Model-based image matching using location
Model-based image matching using location
Computational geometry: an introduction
Computational geometry: an introduction
HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
Localizing Overlapping Parts by Searching the Interpretation Tree
IEEE Transactions on Pattern Analysis and Machine Intelligence
Algorithms in combinatorial geometry
Algorithms in combinatorial geometry
Combinatorial optimization: algorithms and complexity
Combinatorial optimization: algorithms and complexity
Congruence, similarity and symmetries of geometric objects
Discrete & Computational Geometry - ACM Symposium on Computational Geometry, Waterloo
The combinatorics of object recognition in cluttered environments using constrained search
Artificial Intelligence
Recognizing solid objects by alignment with an image
International Journal of Computer Vision
Recognition by Linear Combinations of Models
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
Matching points into noise regions: combinatorial bounds and algorithms
SODA '91 Proceedings of the second annual ACM-SIAM symposium on Discrete algorithms
Polynomial-time geometric matching for object recognition
Polynomial-time geometric matching for object recognition
Recognizing 3-D objects using 2-D images
Recognizing 3-D objects using 2-D images
SCG '94 Proceedings of the tenth annual symposium on Computational geometry
Approximate decision algorithms for point set congruence
Computational Geometry: Theory and Applications
A Bayesian approach to model matching with geometric hashing
Computer Vision and Image Understanding
Measuring the Quality of Hypotheses in Model-Based Recognition
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Robust Affine Structure Matching for 3D Object Recognition
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
An Efficient Correspondence Based Algorithm for 2D and 3D Model Based Recognition
An Efficient Correspondence Based Algorithm for 2D and 3D Model Based Recognition
Robust Affine Structure Matching for 3D Object Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
A General Method for Geometric Feature Matching and Model Extraction
International Journal of Computer Vision
Geometry and texture recovery of scenes of large scale
Computer Vision and Image Understanding
A General Method for Feature Matching and Model Extraction
ICCV '99 Proceedings of the International Workshop on Vision Algorithms: Theory and Practice
A Probabilistic Formulation for Hausdorff Matching
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
International Journal of Computer Vision
Robust Optimal Pose Estimation
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Pose sampling for efficient model-based recognition
ISVC'07 Proceedings of the 3rd international conference on Advances in visual computing - Volume Part II
A systematic approach for 2D-image to 3D-range registration in urban environments
Computer Vision and Image Understanding
Robust fitting for multiple view geometry
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
| Hi-index | 0.00 |
This paper considers the task of recognition and positiondetermination, by computer, of a 2D or 3D object where the inputis a single 2D brightness image, and a model of the objectis known a priori. The primary contribution of this paperis a novel formulation and methods for local geometric featurematching. This formulation is based on analyzing geometricconstraints on transformations of the model features whichgeometrically align it with a substantial subset of imagefeatures. Specifically, the formulation and algorithms forgeometric feature matching presented here provide a guaranteed method for finding all feasibleinterpretations of the data in terms of the model. This methodis robust to measurement uncertainty in the data features and tothe presence of spurious scene features, and its time and spacerequirements are only polynomial in the size of the featuresets. This formulation provides insight into the fundamentalnature of the matching problem, and the algorithms commonly usedin computer vision for solving it.