Loading...
Please wait, while we are loading the content...
Similar Documents
Three-Dimensional Object Recognition from Single Two-Dimensional Images (1987)
| Content Provider | CiteSeerX |
|---|---|
| Author | Lowe, David G. |
| Abstract | A computer vision system has been implemented that can recognize three-dimensional objects from unknown viewpoints in single grayscale images. Unlike most other approaches, the recognition is accomplished without any attempt to reconstruct depth information bottom-up from the visual input. Instead, three other mechanisms are used that can bridge the gap between the two-dimensional image and knowledge of three-dimensional objects. First, a process of perceptual organization is used to form groupings and structures in the image that are likely to be invariantover a wide range of viewpoints. Second, a probabilistic ranking method is used to reduce the size of the search space during model based matching. Finally, a process of spatial correspondence brings the projections of three-dimensional models into direct correspondence with the image by solving for unknown viewpoint and model parameters. A high level of robustness in the presence of occlusion and missing data can be ac... |
| File Format | |
| Volume Number | 31 |
| Journal | ARTIFICIAL INTELLIGENCE |
| Language | English |
| Publisher Date | 1987-01-01 |
| Access Restriction | Open |
| Subject Keyword | Three-dimensional Object Recognition Single Two-dimensional Image Three-dimensional Object Unknown Viewpoint Two-dimensional Image Model Parameter Computer Vision System High Level Direct Correspondence Search Space Probabilistic Ranking Method Three-dimensional Model Spatial Correspondence Perceptual Organization Wide Range Depth Information Bottom-up Visual Input Single Grayscale Image |
| Content Type | Text |
| Resource Type | Article |
