer Vision

Multiple View Geometry in Computer Vision
Recognising Panoramas

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Matching with PROSAC " Progressive Sample Consensus

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Photo tourism: exploring photo collections in 3D

ACM SIGGRAPH 2006 Papers
Scene completion using millions of photographs

ACM SIGGRAPH 2007 papers
A Comparative Analysis of RANSAC Techniques Leading to Adaptive Real-Time Random Sample Consensus

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
A Fast and Effective Dichotomy Based Hash Algorithm for Image Matching

ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper aims at outliers screening for the feature correspondence in image matching. A novel robust matching method, called topology constraint sample consensus (TOCSAC), is proposed to speed up the matching process while keeping the matching accuracy. The TOCSAC method comprises of two parts, the first of which is the constraint of points order, which should be invariant to scale, rotation and view point change. The second one is a constraint of affine invariant vector, which is also used to validate in similar and affine transforms. Comparing to the classical algorithms, such as RANSAC (random sample consensus) and PROSAC (progressive sample consensus), the proposed TOCSAC can significantly reduce time cost and improve the performance for wide base-line image correspondence.