Name
Abstract | ||
|---|---|---|
We present an object recognition algorithm that uses model and image line features to locate complex objects in high clutter environments. Finding correspondences between model and image features is the main challenge in most object recognition systems. In our approach, corresponding line features are determined by a three-stage process. The first stage generates a large number of approximate pose hypotheses from correspondences of one or two lines in the model and image. Next, the pose hypotheses from the previous stage are quickly ranked by comparing local image neighborhoods to the corresponding local model neighborhoods. Fast nearest neighbor and range search algorithms are used to implement a distance measure that is unaffected by clutter and partial occlusion. The ranking of pose hypotheses is invariant to changes in image scale, orientation, and partially invariant to affine distortion. Finally, a robust pose estimation algorithmis applied for refinement and verification, starting from the few best approximate poses produced by the previous stages. Experiments on real images demonstrate robust recognition of partially occluded objects in very high clutter environments. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1109/ICCV.2005.173 | ICCV |
Keywords | Field | DocType |
local image neighborhood,previous stage,real image,line features,object recognition,image scale,high clutter,high clutter environment,image line feature,corresponding local model neighborhood,image feature,object recognition algorithm,object recognition system,nearest neighbor,search algorithm,image features,pose estimation,feature extraction | Affine transformation,Computer vision,Pattern recognition,Clutter,Computer science,Feature (computer vision),3D pose estimation,Pose,Feature extraction,Artificial intelligence,Real image,Cognitive neuroscience of visual object recognition | Conference |
ISSN | ISBN | Citations |
1550-5499 | 0-7695-2334-X-02 | 32 |
PageRank | References | Authors |
1.34 | 10 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Philip David | 1 | 111 | 6.10 |
| Daniel Dementhon | 2 | 1327 | 139.94 |