Partial Shape Recognition: A Landmark-Based Approach
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Bivariate Autoregressive Technique for Analysis and Classification of Planar Shapes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Determining perceptually significant points on noisy boundary curves
Pattern Recognition Letters
Analysis of 2-D Occlusion by Subtracting Out
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern recognition using evolution algorithms with fast simulated annealing
Pattern Recognition Letters
Unsupervised Clustering in Hough Space for Identification of Partially Occluded Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
On the Recognition and Location of Partially Occluded Objects
Journal of Intelligent and Robotic Systems
Invariant Representation and Matching of Space Curves
Journal of Intelligent and Robotic Systems
IEEE Transactions on Pattern Analysis and Machine Intelligence
Ordinal-measure based shape correspondence
EURASIP Journal on Applied Signal Processing - Image analysis for multimedia interactive services - part I
A sequential algorithm for motion estimation from point correspondences with intermittent occlusions
ICIP '95 Proceedings of the 1995 International Conference on Image Processing (Vol.2)-Volume 2 - Volume 2
Computer Vision and Image Understanding
Information-Theoretic Active Polygons for Unsupervised Texture Segmentation
International Journal of Computer Vision
Ordinal-measure based shape correspondence
EURASIP Journal on Applied Signal Processing
Probabilistic Models of Object Geometry with Application to Grasping
International Journal of Robotics Research
Matching occluded objects invariant to rotations, translations, reflections, and scale changes
SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
Occluded 3d object recognition using partial shape and octree model
ICIC'05 Proceedings of the 2005 international conference on Advances in Intelligent Computing - Volume Part I
Hi-index | 0.15 |
We present computer vision algorithms that recognize and locate partially occluded objects. The scene may contain unknown objects that may touch or overlap giving rise to partial occlusion. The algorithms revolve around a generate-test paradigm. The paradigm iteratively generates and tests hypotheses for compatibility with the scene until it identifies all the scene objects. Polygon representations of the object's boundary guide the hypothesis generation scheme. Choosing the polygon representation turns out to have powerful consequences in all phases of hypothesis generation and verification. Special vertices of the polygon called ``corners'' help detect and locate the model in the scene. Polygon moment calculations lead to estimates of the dissimilarity between scene and model corners, and determine the model corner location in the scene. An association graph represents the matches and compatibility constraints. Extraction of the largest set of mutually compatible matches from the association graph forms a model hypothesis. Using a coordinate transform that maps the model onto the scene, the hypothesis gives the proposed model's location and orientation. Hypothesis verification requires checking for region consistency. The union of two polygons and other polygon operations combine to measure the consistency of the hypothesis with the scene. Experimental results give examples of all phases of recognizing and locating the objects.