The representation, recognition, and locating of 3-d objects
International Journal of Robotics Research
Structural Indexing: Efficient 3-D Object Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
A Method for Registration of 3-D Shapes
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
Object modelling by registration of multiple range images
Image and Vision Computing - Special issue: range image understanding
Describing Complicated Objects by Implicit Polynomials
IEEE Transactions on Pattern Analysis and Machine Intelligence
Building 3-D models from unregistered range images
Graphical Models and Image Processing
Multiresolution analysis of arbitrary meshes
SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Geometry of harmonic maps
COSMOS-A Representation Scheme for 3D Free-Form Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Spherical Representation for Recognition of Free-Form Surfaces
IEEE Transactions on Pattern Analysis and Machine Intelligence
Triangles as a Primary Representation
Proceedings of the International NSF-ARPA Workshop on Object Representation in Computer Vision
Multi-Scale Classification of 3-D Objects
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Efficient Multiple Model Recognition in Cluttered 3-D Scenes
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Local shape descriptor selection for object recognition in range data
Computer Vision and Image Understanding
3D polar-radius invariant moments and structure moment invariants
ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part II
| Hi-index | 0.00 |
A new representation called Harmonic Shape Images for 3D free-form surfaces is proposed in this paper. This representation is based on the well-studied theory of Harmonic Maps which studies the mapping between different metric manifolds from the energyminimization point of view. The basic idea of Harmonic Shape Images is to map a 3D surface patch with disc topology to a 2D domain and encode the shape information of the surface patch into the 2D image. Due to the application of harmonic maps in generating Harmonic Shape Images, Harmonic Shape Images have the following advantages: they preserve both the shape and the continuity of the underlying surfaces, they are robust to occlusion and they are independent of surface sampling strategy. The proposed representation is applied to solve the surface-registration problem. Experiments have been conducted on real data and results are presented in the paper.