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
Model-based invariants for 3-D vision
International Journal of Computer Vision
Trilinearity in visual recognition by alignment
ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
Matching 3-D Models to 2-D Images
International Journal of Computer Vision
Dual Computation of Projective Shape and Camera Positions from Multiple Images
International Journal of Computer Vision
View Variation of Point-Set and Line-Segment Features
IEEE Transactions on Pattern Analysis and Machine Intelligence
Limitations of Non Model-Based Recognition Schemes
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Complexity of Indexing: Efficient and Learnable Large Database Indexing
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Invariants of 6 Points from 3 Uncalibrated Images
ECCV '94 Proceedings of the Third European Conference-Volume II on Computer Vision - Volume II
Shape tensors for efficient and learnable indexing
VSR '95 Proceedings of the IEEE Workshop on Representation of Visual Scenes
On the geometry and algebra of the point and line correspondences between N images
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
The study of 3D-from-2D using elimination
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
Model-based invariants are relations between modelparameters and image measurements, which are independent of theimaging parameters. Such relations are true for all images ofthe model. Here we describe an algorithm which, given L independent model-based polynomial invariants describing someshape, will provide a linear re-parameterization of theinvariants. This re-parameterization has the properties that: (i) it includes the minimal number of terms, and (ii) theshape terms are the same in all the model-basedinvariants. This final representation has 2 main applications: (1) it gives new representations of shape in terms ofhyperplanes, which are convenient for object recognition; (2) itallows the design of new linear shape from motion algorithms. Inaddition, we use this representation to identify object classesthat have universal invariants.