Model-based image matching using location
Model-based image matching using location
HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
New methods for matching 3-D objects with single perspective views
IEEE Transactions on Pattern Analysis and Machine Intelligence
Localizing Overlapping Parts by Searching the Interpretation Tree
IEEE Transactions on Pattern Analysis and Machine Intelligence
Decision estimation and classification: an introduction to pattern recognition and related topics
Decision estimation and classification: an introduction to pattern recognition and related topics
On the Sensitivity of the Hough Transform for Object Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Linear programming and convex hulls made easy
SCG '90 Proceedings of the sixth annual symposium on Computational geometry
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
Space and Time Bounds on Indexing 3D Models from 2D Images
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
Visual tracking of known three-dimensional objects
International Journal of Computer Vision
Robust model-based motion tracking through the integration of search and estimation
International Journal of Computer Vision
Polynomial-time geometric matching for object recognition
Polynomial-time geometric matching for object recognition
Massively parallel Bayesian object recognition
Massively parallel Bayesian object recognition
Perceptual Organization and Visual Recognition
Perceptual Organization and Visual Recognition
3-D Pose from 3 Points Using Weak-Perspective
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Study of Affine Matching With Bounded Sensor Error
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Polynomial-Time Object Recognition in the Presence of Clutter, Occlusion, and Uncertainty
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
A Paraperspective Factorization Method for Shape and Motion Recovery
ECCV '94 Proceedings of the Third European Conference-Volume II on Computer Vision - Volume II
Three-Dimensional Recognition of Solid Objects from a Two- Dimensional Image
Three-Dimensional Recognition of Solid Objects from a Two- Dimensional Image
Statistical Object Recognition
Statistical Object Recognition
Robust and Efficient 3D Recognition by Alignment
Robust and Efficient 3D Recognition by Alignment
Recognizing 3-D Objects Using 2-D Images
Recognizing 3-D Objects Using 2-D Images
Paraperspective ? Affine
Introduction: Computer Vision Research at NECI
International Journal of Computer Vision - Special issue on computer vision research at NEC Research Institute
3-D to 2-D Pose Determination with Regions
International Journal of Computer Vision - Special issue on computer vision research at NEC Research Institute
Predicting Performance of 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
A General Method for Feature Matching and Model Extraction
ICCV '99 Proceedings of the International Workshop on Vision Algorithms: Theory and Practice
Implementation techniques for geometric branch-and-bound matching methods
Computer Vision and Image Understanding
| Hi-index | 0.00 |
Robust recognition systems require a careful understanding of theeffects of error in sensed features. In model-based recognition, matchesbetween model features and sensed image features typically are used tocompute a model pose and then project the unmatched model features into theimage. The error in the image features results in uncertainty in theprojected model features. We first show how error propagates when poses arebased on three pairs of 3D model and 2D image points. In particular, we showhow to simply and efficiently compute the distributed region in the imagewhere an unmatched model point might appear, for both Gaussian and boundederror in the detection of image points, and for both scaled-orthographic andperspective projection models. Next, we provide geometric and experimentalanalyses to indicate when this linear approximation will succeed and when itwill fail. Then, based on the linear approximation, we show how we canutilize Linear Programming to compute bounded propagated error regions forany number of initial matches. Finally, we use these results to extend, fromtwo-dimensional to three-dimensional objects, robust implementations ofalignment, interpretation-tree search, and transformation clustering.