A Stereo Vision Technique Using Curve-Segments and Relaxation Matching
IEEE Transactions on Pattern Analysis and Machine Intelligence
Artificial Intelligence - Special volume on computer vision
A Bayesian approach to binocular stereopsis
International Journal of Computer Vision
The Dynamics of Nonlinear Relaxation Labeling Processes
Journal of Mathematical Imaging and Vision
Determining the Epipolar Geometry and its Uncertainty: A Review
International Journal of Computer Vision
Three D-Dynamic Scene Analysis: A Stereo Based Approach
Three D-Dynamic Scene Analysis: A Stereo Based Approach
Epipolar Geometry in Stereo, Motion, and Object Recognition: A Unified Approach
Epipolar Geometry in Stereo, Motion, and Object Recognition: A Unified Approach
Structural Matching in Computer Vision Using Probabilistic Relaxation
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Progressive Scheme for Stereo Matching
SMILE '00 Revised Papers from Second European Workshop on 3D Structure from Multiple Images of Large-Scale Environments
Automatic line matching across views
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
A similarity measure for stereo feature matching
IEEE Transactions on Image Processing
Contextual Inference in Contour-Based Stereo Correspondence
International Journal of Computer Vision
Fuzzy Cognitive Maps for stereovision matching
Pattern Recognition
Kernel PCA for similarity invariant shape recognition
Neurocomputing
Hi-index | 0.00 |
Reliable curve matching is a difficult yet important problem in many vision-based applications including image-based modeling. We describe in this paper two aspects of our research in this area: a new algorithm for curve matching (including lines) within a probabilistic relaxation framework, and an approach of incorporating previously matched points/corners to guide curve matching. We propose similarity-invariant unary and binary measurements suitable for curves, and introduce an additional measurement to model the uncertainty of the binary measurements. The uncertainty measure is proven to be very important in computing the matching support from neighboring matches. We also show how to use a set of previously matched points/corners to guide the curve matching. The role of the corner guidance is explicitly modeled by a set of unary measurements and a similarity function under the same relaxation framework. Preprocessing techniques contributing to the success of our curve matching techniques are also developed and discussed. Experiments with complex real scenes show that the rate of correct matching is higher than 98%.