Name
Abstract | ||
|---|---|---|
The task of identifying 3D objects in 2D images is difficult due to variation in objects' appearance with changes in pose and lighting. The task is further complicated by the presence of occlusion and clutter. Shape indexing is a method for rapid association between features identified in an image and their corresponding 3D features stored in a database. Previous indexing methods ignored variations due to lighting, restricting the approach to polyhedral objects. In this paper, we further develop these methods to handle variations in both pose and lighting. We focus on rigid objects undergoing a scaled-orthographic projection and use spherical harmonics to represent lighting. The resulting integrated algorithm can recognize 3D objects from a single input image; furthermore, it recovers the pose and lighting of each familiar object in the given image. The algorithm has been tested on a database of real objects, demonstrating its performance on cluttered scenes under a variety of poses and illumination conditions. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1109/CVPR.2005.186 | Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference |
Keywords | Field | DocType |
feature extraction,object recognition,visual databases,2D image,3D feature,cluttered scene,integrated algorithm,objects identification,scaled-orthographic projection,shape indexing,spherical harmonics | Computer vision,Pattern recognition,Clutter,Computer science,Spherical harmonics,Search engine indexing,Image-based lighting,Feature extraction,Artificial intelligence,Cognitive neuroscience of visual object recognition | Conference |
Volume | ISSN | ISBN |
1 | 1063-6919 | 0-7695-2372-2 |
Citations | PageRank | References |
2 | 0.37 | 19 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ira Kemelmacher-Shlizerman | 1 | 710 | 28.03 |
| Ronen Basri | 2 | 3467 | 403.18 |